This PDF file contains the front matter associated with SPIE Proceedings Volume 12977, including the Title Page, Copyright information, Table of Contents, and Conference Committee information.

The surge in urban vehicular traffic volume over the past decade has led to an uptick of traffic accidents in busy streets and thoroughfares. These accidents resulted in fatalities, damages to properties, and economic losses. Despite its huge impact on our livelihood, a meaningful spatiotemporal analysis of traffic accident hotspots in urban cities in the Philippines, like Quezon City, remains scarce until now. An additional constraint to performing such analysis is the inaccessibility of relevant data collected by concerned government agencies. To address this issue, this study aims to identify locations where traffic accidents mostly occur (hotspots) in Quezon City, and observe their temporal behavior for a 27-week period using publicly available data gathered from the official Twitter account of the Metro Manila Development Authority (MMDA). Accident locations were extracted from each tweet using natural language processing (NLP) techniques and were subjected to a set of spatial statistics to locate and map accident hotspots. Our analyses show that there is significant spatial clustering of traffic accident locations in Quezon City for the 27-week time series obtained. A stable hotspot was detected along EDSA North Avenue, a disappearing hotspot was found along Commonwealth Litex, and an emerging hotspot was observed along CP Garcia Avenue. The method that we proposed in this study can help promote a data-driven approach to policy making, and encourage the use of publicly available data from social media platforms to uncover insights about vehicular traffic accidents in real-time.

The population growth will drive changes in land use due to the increasing need for housing, industry, and public facilities. A common phenomenon in urban and suburban areas is the conversion of land into built-up areas, known as urban growth or urban expansion. Uncontrolled urban growth can lead to various negative impacts on natural resources, economic conditions, communities, and the environment. According to Government Regulation Number 26 of 2007, the Medan- Binjai-Deli Sedang-Karo (Mebidangro) urban area is one of the National Strategic Areas (KSN) from an economic perspective on Sumatra Island. Mebidangro has a rapidly developing metropolitan area, which requires spatial-temporal monitoring of urban growth to support sustainable urban development processes. Remote sensing enables monitoring and analysis of the dynamics of urban growth in a large area to be carried out quickly. This study aims to analyze the dynamics of the intensity and pattern types of urban growth in Mebidangro by utilizing multi-temporal remote sensing data from 2000 to 2022. The analysis is done in two periods, 2000-2011 and 2011-2022, so that comparisons can be made between the two results. Landsat TM, ETM+, and OLI images were used to map built-up areas using object-based classification. Then, the Landscape Expansion Index (LEI) is used to quantify types of urban growth patterns, such as infilling, edge-expansion, and outlying. Based on the analysis, the pattern of urban development showed a dynamic change in proportion over time. Moreover, the high intensity of urban expansion is mostly found in core city, Additionally, from AWMEI and MEI calculation, the urban expansion characteristics in Mebidangro tends to be disperse.

The Trans Jogja Bus system is an essential urban transportation service in Yogyakarta and its surrounding areas. With numerous bus stops strategically located throughout the Yogyakarta Urban Area, it aims to provide convenient boarding and disembarkation points for passengers. To improve the commuting experience for passengers, it is crucial to ensure that the Trans Jogja shelters are easily accessible and equipped with a comprehensive range of amenities, covering all regions within the urban area. To evaluate the service level of Trans Jogja Bus stops, the service area from each bus stop is modeled as an interactive isochronous service area map. These maps depict the coverage area of each bus stop based on network analysis, considering travel time to the road network. Each bus stop is a single node with four distinct travel time values: 3, 6, 9, 12, and 15 minutes. By employing this interactive modeling approach, the service areas of Trans Jogja bus stops can be presented, along with other variables representing the population in and around these bus stops. The resulting interactive visualization of these isochrone maps showcases the spatial distribution of the bus stop locations and their respective service areas at each travel time interval. This web-based visualization represents the coverage provided by the Trans Jogja bus system across the Yogyakarta urban area. The service area modeling using isochronous service area maps a comprehensive overview of the services offered by Trans Jogja bus stops in Yogyakarta, giving a clear depiction of the accessible amenities around each bus stops. It supports efforts to optimize service accessibility and quality, ensuring a seamless and efficient transportation experience for passengers.

Despite an extensive network, public transportation in Jakarta struggles with inclusive mobility due to spatial disparities. Rapid urbanization since the 1960s led to economic-driven housing, granting some privileged groups easy access to city center amenities, while leaving others disconnected from economic hubs due to inadequate multimodal transport. To further investigate this issue, this study uses spatial autocorrelation to explore economic clustering based on housing types, followed by network analysis of multimodal urban transport accessibility and isochrone of activity centers using ArcGIS Pro and QGIS. The data used includes public transportation networks and integrated JakLingko programs, such as railbased transportation (KRL, MRT, LRT) and road-based public transportation (TransJakarta, mikrotrans, Royaltrans), followed by the 2022 Spatial Masterplan (RDTR) of DKI Jakarta, administration boundary (RT and RW level), Google Earth Imagery, and published statistics provided by Statistics Indonesia (BPS). Our findings show a correlation between the economic clustering of certain housing blocks and their access to public transportation. Middle to upper-class groups living in Central Jakarta tend to have better access to public transportation than those scattered around Jakarta. We argue that there is a need to reassess Jakarta's existing urban transportation network to develop an inclusive urban transportation system that would allow all city residents living in various residential areas to utilize public transit effectively.

The COVID-19 pandemic has had a huge impact on Indonesia, as many other nations throughout the globe, particularly on the travel and tourism industry. The most noticeable effect is the decline in tourist visitation, which fell by over 75% in 2020 compared to the prior year. Businesses and workers in the tourism industry have been significantly impacted by the fall in visitor numbers, particularly in Yogyakarta, one of the most well-liked tourist sites in the nation. This study intends to investigate the geographical effects of the COVID-19 pandemic on tourism-related activities. A strategy to determine changes in travel behaviour before and during the COVID-19 pandemic uses social media data, such as Flickr and Twitter. Both social media has been extensively used in tourism related studies in the past. Because December is the busiest month for tourism, Twitter data from that month was chosen as the sample. The selected sample ranges are for 2019, 2020, and 2021. While Flickr data covers from 2018 to 2023, to generate a different perspective than that of Twitter data. The study's findings demonstrate how limitations on community activities significantly influence the traditionally popular tourist attractions. Public spaces, dining establishments, and even hotels are preferred travel destinations by tourists.

Every year, Jakarta, the capital of Indonesia, always experiences flooding. When natural disasters such as floods occur, the government is obliged to carry out a series of disaster emergency responses, one of which is disaster modeling. Disaster modeling can be done with various data sources, but field survey data sources, remote sensing, and aerial photographs are considered less efficient to use. Field surveys require a longer time, while remote sensing and aerial photography have limitations during the rainy season, which is disrupted due to high cloud intensity. Social media, especially Twitter, has currently received a lot of attention from various groups as a source of data for flood modeling. This research aims to build a spatial database, perform flood modeling, test the level of accuracy produced, and test tweet data with rain events in Jakarta. Flood modeling is carried out with the Kernel-Based Flood Mapping Model method using DEMNAS data, river distribution data, administrative boundaries, water depth data at each river floodgate, tweet data, BPBD flood area maps, and surface observation rainfall data issued by BMKG. The results of flood modeling were tested for accuracy with the overall accuracy method against all tweet data obtained and BPBD flood area maps. In addition, a regression test was conducted to determine the relationship between rainfall and tweet data related to flooding in Jakarta. The results showed that 149 out of 12,345 tweets could be compiled into a database that was used as the basis for modeling. Flood modeling results show an accuracy value of 70% based on the calculation of total flood points and 57% based on BPBD flood zones, this value is in a low category. The regression test between flood points and January rainfall data shows a relationship that does not affect. The regression test value between rainfall at the flood location and the number of tweets is 0.020822, while the flood depth is 0.049214, which means that the rainfall variable only affects the variable number of tweets by 2% and the depth of the flood by 4.9% and the rest is influenced by other factors.

The designation of a geographical location serves as a significant historical reference for understanding the socio-cultural and physical characteristics of a certain area. The process of mapping geographical names can offer valuable insights into several aspects, including cultural legacy, linguistic diversity, patterns of migration, and dynamics of metropolitan areas. The disparities observed in geographical nomenclature between ancient maps and contemporary maps might enhance the robustness of historical data by visually illustrating the transformations that have transpired over time. Hence, the objectives of this research endeavor are: The objectives of this study are as follows: 1.) To acquire information on the state of the maps and the completeness of toponymic information in the historical maps that were utilized. 2.) To quantify the number of geographical names that can be derived from these maps. 3.) To compare the number of geographical names extracted from the historical maps with those found in more modern maps. The primary focus of this study included the digitization of geographical names extracted from historical topographic maps. These maps were sourced from the Topografische Dienst van Nederlands Indië, dated 1889, the Army Maps Service, dated 1943, and the Indonesian official topographic maps (Peta Rupabumi Indonesia-RBI), dated 2014. The findings of this research project have yielded a comprehensive geo-database including the names of Nagari in Agam Regency, spanning the years 1889, 1943, and 2014.

Infrastructure development and industry are a bridge in driving economic growth. On the other hand, the impact of development and population growth also encourages land conversion and suppresses the existence of agricultural land. This research aims to analyze land use change from 2015 to 2021 in Kulon Progo Regency and its relationship with occupation. This study used spatial analysis through overlay to map land use changes in Kulon Progo Regency. Land use maps were obtained from Sentinel images in 2015 and 2021. Image interpretation was supervised through the random forest algorithm. Meanwhile, occupation change data was obtained from Yogyakarta population statistics. Descriptive quantitative analysis is used to determine the relationship between the decline in agricultural land and the decline in the number of occupation in the agricultural sector. The result shows that the impact of development and industry has changed rice fields in Kulon Progo Regency from 26,530.29 Ha in 2015 to only 20,507.70 Ha in 2021. The reduction in rice fields in this regency was also followed by a change in the community occupations, from 48.25% of them working in the agrarian sector in 2015 to only 41.62% in 2021. The decrease in uncontrolled agricultural land area is feared to cause a decline in farmers' welfare and the threat of food availability

The Caraga Region in Mindanao, Philippines, is a key contributor to fiber production due to its Abaca (Musa Textilis) plantations. In 2020, Caraga Region produced more than 14% of the country's Abaca Fiber. The most concerning difficulty for tree farmers is locating a suitable area for establishing new plantations. This study uses Ecocrop, Domain, MaxEnt, and MCDA models to generate suitability maps for abaca plantations. This study also uses a total of 395 Abaca location points distributed in the region, biophysical factors (i.e., Elevation, Soil Type, Aspect, LULC, and the like), and bioclimatic factors (i.e., Maximum and Minimum Temperature, and Annual Precipitation, among others). The result was intersected to quantify the most suitable areas using GIS spatial analysis based on the four models. The ability of the four techniques to model suitable land areas was executed and investigated. After the result of each model, it shows that 28.93 % of the total land area of the Caraga Region is suitable for abaca plantations. In terms of suitability area per province, Surigao del Sur has more Abaca suitable land area with 11.64 %, followed by Agusan del Sur, Agusan del Norte, Surigao del Norte, and Dinagat Islands containing 7.58 %, 5.39 %, 3.03%, and 1.27% respectively.

This research aimed to map land-use in Riau Province using a landscape ecological approach and to assess the level of landscape fragmentation using fragmentation index, edge density, and landscape metrics at observation window sizes of 3×3, 5×5, and 7×7 pixels. Sentinel-2A imagery was the primary input for land-cover mapping, while SRTM DEM was used as the input for terrain unit mapping. The land-cover and terrain unit maps were overlaid to create a land-use map. This map was then used as an input for spatial analysis of fragmentation by computing the fragmentation index and edge density. Another analysis that has been carried out was landscape metrics calculation. The results of the land-use mapping revealed that the study area is predominantly occupied by plantations and forests, with an overall accuracy of 81.88%. The landscape fragmentation analysis showed that areas with high fragmentation level are scattered in the central part of the region, characterized by dense human activity in heterogeneous land-use types. Meanwhile, low fragmentation levels found in homogeneous land-use areas such as natural and semi-natural forests.

Cultural landscapes reflect humanity's creative genius, social evolution, imagination, and spiritual life. The city of Yogyakarta in Indonesia is an ideal example of a cultural landscape reflecting the works of Hindu-Buddhist, Islamic, colonial, reform to contemporary civilization. Reconstructing historical landscapes and regions is critical for preserving historical memory. Geographical names are a possible way to build community identities. Our research aims to trace the multitemporal landscape from historical maps in Yogyakarta. This study conducted a comparative cartographic analysis of several historical maps of Yogyakarta City, focusing on some of the critical changes and phases during the era. We used topographic maps produced by the Topografische Dienst of the Dutch East Indies, the US Army Map Services, and the Indonesian Geospatial Information Agency to trace the historical landscape in Yogyakarta City. We digitized geographical names as they were presented on the historical maps. Indonesia Geographical Features Cataloging was followed to create a geodatabase. The results of this study showed how the dynamics of geographical names change based on historical map tracing. Additionally, there have been changes in the territory boundaries. This dataset of historical geographical names can serve as a database for preserving cultural heritage and as a basis for sustainable development in Yogyakarta City.

Nusantara is a city currently under construction to serve as the future capital city of Indonesia, replacing DKI Jakarta. It is located on the island of Kalimantan/Borneo, approximately 1200 Km away from DKI Jakarta on the island of Java. Initially, a significant portion of the Nusantara Capital City was covered with forests and vegetation. The objective of this study is to assess the land cover changes occurring in the Nusantara Capital City using multi-temporal remote sensing satellite imagery. The satellite images used in this study are obtained from Planet's Doves satellite, which consists of four bands (Blue, Green, Red, and Near Infra-Red), as well as SuperDove, which offers eight bands (Ocean Blue, Blue, Green I, Green, Yellow, Red, Red Edge, and Near Infra-Red). Despite being categorized as small satellites, they have a high spatial resolution of 3-5 meters. Remote sensing indices were used to facilitate the land cover classification in areas of interest (AoI), especially the normalized difference vegetation index (NDVI), considering the nature of the land cover. Land cover changes from several different times, starting from 2021, were compared to determine the extent of changes that have occurred. The carbon stock loss in Nusantara was also approximated quarterly using NDVI. As of June 2023, the results indicate that approximately 8.3% of the total AoI has experienced a loss in vegetation, with the most significant decline observed in March 2023. These findings contribute to expanding our understanding of the evolving landscape in the Nusantara Capital City.

Remote sensing data has been proven capable and efficient as a powerful resource for large-scale land cover mapping. However, a map is considered acceptable with the required accuracy value. The problem related to sampling is how the sample amount and sample technique affect the accuracy of the land cover mapping. Furthermore, the accuracy assessment for mapping usually only utilizes accuracy measurement standards, which are commonly used. This research was conducted to measure the effect of the different sampling sizes and sampling methods on the accuracy value of largescale land cover mapping using area based assessment approach. A visual interpretation was used as a reference while multispectral classification was carried out independently as an object to be tested for accuracy assessment. The number of classes interpreted was 25 and 9. We demonstrated the sampling methods applied were random sampling, stratified random sampling, and systematic grid sampling. A confusion matrix method was used to gain the overall accuracy. The result of this study showed that the number of 200 samples for land cover with 25 classes and 36 sample for nine classes could start the regularity against the actual accuracy. While the sample number below 200 and 36 for both land cover classes showed irregular fluctuations in the accuracy value. Using stratified random sampling was satisfactory for modeling the accuracy compared to random and systematic grid sampling. Thus, those results could be used to indicate accuracy value against different scenarios and gain a recommendation for assessing the accuracy of land cover on a large scale.

Precision agriculture is an integrated farming system based on information and production, to increase the efficiency, productivity and profitability of agricultural production. The application of remote sensing for monitoring rice growth and calculating rice yields is considered more effective than conventional calculation methods. This study aims to review the application of remote sensing for mapping paddy fields and forecasting rice production. The review includes rice characteristics that can be sensed through remote sensing images, types of images, rice yield estimation models, and remote sensing analysis approaches. The study shows that optical and radar images are capable of mapping paddy fields and providing information on rice production by relying on the phenological of rice. Empirical, process-based, and semi-empirical estimation models provide information with different levels of accuracy and scale. The spatial ecological approach is able to examine the relationship between the suitability of paddy fields and production yields, while the spectral approach relies on the transformation of the vegetation index with production yields. Research on rice yield estimation is suggested to go to the field to test the accuracy of mapping paddy fields and interview farmers to obtain data on rice production.

The advancement of remote sensing image acquisition through Unmanned Aerial Vehicles (UAVs) has seen rapid growth in the last five years, particularly in the field of agricultural mapping. The inclusion of multispectral sensors on UAVs holds potential and capabilities for distinguishing different growth stages of rice crops. However, with respect to this objective, there has been limited research investigating pixel-based and object-based classification approaches using multispectral UAV data. This study aims to assess the capabilities of multispectral aerial photos in identifying rice crop growth stages through both pixel-based and object-based classification methods within a portion of the Banyubiru Subdistrict, Semarang Regency. The Support Vector Machine (SVM) method is employed for pixel-based classification, while the object-based classification (OBIA) process employs the Segment Mean Shift algorithm for segmentation. Training samples and data accuracy are obtained through visual interpretation based on the developed orthomosaic data. Four rice crop growth stages are mapped, namely vegetative, reproductive, ripening, and bare-land phases. The two approaches yield differing accuracy performance. The pixel based approach using support vector machine (SVM) achieves an accuracy of 45% with a kappa coefficient of 0.28, whereas the Object Based Image Analysis (OBIA) approach attains an accuracy of 37% with a kappa coefficient of 0.24. The results indicate that, in this case, the pixel-based approach (SVM) demonstrates higher accuracy compared to the Object Based Image Analysis (OBIA) approach. However, the low accuracy indicates the limitations of pixel based image analysis using spectrometer inputs for mapping using UAV datasets.

The Philippines has made significant strides in developing its rice production sustainably, which has contributed to the nation's food security and sustainable agriculture. However, the sector faces various obstacles, and ensuring its long-term viability is crucial. For this reason, building a tool that allows estimating rice yield is necessary. Synthetic Aperture Radar (SAR) remote sensing data from Sentinel-1 satellites provide no cost, extensive coverage, and high spatiotemporal resolution, which has the advantage of observation in cloudy, foggy, rainy weather and independent of solar radiation. This study aimed to delineate rice crop fields and estimate the rice yield in the Rice Granary Capital of Agusan del Sur – Bayugan City, using multi-temporal Sentinel-1 data with C-band wavelength. Predictor variables derived from the Sentinel-1 image were used to model the rice yield: the VV and VH polarization backscatter value and the GLCM of VV and VH polarizations. The results showed that VH polarization produces the highest kappa coefficient of 0.93 and overall accuracy of 96.5% in delineating rice fields using the Maximum Likelihood classifier. An exponential solid relationship has been identified between the VH polarization and rice yield, producing accurate yield estimation with the highest coefficient of determination (R²) of 0.83 and the lowest root mean square error (RMSE) value of 5.29. The generated map showed the estimated rice yield value of 100.60 sacks/ha to 128.62 sacks/ha, with an average yield of 112.04 sacks/ha. Therefore, it seems reasonable to conclude that Sentinel-1A effectively estimates rice yield with its large-scale polarization's backscatter information.

Slash-and-burn agriculture or kaingin is a method of clearing and burning of forest for the planting of agricultural and agro-forestry crops. Observed effects of kaingin are destruction of forests, grassland fires due to uncontrolled or accidental fires, degraded soil, cultivation leaching, massive erosion and landslide. This study utilizes Fire Information for Resource Management System (FIRMS), Moderate Resolution Imaging Spectroradiometer (MODIS) Active Fire and Thermal Anomalies, Fire CCI (European Space Agency Fire Climate Change Initiative), and MODIS Burned Area for a study period of 2015 to 2022. Results show that both fire and burn products capture the burning season in Palawan, occurring in April and March with high fire pixel counts, concurrent to its climate’s dry season. La Niña affected the trend across datasets wherein declines in fire pixel count during the years 2021 and 2022 were observed. The use of fire and burnt product depicted fire schemes across vegetation types. Clusters are assessed per vegetation type revealing fire incidents occurred predominately over shrublands with low intensity and temperature fire, and long duration of burns; and open forests with intense and high temperature fires with varying duration of burning. Moreover, density of fire occurrences are highest in the municipalities of Sofronio Espanola, Bataraza, Rizal, Quezon, Culion, Roxas, Aborlan, Taytay and Narra. Synergestic use of fire and burned area products is instrumental in understanding the quality and characteristics of fire; fire descriptors and schemes are crucial for fire management strategies.

Garlic cultivation is an essential source of livelihood for smallholder farmers in Indonesia, particularly in the Sembalun sub-district of East Lombok, West Nusa Tenggara. However, accurate mapping of garlic cultivation areas has been challenging due to limited resources and access to information. Thus, accurate mapping of garlic area and distribution is essential for improving agricultural monitoring and management in smallholder farming contexts. This study used geospatial techniques and remote sensing to map garlic area and distribution in the Sembalun sub-district, East Lombok, West Nusa Tenggara, Indonesia. This study applied a rules-based classification approach to map garlic cultivation areas in the Sembalun sub-district. The rule was based on Normalized Difference Vegetation Index (NDVI) values, elevation, slope, the existing map of agricultural land use, and the number of garlic producers in each sub-district for identifying areas with a higher probability of garlic cultivation. The approach proved effective in classifying garlic fields with high accuracy. The mapping results showed that garlic was primarily grown in highland areas, with a total garlic area is 780.4 ha or 38.9% of the total agriculture area. The study demonstrates the potential of geospatial techniques and remote sensing for improving agricultural monitoring and management in smallholder farming contexts with limited field data.

Oil palm is an essential commodity for Indonesia, which generated USD 28.72 billion in foreign exchange in 2021. This commodity has a history for North Sumatra since the beginning of the oil palm industry, where the origins of the palm oil industry were in the province of North Sumatra. The importance of oil palm for the economy in North Sumatra can be seen from the production of palm oil in the region which fourth ranks in the national palm oil production. The success of oil palm cultivation is strongly influenced by various production factors, one of which is fertilization activities to replace the lost nutrients through harvest or other activities. Accuracy in fertilizing activities is the primary key to the success of oil palm production. Determining the fertilization dosage for oil palm plants currently requires high costs and a relatively long time because it requires leaf analysis in the laboratory. Mapping oil palm leaf nutrients through satellite imagery, especially Landsat-8 imagery, is one of the non-destructive alternative steps to determine the nutrient content of oil palm leaves quickly and precisely. This study aims to map and classify the nutrient condition of oil palm leaves as a reference for preparing the correct dosage of fertilization recommendations in the North Sumatra region. The methods used in this study are three types of classification using machine learning, namely classification and regression tree (CART), random forest (RF), and support vector machine (SVM). The classification results of the three types of machine learning have a high accuracy in classifying or mapping oil palm leaf nutrients in North Sumatra, which is then followed by calculating doses based on plant-transported nutrients and nutrient availability in oil palm leaves. Based on this, the three-machine learning have the potential to provide information quickly on the nutrient content of oil palm leaves.

The effects of global warming are shown by increasing temperatures in various regions, especially urban areas. Urbanization and urban development is one of the factors in increasing ground surface temperature (SPT). SPT is the main indicator of Surface Urban Heat Island (SUHI) effect. SUHI can be quantified into a standard value by utilizing the Urban Thermal Variance Index (UTFVI). The effect of SUHI in urban areas close to the coast is usually influenced by the aspects of elevation and distance from the sea. Through this research, the relationship between the aspects of elevation, distance from sea level, and the SUHI effect based on UTFVI values is then studied to see the relationship. The area studied in this research is the Makassar City area and the districts bordering the Makassar City administration. The relationship between these variables was analyzed by applying the global regression method, Ordinary Least Square (OLS). The UTFVI value variable in this study acts as the dependent variable, while the elevation and distance values act as independent variables. The results of the OLS analysis show that the distance and elevation variables have a simultaneous influence on the UTFVI variable with a regression coefficient of 70.98%. These two effects show a negative influence, where the greater the elevation and distance values, the lower the UTFVI value.

Climate change has led to an increase in global air temperatures, posing a threat to the liability of capital cities. This study focuses on understanding the Surface Urban Heat Island (SUHI) phenomena, which occurs over cities and is exacerbated by climate change. Spectral indices derived from Landsat data were used to understand SUHI, while trends in air temperature, precipitation, and relative humidity were analyzed using ground observation data collected from 1992 to 2022 in the capital city of Indonesia, Jakarta. The spectral indices used were the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Soil Adjusted Vegetation Index (SAVI), and Normalized Difference Moisture Index (NDMI). Land Surface Temperature (LST) was used to represent SUHI. Results indicate that NDMI has the highest Pearson’s correlation coefficient with LST (-0.73), followed by EVI (-0.41), SAVI (-0.4), and NDVI (-0.4). Trend analysis using Mann-Kendal test and Sen’s Slope showed a statistically significant increase in air temperature with a slope estimation of 0.03°C per year, while rainfall and relative humidity did not significantly differ over 30 years. SUHI trend analysis showed a statistically significant increase with a slope estimation of 0.1°C from 1992-2022. Mean surface temperature increased from 38.9°C in 1992 to 39.4°C in 2022. Jakarta's surface temperature ranged from 24°C – 57°C across water bodies, vegetation, bare land, urban, and industry, analyzed using Support Vector Machine. This study provides insight into the condition of SUHI over time, allowing the government to make efforts to mitigate the impact of climate change.

Intense human activity in urban areas plays an important role in increasing temperatures, which is reflected in the high surface temperature over built-up areas in cities. The aim of this study is to analyze the Urban Heat Island (UHI) phenomenon in Jakarta and Surabaya, using Landsat data associated with spectral indices and Land Use Land Cover (LULC), specifically for built-up areas. We used spectral indices for detecting built-up areas such as Index-based Built- Up Index (IBI), New Built-up Index (NBI), Normalized Difference Built-up Index (NDBI), and Urban Index (UI) to analyze UHI over a 10-year period from 2012 to 2022. Machine learning algorithms were employed to map the LULC, achieving an overall accuracy of 84% with the Support Vector Machine algorithm and 83% with the Random Forest. The analysis revealed that IBI has the highest correlation (0.69-0.84) with LST, compared to other built-up indices in Jakarta and Surabaya. The UHI classification based on LULC showed that residential areas had the highest average temperature compared to bare land, industrial areas, vegetation, and water bodies, with a temperature of 43.3°C for Jakarta and 43.°C for Surabaya, due to the high density of residential areas and buildings in the city. The spectral index correlation results show that IBI has the highest value, 0.69 for Jakarta and 0.85 for Surabaya.. Further research needs to explore high spatial resolution data to distinguish detailed built-up objects in the city.

The Indonesian Government have decided to relocate the capital city of Indonesia from DKI Jakarta to East Kalimantan Province in 2024. This new capital city of Indonesia called Nusantara Capital City (IKN) presents strategic issues regarding the lack of water availability and hydrometeorological disasters. Continuing the previous study about statistical comparison of rainfall extremes between Jakarta and IKN, this study on drought in IKN aims to investigate the water availability’s condition by using drought index associated with rainfall intensity and number of no rain days. We analyze the trend of consecutive dry days (CDD), The highest one-day rainfall (RX1day), and Simple Precipitation Intensity (SDII) indices yearly and seasonally. The ground-based daily rainfall data at Sepinggan, Samarinda, Penajam Paser Utara, Balikpapan, and Sepaku during 1979-2022 (42 years) are used in this study. The Mann-Kendall method is carried out to detect the trend of each index. The preliminary results show that in general CDD shows no trend tendency over all stations. However, we found a tendency of a decrease CDD in Dec-Feb (DJF) and Sep-Oct (SON) indicating these periods have generally have no rainy days overall resulting in decreasing CDD relative to other seasons. However, the CDD tends to show a slight increase trend between 1980 and 2009. In 1997, the CDD index was exceptionally high coincided with El Nino event. In contrast, the SDII and RX1day tend to increase in Jun-Aug (JJA). This study has found that the yearly decreasing trend of CDD does not simply conclude that there is no contribution of CDD to drought events. Instead, the drought might be more related to high occurrence of CDD influenced by large scale events depending on season and topography. This research has provided basis knowledge about CDD associated with drought and should be beneficial to develop strategic plan for water availability and its impact on the forest fire mitigation management as well as reducing the hydrometeorological disasters which commonly occur over IKN and its surrounding areas.

The rising demand for electricity, driven primarily by coal-fired power plants, has escalated concerns over hazardous gas emissions and their impact on air quality and human health. This study focuses on the Pelabuhan Ratu region, where there is a notable gap in understanding the spatial and temporal distribution of particulate matter (PM) and carbon monoxide (CO). To address this, we conducted a ground survey to measure concentrations of CO, PM2.5, and PM10 at various points. Additionally, we utilized Landsat 8 satellite imagery to predict the spatial distribution of these aerosols, while also developing a one-year temporal model. Pelabuhan Ratu's unique geomorphology, encompassing both mountains and coasts, significantly influences pollutant concentrations, which vary with elevation and proximity to the power plant. Employing the Random Forest machine learning algorithm, we predicted concentrations of CO, PM2.5, and PM10 by integrating ground-level gas concentrations with satellite-derived vegetation indices, ambient temperature, altitude, land use, wind direction, and humidity data. Our findings reveal varied predictive accuracies: the CO model exhibited a low correlation value (0.32) and a Root Mean Square Error (RMSE) of 136 ppm, suggesting a less reliable prediction. In contrast, the PM2.5 model showed a moderate correlation (0.474) with an RMSE of 18.4 μg/m³. The PM10 model performed slightly better, achieving a correlation of 0.56 and an RMSE of 55.4 μg/m³. These results underscore the challenges and potential of using integrated ground and satellite data for predicting air pollutant concentrations in complex geographic settings.

GEBCO (General Bathymetric Chart of The Ocean) is the international organization responsible for collecting, processing, and disseminating global bathymetric data. One of the data provided is the depth of the seabed. One of Indonesia's seas with a wealth of underwater physical characteristics is the Flores Sea. In this research, we validate the accuracy of the topographical information generated from GEBCO satellite images in the Flores Sea in deep and shallow waters. Seabed depth data is obtained free of charge via the official GEBCO website and processed using ArcGIS Pro software. Furthermore, the data obtained from GEBCO will be compared with data from MBES (Multi-Beam Echo Sounder) measurements. Data analysis was performed using statistical tests at each depth variation. The results obtained, as a whole, amounting to 96,227% of the GEBCO bathymetry data, can represent the measurement data in the deep water and only 0,916% in the shallow water. At each depth variation, the GEBCO bathymetry data does not show a consistent error trend. When analyzing the depth data, no pattern or trend can be identified, or it can be said that the distribution of the data does not follow a specific pattern.

One method for detecting oil spills from optical satellite data is using Oil Spill Index (OSI). In several studies, this index was used to visualize oil spill distribution. In order to estimate the coverage area of oil spill that occurs, image segmentation needs to be carried out to separate object of oil spill from non-oil spills. Therefore, this study used comparison of several OSI index applied to Sentinel-2 images and segmentation of oil and non-oil objects from OSI images using index threshold values. The data used consist of Sentinel-2 data date 12 August 2021 in Karawang waters, and 5 October 2019 and 2 May 2021 in Bintan waters. Karawang water image indicated oil spill from oil well platform leakage and Bintan waters image showed oil spills from ship sewage and other unknown sources. Two OSI algorithms were used, that is OSI₁ that had been developed using Sentinel-2 image, and OSI₂ was developed using MODIS data. OSI image threshold was then used to separate oil and non-oil objects. Other band combinations thresholds were also used to obtain the better results. Based on the result of threshold on OSI1 and OSI2 images, the study found that oil object can be separated better in OSI₂ image, however in the two images there were still a lot of non-oil subject mixed with oil class especially in OSI₁. Based on analysis of spectral pattern, object separation in OSI₁ image need to be carried out further using band 2 and band 9 threshold, while for OSI₂ needs to be separated further using band 3 threshold. Based on the comparison of the 2 thresholds, using combination of OSI₂ and band 3 gave better result. Accuracy analysis of OSI₂ threshold also showed the better result with overall accuracy of 86%.

Seagrass beds are ecosystems that are sensitive to anthropogenic pressures. The restrictions imposed on human activities during the Covid-19 pandemic provide a unique opportunity for coastal ecosystems to recover. This situation presents a chance to monitor seagrass ecosystems on Panggang Island and Karang Congkak Island, aiming to observe any changes in the seagrass area. The method employed to ascertain the community structure involved photo transects, which were then processed using a machine learning supervised classification approach utilizing the random forest algorithm. The classification process categorized the area into five classes: seagrass, macroalgae, coral, bare substrate, and dead coral algae. Confusion Matrix Test was chosen to assess mapping accuracy, setting an accuracy threshold of ≥ 60%. The findings reveal notable alterations in seagrass areas across both islands. Panggang Island exhibited a considerable increase in seagrass coverage by 21,05 hectares. Conversely, Karang Congkak Island experienced a decrease of 2,88 hectares in seagrass coverage. These observed changes are likely not influenced by the anthropause phenomenon but rather by natural occurrences between 2019 and 2022, including the La Niña Triple Dip phenomenon and variations in sampling time during the transition season. The Overall mapping accuracy (OA) results for Panggang Island in 2019 and 2022 were 52,63% and 57,89%, respectively. Similarly, for Karang Congkak Island, the Overall Accuracy results were 60% in 2019 and 60,66% in 2022.

Escalating climate impacts prompt governments to act as seen in the fifth Conference of the Parties (COP), demanding eco-friendly practices to limit warming to 1.5°C. Carbon accounting is vital for global sustainability, requiring robust national monitoring of stocks and emissions. Remote sensing technology and satellite data enable modeling terrestrial carbon reserves, though challenges remain for coastal areas due to water attenuation. Ongoing studies aim to prove the technology’s viability, despite accuracy issues in capturing shallow coastal environments. With this being gap, this study developed a methodology to map a coastal environment using satellite data and machine learning. Sentinel-2 MSI, an open-source multispectral image, was utilized in this study. Geospatial derivatives such as ratios of the visible bands, bathymetry model using the Stumpf’s ratio and principal components which contained at least 90% of uncorrelated data were also integrated in the modeling process to improve benthic feature separability. Different combinations of the datasets were also explored in this study. Benthic habitat models were produced using Random Forest (RF) and Support Vector Machine (SVM) machine learning algorithms for each variable combination. The generated models generated overall accuracies ranging from 0.69 to 0.74 and 0.22 to 0.68 respectively. This translated to a maximum percent difference of 77% for the case of RGB model only and a minimum of 8% using all the variables. In terms of using different variable combinations, RF exhibited robust performance showing relatively consistent results compared to SVM which produced a wide range of accuracy values across the different models.

The sea waters of Banyuasin have several estuaries. These conditions will affect the biophysics of the waters, especially chlorophyll-a as an indicator of water fertility and fishing ground habitat. This study aims to map the dynamics of the distribution of chlorophyll-a concentrations based on different seasons in the coastal water of Banyuasin Regency. The method used is the analysis of Landsat 8 OLI imagery. The images used consist of images recorded on September 19, 2019, December 30, 2019, April 20, 2020, and July 20, 2020. The images represent the transitional season II, western season, transitional season I, and eastern season, respectively. The results showed that the concentration of chlorophyll in the transitional season II was 0.502 mg/m³–2.514 mg/m³, the western season was 1.627 mg/m³–3.934 mg/m³, the transitional season I was 0.854 mg/m³–2.782 mg/m³, and the concentration of chlorophyll-a in the east monsoon was 0.801 mg/m³–2.904 mg/m³. The dynamics of Chlorophyll-a concentration in the study area varied according to the season, and its distribution pattern was seen to be higher in coastal areas, while its concentration decreased towards the sea.

Water quality is crucial for the long-term health of undersea biological ecosystems, including elements like Colored Dissolved Organic Matter (CDOM). Gathering field data to characterize CDOM is expensive and time-consuming. To address this, the optical aquatic research community has compiled the GLORIA dataset, which includes measurements of water quality indicators such as chlorophyll a, total suspended solids, absorption by dissolved substances, and Secchi depth. This dataset aids in routine monitoring of high-priority sites, algorithm development, and data validation. In this study, we employed the CDOM data from the GLORIA dataset to develop an empirical CDOM algorithm using Sentinel-2 imagery. The GLORIA dataset encompasses 7,572 stations globally, but for this study, only 92 stations were utilized to construct a tropical water CDOM algorithm. This algorithm was then calibrated with CDOM measurements from the Derawan Archipelago. The developed empirical algorithm is based on a random forest regression model. The algorithm, derived from the GLORIA dataset, demonstrated promising training data accuracy (RMSE = 0.42, R-Square = 0.37). However, the validation accuracy was lower (RMSE = 0.41, R-Square = 0.23), and the tests on the Derawan CDOM dataset indicated even poorer accuracy. These results highlight the challenges in developing a global CDOM algorithm based on multispectral imagery.

Wetland areas play a crucial role in ecological development and land utilization. The availability of wetlands is urgently needed, as they are vital for maintaining ecosystem integrity. However, land conversion poses a significant threat to wetland management in Indonesia. This study focuses on the rapid changes in land use occurring in Bekasi Regency, which is undergoing extensive development as an industrial center. The dynamic nature of human needs, coupled with advancements in technology, has led to the conversion of wetland areas into new land uses, thereby posing a threat to the natural environment. This research aims to examine the changes in land use dynamics within the Bekasi wetlands area from 1988 to 2022. The detection of changes was performed by integrating Landsat data and using the transformation index indicator methods on a cloud computing platform, specifically the Google Earth Engine (GEE). The results indicate that wetland degradation in northern Bekasi Regency has resulted in a reduction of over 11.5% of wetland area. Concurrently, the non-wetland area has experienced an increase, spanning approximately 3,224.40 hectares, while the wetland area has shown a decreasing trend, covering 3,828.80 hectares.

Indonesia was under Dutch colonial authority for several centuries, during which mapping activities were carried out to serve the interests of the ruling government. Indonesia possesses several historical maps with significant potential, although their utilization remains incomplete. This research aims to explore the possible applications of historical maps, particularly in the context of organizing historical coastlines. The historical maps included in this project originate from the years 1896, 1898, 1920, and 1944 and have undergone georeferencing and digitizing processes. The Digital Shoreline Analysis System (DSAS) utilizes the Net Shoreline Movement (NSM) and Linear Regression Rate (LRR) statistical techniques to assess shoreline changes. The outcome of this study is a cartographic representation of the alteration in the coastline of Tangerang Regency, accompanied by a graphical depiction of the shoreline's transformation. The accuracy of the results is compromised due to variations in historical maps originating from different time periods, resulting in differing geographical perspectives across authors. Consequently, the reliability of the accuracy is diminished. Nevertheless, these limits restrict the extent to which geography may be advanced based on each individual map.

Seagrass beds play a crucial role in coastal ecosystems, providing various ecosystems services that are unique to each seagrass species. It is important to have spatial information on the composition of seagrass species in order to effectively manage and utilize seagrass beds. Unfortunately, the lack of such data hinders the optimal management of seagrass beds in Indonesia, as exemplified by the case of Pari Island in the Thousand Islands. To address this issue, WorldView-2 imagery, a multispectral remote sensing image with high spatial and spectral resolution, can be utilized to map composition of seagrass species. Therefore, the objectives of this study were twofold: (1) to map the composition of seagrass species and (2) to assess the accuracy of the resulting seagrass species composition map for selected areas of Pari Island, using WorldView-2 imagery. To achieve these objectives, a combination of image segmentation approaches and multispectral classification employing the random forest algorithm was employed. The findings revealed that the seagrass species composition in the designated areas of Pari Island, based on a life-form classification scheme, comprised Enhalus acoroides (Ea) covering an area of 0.04 km², Enhalus acoroides-Thalassia hemprichii (EaTh) covering 0.21 km², and Thalassia hemprichii-Cymodocea rotundata (ThCr) covering 0.28 km². The overall accuracy (OA) of the seagrass species composition map was determined to be 60.76%.

Oil spills frequently occur on the sea surface due to heightened vessel activities. Oil spills can be detected by applying supervised and unsupervised classification methods to satellite images using radar sensors. Supervised classification methods such as visual interpretation are widely used, but the results are very subjective. Conversely, unsupervised methods, while less subjective, necessitate parameter tuning for accurate results. This study's primary goal is to assess the impact of parameter tuning on unsupervised K-Means and Clustering Large Applications (CLARA) algorithms for detecting sea surface oil spills. It can be concluded that the area of identified oil spills is closely related to the iteration parameters and the number of cluster centers. The results of identification using the unsupervised method with these two algorithms will be compared with reference data from Indonesia National Institute of Aeronautics and Space (LAPAN) as the official institution that provides information regarding oil spills pollution on the sea surface in Indonesia. The main conclusion from this study, parameter tuning is highly required before carrying out the process of identifying oil spills on sea level using the unsupervised method especially related to the number of iterations executed, the desired number of cluster centers, and the clustering type of the algorithm used. Using the tuned parameters, the K-Means algorithm is able to identify oil spill areas that are quantitatively close to the reference data area, but the CLARA algorithm is able to provide identification results that have fewer errors in terms of oil spills look-alikes.

Water quality along the northern coast of Manila Bay is deteriorating due to anthropogenic influence, and the use of remote sensing is an effective tool for environmental monitoring. This study estimated the chlorophyll-a (chl-a) and total suspended matter (TSM) concentrations in Manila Bay from 2002 to 2016 and evaluated the possible environmental factors that contributed to the spatiotemporal changes in these two parameters. MODIS images were processed through the Case 2 Regional Coast Color model to determine monthly chl-a and TSM concentrations. Manila Bay was divided into six zones based on spectral characteristics. Each zone was then compared for the environmental variables precipitation, runoff, sea surface temperature, and wind speed downloaded from the ECMWF Reanalysis v5 global dataset. Zones 1-3 are located in the northern half of the bay and showed higher chl-a (3.2±0.9 to 8.3±2.2 μg/L) and TSM (2.0±0.7 to 11.0±2.5 g/m³ ) than Zones 4-6 (chl-a: 0.9±0.4 to 1.9±0.8 μg/L, TSM: 0.7±0.2 to 1.3±0.5 g/m³ ). The highest chl-a and TSM are in Zone 1, located at the mouth of Pampanga River, which is the largest watershed in Manila Bay. It is also an area with extensivemariculture activity. Within Zone 3 is the mouth of Pasig River, a localized area with anomalously high chl-a and TSM due to the high amount of organic load from urbanization. Pearson correlation of the environmental variables in each zone shows that precipitation (0.15-0.68) and runoff (0.38-0.79) are more correlated with water quality than sea surface temperature and wind speed. Paired t-test of chl-a and TSM also show a significant difference between the wet (June to November) and dry (December to May) seasons. Results suggest that water quality is largely influenced by precipitation and runoff. This means that effective river basin management could be the key to improving water quality in Manila Bay.

Problems in the coastal area of the karst formation area are highly correlated with uncontrolled tourism development in the southern part of Bali Island over time. To address this issue, identifying coastal typ ology and their change was conducted by comparing and interpreting high-resolution satellite images from November 2012, April 2017, and June 2022, which were georeferenced using GIS tools at the selected research location through purposive sampling. The analysis employed a descriptive qualitative and spatial approach and an environmental approach. The results revealed four coastal typology classes, including primary coast which is land erosion coasts and structurally shaped coasts, and two secondary coastal classes the marine deposition coasts and wave erosion coasts. These coastal typology were observed across three different periods. Changes in coastal typology predominantly occurred at Melasti Beach and Pandawa Beach, which experienced significant influences from anthropogenic and some natural forces due to their geographical location and tourism development pressures resulting in high intensity of accretion and coastal erosion.

Seagrass, a marine angiosperm, plays a crucial role in providing significant ecosystem services. Due to its highly dynamic nature, seagrass cover can exhibit monthly or seasonal fluctuations. This research aims to investigate the dynamics of seagrass cover changes on Gili Lawang Island, East Lombok Regency throughout the period of 2022-2023, utilizing timeseries PlanetScope images. To develop a model for estimating seagrass cover percentage, we employed a stepwise regression approach that integrated sunglint-corrected Planetscope level 3B bands with field seagrass data. Training and accuracy assessment samples were collected using the photo-quadrate method, spatially distributed across various coastal characteristics of Gili Lawang Island. The obtained time-series seagrass percent cover maps were further analyzed in conjunction with climatic data to discern the underlying patterns governing seagrass cover dynamics. The novelty of this study lies in its potential to serve as a foundation for future research endeavors, such as the analysis of carbon stock dynamics in seagrass fields, and as a basis for establishing seagrass conservation zones in Gili Lawang.

Landslides, which are triggered by heavy rainfall or seismic activity, pose serious threats in mountainous regions, necessitating the implementation of structural mitigations, early warning systems, and hazard maps. Traditionally, hazard maps have been empirically derived based on topographical parameters; however, recent advancements have seen the integration of numerical models with digital elevation models (DEMs) to calculate hazard maps. These numerical models are grounded in a comprehensive understanding of landslide dynamics. Large-scale landslides often inundate a larger area than predicted by existing models, which is attributed to the impact of suspended fine sediment reducing bottom friction. To address the inadequacies of existing models in reflecting these effects, we developed a new numerical model for largescale landslides that considers the suspension of fine sediment. First, we investigated the relationship between the quantity of suspended fine sediment and the kinematic conditions of a landslide through flume experiments, resulting in a regression equation for estimating the quantity of suspended fine sediment. This equation was incorporated into a two-dimensional depth-averaged model, forming the basis for the new large-scale landslide model. When this model is integrated with a DEM, it accurately calculates the inundated area associated with a landslide. We tested the model using data for a largescale landslide event in Japan, where pre- and post-landslide DEMs were available for model validation. The results showed that our model successfully replicated the actual inundation area, demonstrating its potential utility in generating hazard maps based on numerical simulations.

Coastal protection structures are crucial for safeguarding coastal communities from natural disasters, such as coastal erosion and flooding. However, due to various factors, such as cyclones, and floods, these structures can be damaged, leaving the population living in their vicinity at risk. This study pivots from a general evaluation to a refined methodological approach, centered on the Kollam district, to assess and prioritize vulnerable coastal stretches. We employed a comprehensive GIS-based framework, synthesizing data on demographics, coastal structures integrity, and shoreline dynamics. The analysis meticulously delineated the extent of coastal stretches with damaged structures, the populace within the proximity, and the corresponding shoreline status. The results unveiled critical zones, such as Alappad village, characterized by pronounced structural damage, eroding shoreline, and substantial resident populations within proximity. By identifying such high-risk areas, the research facilitates strategic prioritization for mitigation measures and astute resource allocation. Furthermore, the study underlines the pivotal role of continuous monitoring, timely interventions, and data-driven decision-making in managing coastal areas. While the research presents significant insights, it acknowledges inherent limitations tied to data accuracy and its dynamism. Future work should pivot towards real-time data integration, encompassing broader factors like climate projections and socio-economic determinants, thereby enhancing the robustness and applicability of our risk assessment model for global coastal management.

Indonesia is a country located on the Pacific Ring of Fire which causes Indonesia to have the largest number of active volcanoes in the world, resulting in frequent volcanic eruptions. As happened in 2021, the eruption of Semeru Volcano caused casualties and damage to landuse. This study aims to determine the impact of the 2021 Semeru Volcano Eruption and to map the impact of Semeru Volcano erupton to landuse in Lumajang Regency using Normalized Difference Vegetation Index (NDVI). This research includes three stages. In the first stage, data collection was carried out by downloading pre-eruption and post-eruption Landsat 8 OLI satellite images of Semeru Volcano. Second, analyze data, reports and documents to obtain data and information regarding the impact of the Semeru Volcano eruption. The third phase focuses on data analysis and mapping of impact caused by the eruption. The most affected area with lahar flood were bareland with 2330 ha or 45.56% of affected area, followed by forest with 1921 ha (37.56%), dryland agriculture with 713 ha (13.94%) and rice fields with 134 ha (2.62%). The whole area that affected by Semeru Volcano eruption in Lumajang Regency is 5114 ha or 2.8% from total area of Lumajang Regency. Pronojiwo District is the district with the largest area affected by the eruption with total of 20.34% of its area affected by Semeru Volcano eruption.

The subsidence of the land surface in the north coast of Java has become a national and international concern, which says that Jakarta will sink in the next few years. Remote sensing, especially with SAR data, is widely used to view the deformation and subsidence of the ground. Several studies have indeed shown a trend of land subsidence in Jakarta in recent years. This research processing uses Sentinel 1 data to obtain information related to the rate of subsidence using the Insar method, which results. The Lidar data is then used to predict inundation models in recent years to see areas below sea level. Then, a Land Use Land Cover analysis is carried out to see the use of land that will experience inundation in the future. The results show that the total area inundated in 2031 is 1393.6 ha, with the most significant area will inundated in North Jakarta, and for future potential LULC in Jakarta The largest land use land cover in Urban Area with 85 % from total LULC. And for total Potential LULC will be inundated is urban area with 1197.79 ha.

Smoke information serves as a crucial marker for detecting peatland fires. Practically, smoke identification utilizing remote sensing satellites, based on visual interpretation techniques, proves inefficient in processing time and high subjectivity. The application of machine learning technology for smoke detection remains limited in the tropics, especially in peatland areas. This study aims to identify smoke from peatland fires using machine learning techniques. The dataset comprises Visible Infrared Imaging Radiometer Suite (VIIRS) images and the VIIRS’s hotspots on September 11^st 2019, coinciding with a major peat fire incident in Indonesia. Various machine learning techniques were tested, encompassing Random Forest (RF), Classification and Regression Trees (CART), Support Vector Machine (SVM), Naive Bayes (NB), and Gradient Tree Boost (GTB). Object classification includes thin smoke, thick smoke, clouds/smoke, clouds, vegetation, water body, and bare land. The accuracy assessment involved both qualitative assessment based on true-color images and quantitative evaluation through the 70:30 sample splitting accuracy assessment method. The analysis of spectral distance for the seven object types reveals that band 5, 10, and 12 exhibit the highest value. Successfully identification of peatland fire smoke is achieved via supervised machine learning, particularly logic-based algorithms (RF, CART, GTB) and support vector machine methods (SVM), while statistical method (NB) yield comparatively less success. Qualitative validation using true-color VIIRS image indicates strong alignment between thick smoke and the RF all-bands approach. Quantitative validation, based on accuracy assessment with 1531 samples, establishes SVM as the most accurate method, boasting an overall accuracy of 0.93, followed by GTB at 0.91, RF at 0.90, and CART at 0.88.

This research aims to map the level of potential and analyze and map the microzonation of building damage after an earthquake disaster in Nagari Kajai, West Pasaman Regency. The method used in mapping the potential level of earthquake hazard is scoring analysis, while in modeling the microzonation map of building damage is done by buffer method and matching the zone of danger level, then validating the model with field survey method which is integrated into the results of on-screen digitization of high-resolution satellite image interpretation of each distribution of damaged buildings at the research location.
The results of this study are in the form of a map model of the potential level of earthquake disaster hazard which is divided into three zones, namely unstable areas with a score of 46-60, less stable areas have a score of 31-45, and stable areas against earthquakes have a score of 15-30. The results of the analysis of the microzoning map of post-earthquake building damage in Nagari Kajai, West Pasaman Regency obtained a microzoning area, in the unstable class covering 3583.63 ha, located in the jorong rimbo batu, kampung alang, pasa lamo area. In the less stable microzonation class covering an area of 6349.78 ha, located in the limpato jorong area, most of the lubuak sariak jorong area, and part of the tanjuang beruang jorong area, and in the stable class has an area of 1251.04 ha, located in the mudiak simpang jorong area, part of the timbo abu jorong, limpato, and some of the lubuak sariak jorong area.

Coal makes up a large percentage of the world’s energy consumption and contributes to industrial growth. However, despite the largely unexplored areas, it is still not given much focus. This study utilizes GIS techniques and AHP to delineate coal areas in Surigao del Sur, Philippines, by reclassifying and establishing a weighted ranking system for the selected criteria, generating a coal prospect map, and quantifying regions for the possible occurrence of coal. The weights of the selected criteria, which included slope, rock type and age, vegetation development, and lineaments, were determined using AHP. Among these, the type of rocks was highly considered in identifying coal areas with an average final weight of 33.16%. Overall, the majority of the study area has a high potential for coal occurrence, covering 128,704.59 hectares or 26% of the total area.

Most of the peatland degradation was caused by land fires, water mismanagement, and mining activities. Indicators of degraded peatlands based on the kind of land cover in the field are characterized by (1) shrubs, and (2) barren lands (open areas of ex-mining land). This study aims to identify, distribute, and determine the dynamics and prediction of the existence of degraded peatlands in Kepulauan Meranti Regency, Riau Province, Indonesia. The methods used were spatial analysis and CA Markov analysis. The data used: Landsat imagery 1999–2018, Regional Spatial Planning (RTRW) map, map of landform and soil, hotspot data, and peatland data. The results of this study show that the maximum land degradation area of 280.366,8 ha occurred in 2000, and the smallest of 154.365,01 ha occurred in 2010. The increase in land degradation is due to an increase in forest and land fires in the area. The factor driving the increase in forest and land fires is the practice of clearing land by burning. The prediction analysis of land degradation in 2030 shows that degraded peatland has decreased by 2.471 ha which includes degraded peatland in protected areas and cultivated areas.

Batang Gadis National Park or also known as TNBG is one of the national parks in Indonesia located in Mandailing Natal Regency, and there are at least 8 types of hornbill species (Bucerotidae Family) that inhabit this area. According to the IUCN Red List, these hornbill species are generally classified as vulnerable, threatened, or even endangered. This research aims to identify the general hornbill habitats suitability in TNBG and create the geospatial model based on its distribution survey. This study utilizes the Maximum Entropy algorithm as an analysis method with seven environmental variables such as; habitat fragments, canopy density, distance from the river, slope, elevation, aspect, and also the presence data obtained from field survey that will serve as guidelines in predicting the distribution tendencies of hornbills. Out of 20 tests, the algorithm produced the best model in the 18th replication, achieving the AUC value of 0.8306. Elevation was found to be the most influential variable, contributing 38.7% to the identification and modeling of hornbill habitat suitability in TNBG, aspect accounted for 17.9%, followed by land cover at 16.6%. The average habitat characteristics indicate elevations between 650-1250 meters above sea level, with slopes facing southwest, east, and north. The hornbill also can be found in forest, plantation, and agriculture land cover on moderately steep and steep slopes within the distance range of 0-500 meters from the main river and 0-50 meters from habitat fragments with high vegetation density. The modeling results reveal that 22.85% of the area has very low habitat suitability, while 24.64% has low suitability. Moderate suitability accounts for 24.55%, high suitability for 21.72%, and very high suitability for 6.23%.

As one of the country's top abaca-producing regions, the Caraga region is experiencing the impacts of climate change. In this study, the impacts of climate change on the suitability of abaca using Maxent were quantified to provide knowledge to the extent in 2021-2040 and 2041-2060 with the EC-Earth3-Veg GCM under different socioeconomic pathways scenarios. Maxent models show good and acceptable reliability with an AUC score range of 0.794-0.855. Using a threshold of ≥ 0.5, the suitable area of the Caraga region for the current period is 210,700 hectares. The suitability increases in 2021-2040 and 2041-2060, specifically in SSP 126. The land area suitable for abaca exhibited a trend toward a minor decrease in some of the different climate change scenarios. However, the suitable land area increased when compared to the current period. Maxent species distribution models are a valuable tool for predicting how climate change would affect the spread of abaca species.

Digital elevation models, or DEMs, are digital representation of the Earth’s surface elevation, and have a variety of applications, such as environmental impact assessment and disaster management. This paper discusses extraction of highresolution DEMs from tri-stereo satellite imagery, and accuracy assessment of these DEMs after comparison with publicly available dataset containing elevation information. Tri-stereo images from KOMPSAT are of Level 1O, also known as ortho-ready. Pansharpening of multispectral image, with approximately 2.8-meter resolution, and panchromatic image, with approximately 0.7-meter resolution, was done to obtain a multispectral image with the resolution of the panchromatic image. Tri-stereo images from SkySat were already pansharpened and has approximately 0.5-meter resolution. ESRI World Imagery of Davao City was used as reference image for GCP collection. Epipolar images of the pansharpened KOMPSAT and SkySat images were used to generate 0.7 m resolution and 0.85 m resolution DEMs of Davao City, respectively. To assess the accuracy of the generated DEMs, these were compared with the spot elevation from NAMRIA, with a scale of 1:50,000, and 30 m resolution SRTM DEM. Generated DEM from KOMPSAT has mean error and RMSE of 2.78 and 4.58, respectively, from the spot elevation, and 4.40 and 6.27, respectively, from the SRTM DEM. As for the generated DEM from SkySat, the mean error and RMSE are 3.23 and 5.57, respectively, from the spot elevation, and 3.94 and 6.04, respectively, from the SRTM DEM. The KOMPSAT-generated DEM has lower error after comparison with the spot elevation, while the SkySat-generated DEM has lower error after comparison with the SRTM DEM.

Water resources are an important factor in the lives of living organisms. Water resources include groundwater and surface water. The interaction between surface water and groundwater is an important component of groundwater cycle research (Winter et al., 2003; Meng et al., 2019). The LukUlo Watershed has an area of 675,53 km². The groundwater and LukUlo River conditions differed between the upstream and downstream areas. These different conditions can potentially affect the physical quality of groundwater and surface water, particularly in the downstream area of the Luk Ulo River. This study aimed to determine the interaction between groundwater and surface water in the lower reaches of the Luk Ulo River. Understanding the interaction between surface water and groundwater in an area is required to better manage watersheds. (Khan and Khan, 2019). The Global Information System (GIS) method was used in this study. GIS applications interpolate groundwater conditions and Total Dissolved Solids (TDS) content to determine the direction of groundwater flow and the distribution of TDS content. In addition, water discharge measurements were carried out in several rivers to ascertain the interaction between groundwater and surface water in the downstream portion of the LukUlo River. Based on the results of data analysis, it was concluded that the nature of groundwater to surface water in the lower reaches of the LukUlo River is effluent. From the condition of the direction of groundwater flow towards the LukUlo River, the distribution of TDS values for most groundwater is higher than surface water. Meanwhile, in measuring the surface water discharge, the average discharge is 26.38 m³/s, higher than groundwater. The effluent's nature can cause the cliffs on the river walls downstream of the LukUlo River to become prone to landslides when conditions are saturated or during the rainy season. Therefore, spatial planning is needed to sterilize the area around the riverbanks from buildings to minimize casualties in a landslide disaster.

Gully erosion is the most destructive type of soil erosion, induced by soil detachment. As a result, modest to massive incisions are made in the field. The process can degrade the quantity and quality of soil and potentially cause structural damage. Field studies are used to map the position of gullies, but they are inefficient in terms of time and cost, especially on a regional scale. Therefore, another approach is applied to visualize the probability of gully erosion development using geoenvironmental factors. Remote sensing data can be used to examine the condition of the land, leading to an accurate representation of the earth's surface. This research's primary goal is to predict the location of gully erosion using remote sensing data in the upper section of the Sapi Watershed, Banjarnegara, Indonesia. This location primarily consists of mountainous areas used for massive cultivation. Parameters comprising land use and vegetation area derived from SENTINEL 2A, and topographic and hydrological data from DEMNAS. The mapping process considers the actual location of the gully and other geographical characteristics using Random Forest. A total of 85 gully location records were collected and verified using Google Earth and field surveys. Nongully data were obtained using median filters to distinguish between river and mountain top. 70% of the data is used for modelling and the rest for validation of model results. RF-generated prediction maps could provide an essential instrument for planning and land conservation in the early phases of gully formation.

Generating Digital Elevation Models (DEMs) from stereo optical satellite data has been a well-established practice for many years. The typical workflow involves performing Bundle Adjustment (BA) to align the stereo imagery, often supplemented with Ground Control Point (GCP) data for accurate vertical values. However, acquiring high-precision GCPs using geodetic GPS can be costly and time-consuming. In this study, we utilize a GCP-less approach that combines iterative bundle adjustment with an existing DEM for SPOT-7 tri-stereo imagery. The Semi-global matching algorithm is employed as the stereo correlator for all three stereo combinations (Forward-Nadir, Nadir-Backward, Forward-Backward). We also explore four alternative approaches: single BA without GCPs, single BA with 9 GCPs, 9 GCPs only, and single BA without GCPs but with DEM co-registration. To build the DEM, we utilize the SPOT-7 panchromatic band (1.5m) and upscale it by a factor of two to achieve a Ground Sampling Distance of 3 meters. We evaluate the horizontal shift in the x and y directions of the produced DEMs using DEMNAS as the reference. Additionally, the vertical accuracy is assessed using the Root Mean Square Error (RMSE) by comparing the results to a combination of geodetic Independent Control Points (ICPs), Unmanned Aerial Vehicle (UAV) Digital Surface Models (DSMs), and filtered ICESat-2 ATL-08 points as the reference data. Preliminary findings indicate that the GCP-less iterative BA approach outperforms all but one other method on average. The iterative BA method yields average x and y shifts of 1.72 meters and 0.95 meters, respectively. These values are lower than those obtained using single BA (13.01 and 3.27), single BA with 9 GCPs (2.85 and 2.62), and 9 GCPs only (3.94 and 1.00) approaches. The only approach that produces lower shifts is the single BA with DEM co-registration, which results in 0.60m and 0.72m for x and y shifts, respectively.

Satellite remote sensing assesses hydrocarbon-rich areas in sedimentary basins by analyzing multi-spectral remote sensing-derived geological data. This study used geospatial datasets and techniques to map potential hydrocarbon microseepage areas in the Lower Agusan River Basin, Caraga, Philippines. The study employed parameters such as clay-carbonate alteration symptoms, ferric iron, ferrous iron minerals, Normalized Difference Vegetation Index (NDVI), and geological characteristics. Principal component analysis (PCA) was conducted on Sentinel 2 multispectral satellite imagery to detect mineral alteration phenomena. The PCA processing resulted in having PCA 3, with a value of -1.31862, to be used to extract the ferric iron mineralization. Moreover, PCA 1 has the highest eigenvector value for the ferrous iron band ratio, with a value of 1.34926. Lastly, PCA 2 extraction reveals clay carbonate mineralization with an eigenvector value of -1.19985. The fuzzy logic method was then applied to each parameter and integrated to determine the distribution of hydrocarbon microseepage areas. The results revealed that 83.3% of the study area exhibits a high potential for hydrocarbon microseepage, while 15.4% and 1.3% indicate moderate and low potential, respectively.

The increase in population from year to year causes the need for improvements in facilities and infrastructures. The number of new buildings causes the area that was intended as a water catchment to turn into watertight areas so there is an increase in the amount of surface runoff. An understanding of the processes and factors that influence runoff is needed as a reference for more effective water management and land use. The purpose of this study is to map areas that have the potential to experience surface runoff and determine the level of vulnerability of surface runoff occurred in Batam. This study employed overlay and scoring of the parameters of surface runoff as the method. There are four parameters of surface runoff used, which are land use, soil type, rainfall, and slope. The level of surface runoff vulnerability is categorized into five classes, which are not vulnerable, less vulnerable, moderate, vulnerable, and highly vulnerable. The results showed that 52.57% area in Batam (18,176.39 ha) has a moderate level of surface runoff vulnerability. The areas that have the greatest potential and are the most vulnerable include Batam Center, Lubuk Baja, Nongsa, and Sungai Beduk. Areas categorized as not vulnerable and less vulnerable include northeast Sungai Beduk, south Nongsa, south Sekupang, north Sekupang, some areas in Batu Aji, as well as some areas in Sagulung.

The Krakal region in Kebumen, Central Java, is known for its distinct non-volcanic hot spring manifestation. In the absence of overt volcanic indicators, fault lineaments offer invaluable insights into the subsurface architecture that dictates the distribution and movement of geothermal resources. This research aims to evaluate lineament density by merging Digital Elevation Models (DEM) with remote sensing imagery via ArcGIS and produce Fault and Fracture Density (FFD) measurements. The analysis of lineaments was carried out based on raster image derived from ASTERGDEM 10 M, highlighting the density of lineaments. The lineament density map underscores a prominent connection between the Krakal hot springs and dominant lineaments exhibiting east-west and northwest-southeast trends. These lineaments significantly influence the outflow system of the hot springs, notably dictated by the high-lineament density region. This area of elevated lineament density is attributed to the Kedungramat sinistral fault. The study posits the utility of lineament density maps as an alternative approach for identifying geothermal surface manifestations within the study area.

Watershed is a region inland that group on how the water flow, accumulate, and dischare based on its morphology. Every watershed has its morphometric parameter, and it might affect the flood frequency or hazard in the region. One of the parameters is the circularity ratio or Rc, the ratio of areas of a watershed and a circle with the same circumference/perimeter. There has not been any research that tries to compare the Rc and flood hazard on multiple watersheds. Here we try to calculate the Rc and flood hazard on multiple watersheds on the island of Java. The purpose is to find any correlation and pattern that can explain the rate of flooding using geometric and morphometric characteristics of the watershed. The watershed geometry is acquired from KLHK, and the flood hazard is generated from the Normalized Difference Flood Index (NDFI) of multi-temporal Sentinel-1 SAR Imagery. The result shows there are two patterns of relationship found on low (0 - 0.2) and high (0.6 - 0.8) Rc. These two groups show that higher Rc means a lower flood area but a higher flood hazard score. This pattern does not show up in the middle-value groups of Rc (0.2 - 0.6). Using other flood data or regions might show a different result.

Coastal cliffs are dynamic landforms that are constantly changing due to natural and anthropogenic factors. Continuous monitoring of the vulnerable cliffs is crucial to understanding their stability and developing effective strategies for managing coastal areas. An attempt to understand the retreat rate and extent of the Varkala cliff, Kerala - a geo heritage site and its contributing factors were investigated in this study. Remote sensing and GIS analysis through satellite imageries were employed to estimate the retreat. The results indicated that the Varkala cliff has retreated significantly over the past few decades, with rates of erosion varying along the length of the cliff. The causative factors that govern the retreat; such as urbanization, and geological and hydrology forces were examined. The cliff recession based on sea level rise is also examined. The findings indicate that human activities, particularly the expansion of urban areas along the cliff, have played a significant role in accelerating the retreat of the Varkala cliff. Additionally, variation in the cliff morphology has influenced the rate and pattern of retreat. The importance of considering the complex interactions between natural and anthropogenic factors in understanding cliff erosion and retreat was highlighted. This study provides important insights into the factors driving cliff erosion in Varkala. This will help develop coastal management strategies that can preserve its geological and ecological value for future generations.

Purwodadi and Bagelen sub-districts are areas that are frequently inundated by floods from the overflow of the Bogowonto River. These inundations can disrupt community activities and has an impact on material, social and economic damage. Therefore, it is necessary to have an effective and efficient flood potential in the Bogowonto watershed. The purpose of this study is to extract data of land use and river geometry using remote sensing data and geographic information systems for estimating flood discharges and constructing flood inundation spatial models using HEC-RAS and ArcGIS software in return periods 1, 2, 5, 10, 20, 50, and 100 years. Modeling is doing with integrating HEC-RAS and ArcGIS software. This study generally carried out hydrological and hydraulic modeling in the Bogowonto watershed. Hydrological modeling was carried out to convert rainfall data into flood discharge using the Nakayasu Synthetic Unit Hydrograph. The data used is the maximum daily rainfall for 2010-2022 from 10 rain stations in the Bogowonto watershed. Hydraulic modeling was carried out to simulate flood inundation using the HEC-RAS software with 2D unsteady flow simulation. The data required in this study are river geometry, design flood discharge, and Manning’s values. River geometry data and Manning’s values were obtained from digitizing remote sensing data in the form of DEMNAS and Sentinel-2A. The results of the modeling were analyzed and visualized using ArcGIS. This study shows that remote sensing data and geographic information systems can extract land use and river geometry data, which can then be used in flood modeling.

Urban Heat Island (UHI) is a common phenomenon in urban areas due to the dense infrastructure and lack of green spaces. Vegetation can play an important role in mitigating UHI. This study investigates the relationship between vegetation and land surface temperature (LST) in selected Indian cities from 1985 to 2017. Additionally, this research examines the influence of configuration or spatial distribution of vegetation across a city on vegetation-LST relationship. Landsat images were used to extract LST and vegetation percentage. Pearson correlation coefficient was used to determine the relationship between vegetation and LST. Furthermore, seven configurational metrics were used to analyse the influence of vegetation arrangement on the vegetation-LST relationship. The results showed that in most cities, the relationship between vegetation and LST shifted from a strong or medium negative significant relationship to no relationship and the ability of vegetation to mitigate LST is diminishing over time. The results also suggested that larger and more connected vegetation patches are more effective in mitigating LST. The multiple regression models used to investigate the influence of configurational metrics indicated that vegetation configuration is an important determinant of the influence of vegetation on LST. However, external factors such as pollution and weather conditions could affect the results. Despite the study limitations in terms of coarser spatial resolution and lack of considering climatic, environmental and health parameters of vegetation parameters, it provides an overview of the relationship between vegetation and LST and the spatial parameters that can influence it.

Publisher's Note: This paper, originally published on 29 January 2024, was withdrawn on 15 March 2024 per author's and organizer's request.

Climate change induced extreme rainfall events have become more frequent in urban cities in the Philippines. The Intergovernmental Panel on Climate Change warns that it will continue and become more regular. Vector-borne diseases such as dengue fever can become more common due to these events as it can provide an ideal breeding ground for mosquitos. In this paper, we study the association of a dengue outbreak in Mandaue city, Philippines with independent variables including climatic variables, the area’s impoundments, flood hazards, urbanization levels in terms of building and road density, and vegetation. The study's denominator is the barangay-level population data, and a rudimentary map of dengue incidence at the barangay-level was calculated and mapped. For the spatial association analysis, the Global Moran’s I index was used to measure autocorrelation between the locations of dengue cases. The results of this work suggest that inadequate flood control and water disposal facilities can increase the risk of a dengue outbreak, and there is a need to implement centralized dengue control strategies, including large-scale water drainage and sanitation drives, as well as public health awareness campaigns, to combat vector-borne disease epidemics.

Mangrove ecosystems are one of the blue carbon parameters with large carbon storage capabilities. The carbon sequestration is crucial in addressing the greenhouse effect that causes the rise of carbon emissions in the atmosphere. One of the measurements that can be made is the estimation of mangrove above-ground biomass (AGB). This is due to the binding of carbon stored in the form of mangrove biomass. The aim of this research is to estimate and map the spatial distribution of mangrove above-ground biomass (AGB) is conducted using WorldView-3 (WV-3) image, a high spatial resolution remote sensing data. We used Normalized Difference Vegetation Index (NDVI) and Soil Adjusted Vegetation Index (SAVI) to estimate mangrove above-ground biomass (AGB). Field data obtained from measuring mangrove tree diameter at breast height (DBH) which is then calculated using the allometric equation. We conducted regression analysis between field data and vegetation indices (NDVI and SAVI) to determine the most accurate vegetation index for estimating mangrove above-ground biomass values varied across the mangrove forest. This results of this research shows that the NDVI vegetation index provided higher accuracy for mangrove AGB estimation than SAVI index with R² of 0,603 and resulting the AGB value between 750 to 1.300 kg/m².

Active system remote sensing technology is increasingly developing in extracting information on the biophysical aspects of mangrove vegetation, such as mapping the percentage of canopy cover. Mapping the percentage of mangrove canopy cover is essential to maintain the stability of coastal ecosystems. This study uses airborne LiDAR data based on the First Return Cover Index (FRCI) to map and analyze the variation and spatial distribution of the canopy cover percentage in the Ratai Bay mangrove forest, Pesawaran, Lampung, Indonesia. This study aims to (1) Analyze the variation and spatial distribution of the percentage of FRCI-based mangrove canopy cover using LiDAR data and (2) Calculate the accuracy level of the mapping results. FRCI is a LiDAR point cloud data rasterization algorithm that calculates pixel value information from canopy cover recorded by airborne LiDAR. The canopy cover value at each pixel and the regression function obtained from field measurements were integrated to build a model to obtain a map of the percentage of mangrove canopy cover. The resulting map identifies that the Ratai Bay mangrove forest is dominated by the dense and evenly distributed canopy cover class with a mean cover value of 89.78%, generally found in almost all study areas. This FRCI-based mangrove canopy cover percentage mapping has high mapping accuracy with minimum and maximum accuracy values of 92.31% and 93.09%, respectively. The results of this study indicate that the biophysical aspects of mangrove vegetation, especially canopy cover, can be mapped using LiDAR data with the FRCI algorithm.

The Segara Anakan Lagoon (SAL) is a prominent estuarine mangrove ecosystem located in Java, which is recognised as the most densely populated island in Indonesia. SAL is a degraded mangrove forest due to the encroachment of mangrove edge ecotone species such as Nypa frutican (NF), as well as the proliferation of understory communities including Derris trifoliata and Acanthus spp. within the interior of the forest. Nevertheless, there has been a scarcity of research conducted on this particular phenomenon. The present study employed a land-use/cover change model to examine the following inquiries pertaining to the expansion of these communities: 1) What factors contributed to the expansion of the community?, and 2) What are the projected patterns of future community expansion? Various statistical models were employed to conduct a causal analysis in order to assess the factors influencing driving factors. The multitemporal mangrove maps from the previous study were used as input data for the model. Explanatory variables used in the model included environmental data, such as multi-temporal maps depicting the coastline of the lagoon, distances to the shoreline and river mouth, as well as the lagoon outlet. Additionally, multi-temporal maps representing ground elevation were also incorporated. The Conversion of Land Use and its Effects at Small Regional Extent (CLUE-S) dynamic model was employed to forecast the extent of land spreading. The dynamic model was executed utilising the provided statistical model as the input. The land-use/cover change (LULCC) methodology was employed to execute all procedures in R. The results of the study indicated that alterations in ground elevation and shoreline played a significant role in influencing the spread of NF) and understory, as well as the displacement of mangrove tree, particularly in the western region of the study area. According to the prediction model, it was forecasted that the invasion would persist unless the influencing factors were effectively controlled.

Forest Fire Danger Rating System (FDRS) developed in Indonesia is based on the Canadian Forest Fires Danger Rating System. The Meteorology, Climatology, and Geophysics Agency operates and publishes a daily Fire Weather Index system on its website as part of the FDRS. The so-called SPARTAN system is based on weather elements of rainfall, air temperature, wind speed, and humidity and does not consider soil conditions. This research aims to improve the Fire Weather Index system by adding information on land conditions. In this study, the area of interest was South Sumatera Province of Indonesia and the period of analysis was 2019. The normalized difference polarization index (NDPI) derived from the Synthetic Aperture Radar (SAR) data of the Sentinel-1 satellite and land cover changes and fire incidents derived from the optical data of the Sentinel-2 satellite are used to represent land conditions. Since NDPI shows a good correlation with the degree of soil moisture, the NDPI is considered for the soil moisture conditions. Furthermore, integrating soil moisture conditions and land cover changes into the FWI system provides better early warning information for land/forest fires. Fire hotspot data and in-situ fire information are used to validate the results. This study concludes that adding information on land conditions will provide detailed and better land/forest fire warnings.

Mangroves play important roles in the blue carbon ecosystem. Mangrove map is important data, robust and reproducible methods for mangrove mapping and monitoring are needed. Along with the freely available optical remote sensing satellite data such as Sentinel-2 and the development of deep learning fields, mangrove mapping and monitoring are more reachable. Therefore, the main goal of this study is to evaluate and utilize some state-of-the-art deep learning semantic segmentation architectures (U-Net, LinkNet, PSPNet, and FPN) for mangrove mapping and monitoring. This study will provide evidence of the ability of state-of-the-art deep learning semantic segmentation that can provide a robust and reproducible method for mangrove mapping and monitoring. The study area is the coastal zone of Rookery Bay, Florida, USA. The Sentinel-2 bottom-of-atmosphere corrected reflectance data (2016) with the target data (water body, nonmangrove, and mangrove) used for training and evaluating the capability of U-Net, LinkNet, PSPNet, and FPN for mangrove mapping. While, for the mangrove monitoring evaluation, the best trained deep learning model based on the 2016 dataset was used here to produce a new mangrove map in 2022. The reference data were collected from google earth imagery in 2022 by visual interpretation (250 points for each class) and conducted mangroves monitoring evaluation by calculating class accuracy and overall accuracy for the produced mangrove map in 2022. Based on the experiment results, all of the state-of-the-art deep learning semantic segmentation architectures have promising results and U-Net achieved the highest performance with an average intersection over union (IoU) score of 0.926. Based on the evaluation result, the trained deep learning model based on the 2016 dataset successfully produced a mangrove map using 2022 Sentinel-2 data with an overall accuracy of around 0.98. This finding indicates the ability of U-Net, LinkNet, PSPNet, and FPN for mangrove mapping and monitoring.

Green space beside has an ecological function also stabilize the psychology people and provides coolness, comfort, and peace because it has a high oxygen content and good humidity. Seeing the scenery, lush plants, soothing aromas, splashing water, and a high oxygen content have a positive effect on human mental health. Therefore, the use of natural forests for eco-therapy healing is urgently needed at this time. This study aims to identify the potential of the TWA Gunung Kelam area as a basis for preparing designs for the development of ecotherapy healing forest in West Kalimantan, based on with the criteria of vegetation index density (NDVI), microclimate, noise level, wind speed, and also the negative ion content of each site used for eco-therapy. Normalized Difference Vegetation Index (NDVI) plays a very important role in this research, will affect the level of comfort and response to human health and microclimate. The research method involving 6 sites and 89 populations with 44 samples students at kapuas university with stratified random sampling. The cycle was carried out 5 times, by measuring health before and after attending therapy. The results obtained from measurements for each site are NDVI, temperature, temperature humidity index, noise level, wind speed, and negative ion content which are included in the comfortable and good for health category, only the air humidity value is quite high Based on DASS 42 evaluation, it also showed a decrease in Stress values after participating in treatment. Based on analyses, Gunung Kelam TWA could developed as a location for eco-therapy healing forests, by utilizing the forest environment which has abundant natural resources.

The health of Indonesian rubber plantations has recently been compromised by rubber leaf fall disease, prompting a need for effective monitoring techniques. This study explores the use of high-resolution aerial photographs to assess rubber plant health through canopy density analysis. We employed the Random Forest machine learning algorithm for this purpose, focusing on two classification systems: [low, medium, high] and [low, high] canopy densities. Our findings reveal contrasting levels of accuracy between the two classification systems. The three-tier classification ([low, medium, high]) resulted in moderate accuracy (Overall Accuracy: 0.50, Kappa Value: 0.24), suggesting that this approach might be too detailed for the task. In contrast, the binary classification ([low, high]) demonstrated significantly better performance, with satisfactory accuracy (Overall Accuracy: 0.76, Kappa Value: 0.33). This improvement indicates that a simpler classification system with fewer categories is more effective for identifying the health of rubber plants using aerial photographs and machine learning techniques. This study underscores the importance of selecting an appropriate level of classification detail in machine learning models for agricultural monitoring. The results suggest that less complex models, with fewer canopy density categories, are more suitable for accurately assessing the health of rubber plants in situations like the rubber leaf fall disease outbreak in Indonesia.

Palawan is considered "the last frontier" of the Philippines; in light of this, the province receives special attention from the national and international community. Despite this, there are still numerous issues that need to be addressed, including illegal burning activities. Based on reports and satellite image analyses, slash-and-burn (kaingin) farming is pervasive in Palawan. Burned areas are easily detected from optical satellite images using the Normalized Burn Ratio (NBR) or similar indices. However, the usefulness of optical imagery is severely limited by persistent cloud cover, especially in upland areas where kaingin is commonly practiced. This study focuses on the utilization of Sentinel-1 SAR data in monitoring the burned areas due to its ability to penetrate clouds, smoke, and haze. Radar burn and vegetation indices such as Radar Burn Difference (RBD), Radar Burn Ratio (RBR), Radar Vegetation Index (RVI), and Radar Forest Degradation Index (RFDI) were used to detect the burned areas. These were then cross-validated with the NBR layer. RBD index yielded better results compared to other radar burn and vegetation indices in mapping the burned areas. Additionally, the RBD using the VH polarization band provided detailed delineation of burned areas than that using the VV polarization band. In the operational monitoring of burned areas, the synergistic use of burned indices from optical and SAR images is recommended.

The objective of this study is to identify variations in the level of accuracy of the Forest Canopy Density (FCD) method's utilization of thermal index (TI). This is significant because the FCD approach can be used to determine vegetation cover without relying on the TI indicator. The four primary indicators used in the initial development of the FCD approach by Rikimaru et al. were the vegetation index, shadow index, soil index, and thermal index. The Split Windows Algorithm (SWA), which is the most effective for Landsat 8 OLI/TIRS imagery with a combination of bands 10 and 11, is utilized as the thermal index calculation method. SWA is obtained by concentrating on variations in the vegetation index value used to calculate surface emissivity. Hence, two types of FCD—SWA FCD and non-SWA FCD—are developed. The results showed that accuracy is obtained using the error matrix: the non-SWA FCD is 42% and the SWA FCD is 53%. In addition, the 1 × 1 test plot further show that SWA FCD tends to overestimate, while non-SWA FCD tends to underestimate. The overall accuracy of the analysis conditions may be impacted by the availability of additional samples and the occurrence of the COVID-19 incident. Based on this, that FCD with four indicators may be more accurate than FCD without TI. Despite the need to deep attention to the high-FCD class of analysis, which has a propensity to overestimate.

In recent years, rubber plantations in Indonesia have been attacked by the Pestalotiopsis sp. leaf fall disease, which has caused a significant leaf fall that then creates a decline in latex production. Remote sensing data can be used to monitor the health of rubber plants. Sentinel-1 imagery is used to overcome cloud cover constraints in optical imagery at the Rubber Plantation. This study aims to analyze the spatial distribution and monthly rubber plant health trends using the radar vegetation indexes in Sembawa Rubber Plantation, South Sumatera, Indonesia. Furthermore this study compares the performance of two radar vegetation Index namely the RVI (Radar Vegetation Index) and NDRVI (Normalize Different Radar Vegetation Index) algorithms. The results of this study indicate that the vegetation index indicates the health of the rubber plant based on the leaf fall cycle due to Pestalotiopsis sp. within 5 months. A low index value indicates leaf fall, and a high value indicates regrowth.