High spatial and temporal resolution data is vital for crop monitoring and phenology change detection. Due to the lack of satellite architecture and frequent cloud cover issues, availability of daily high spatial data is still far from reality. Remote sensing time series generation of high spatial and temporal data by data fusion seems to be a practical alternative. However, it is not an easy process, since it involves multiple steps and also requires multiple tools. In this paper, a framework of Geo Information System (GIS) based tool is presented for semi-autonomous time series generation. This tool will eliminate the difficulties by automating all the steps and enable the users to generate synthetic time series data with ease. Firstly, all the steps required for the time series generation process are identified and grouped into blocks based on their functionalities. Later two main frameworks are created, one to perform all the pre-processing steps on various satellite data and the other one to perform data fusion to generate time series. The two frameworks can be used individually to perform specific tasks or they could be combined to perform both the processes in one go. This tool can handle most of the known geo data formats currently available which makes it a generic tool for time series generation of various remote sensing satellite data. This tool is developed as a common platform with good interface which provides lot of functionalities to enable further development of more remote sensing applications. A detailed description on the capabilities and the advantages of the frameworks are given in this paper.
The semi-Mediterranean Zagros forests in western Iran are a crucial source of environmental services, but are severely threatened by climatic and anthropological constraints. Thus, an adequate inventory of existing tree cover is essential for conservation purposes. We combined ground samples and Quickbird imagery for mapping the canopy cover in a portion of unmanaged Quercus brantii stands. Orthorectified Quickbird imagery was preprocessed to derive a set of features to enhance the vegetation signal by minimizing solar irradiance effects. A recursive feature elimination was conducted to screen the predictor feature space. The random forest (RF) and support vector machines (SVMs) were applied for modeling. The input datasets were composed of four sets of predictors including the full set of predictors, the four original Quickbird bands, selected vegetation indices, and the soil line-based vegetation indices. The highest r2 and lowest relative root mean square error (RMSE) were observed in modeling with total indices and the full data set in both modeling methods. Regardless of the input dataset used, the RF models outperformed the SVM by returning higher r2 and lower relative RMSEs. It can be concluded that applying these methods and vegetation indices can provide useful information for the retrieval of canopy cover in mountainous, semiarid stands which is crucial for conservation practices in such areas.
Accurate crop identification and crop area estimation are important for studies on irrigated agricultural systems, yield and water demand modeling, and agrarian policy development. In this study a novel combination of Random Forest (RF) and Support Vector Machine (SVM) classifiers is presented that (i) enhances crop classification accuracy and (ii) provides spatial information on map uncertainty. The methodology was implemented over four distinct irrigated sites in Middle Asia using RapidEye time series data. The RF feature importance statistics was used as feature-selection strategy for the SVM to assess possible negative effects on classification accuracy caused by an oversized feature space. The results of the individual RF and SVM classifications were combined with rules based on posterior classification probability and estimates of classification probability entropy. SVM classification performance was increased by feature selection through RF. Further experimental results indicate that the hybrid classifier improves overall classification accuracy in comparison to the single classifiers as well as user´s and producer´s accuracy.
Sustainability of irrigated agriculture-based economies, such as in Central Asia, is threatened by cropland degradation. The field-based identification of the degraded agricultural areas can aid in developing appropriate land rehabilitation and monitoring programs. This paper combined the object-based change detection and spectral mixture analysis to develop an approach for identifying parcels of irrigated degraded cropland in Northern Uzbekistan, Central Asia. A linear spectral unmixing, followed by the object-based change vector analysis, was applied to the multiple Landsat TM images, acquired in 1987 and 2009. Considering a spectral dimensionality of Landsat TM, a multiple 4-endmember model (green vegetation, water, dark soil, and bright soil) was set up for the analysis. The spectral unmixing results were valid, as indicated by the overall root mean square errors of <2.5% reflectance for all images. The results of change detection revealed that about 33% (84,540 ha) of cropland in the study area were affected by the degradation processes to varying degrees. Spatial distribution of degraded fields was mainly associated with the abandoned fields and lands with inherently low fertile soils. The proposed approach could be elaborated for a field-based monitoring of cropland degradation in similar landscapes of Central Asia and elsewhere.
Drought monitoring models and products assist decision makers in drought planning, preparation, and mitigation, all of which can play a role in reducing drought impacts. In this study, the performance of two newly developed remote sensing-based drought indices, the perpendicular drought index (PDI) and modified perpendicular drought index (MPDI), are further explored for regional drought monitoring in agricultural regions located in central and south western Asia. The study area covers regions from moderate and wet climatological zones with dense vegetation coverage to semi-arid and arid climatological conditions with moderate to poor vegetation coverage. The spatio-temporal patterns of surface drought derived by PDI and MPDI from 250m MODerate Resolution Imaging Spectroradiometer (MODIS) data in 8-day time steps are compared against two other drought indices: the Standardized Precipitation Index (SPI) as a meteorological drought index and the potential evapotranspiration (ET0) as an agro-meteorological drought index, which both were calculated based on field-measured precipitation and regional meteorological parameters. In addition, 8-day MODIS Normalized Difference Vegetation Index (NDVI) was calculated and its performance to detect drought occurrence and measuring of drought severity compared with the two perpendicular drought indices. Significant correlations were found between the PDI, the MPDI and precipitation and other applied meteorological and agrometeorological drought indices. The results confirm previous studies which has been analyzing the PDI and the MPDI over some study points in Iran. In this research, however, implementation of higher resolution data (MOD09Q1) in both spatial (250 m) and temporal (8-days) dimensions revealed a greater agreement between the drought information extracted by the MPDI, PDI and field meteorological measurements. It could be concluded that the applied perpendicular indices could be used as a drought early warning system over case study region and other regions with similar arid and semi-arid climatological conditions.
Accurate information about land use patterns is crucial for a sustainable and economical use of water in agricultural systems. Water demand estimation, yield modeling and agrarian policy are only a few applications addressed by land use classifications based on remote sensing imagery. In Central Asia, where fields are traditionally large and state order crops dominate the area, small units of fields are often separated for the additional cultivation of income crops for the farmers. Traditional object based land use classifications on multi-temporal satellite imagery using field boundaries show low classification accuracies on these separated fields, expressed by a high uncertainty of the final class labels. Although segmentation of smaller subfields was shown to be suitable for improving the classification result, the extraction of subfields is still a time-consuming and error-prone process. In this study, energy based Graph-Cut segmentation technique is used to enhance the segmentation process and finally to improve the classification result. The interactive segmentation technique was successfully adopted from bio-medical image analysis to fit remote sensing imagery in the spatial and in the temporal domain. A set of rules was developed to perform the image segmentation procedure on pixels of single satellite datasets and on objects representing time series of a vegetation index. An ensemble classifier based on Random Forest and Support Vector Machines was used to receive information about classification uncertainty before and after applying the segmentation. It is demonstrated that subfield extraction based on Graph Cuts outperforms traditional image segmentation approaches in simplicity and reduces the risk of under- and over-segmentation significantly. Classification uncertainty decreased using the derived subfields as object boundaries instead of original field boundaries. The segmentation technique performs well on several multi-temporal satellite images without changing parameters and may be used to refine object based land use classifications to subfield level.
Monitoring of vegetation dynamics in extensive irrigated croplands is essential for improving land and water
management, especially to understand the reaction of the system to water scarcity and degradation processes. This study focuses on the assessment of irrigated cropland dynamics in the western part of the Aral Sea Basin in Central Asia during the past decade. Extend of cropland and spatio-temporal cropping patters are analyzed based on phenological profiles extracted from 16day MODIS vegetation index time series at a spatial resolution of 250m. Knowledge-based classifications which needed to be adjusted for every single year were applied to distinguish between cropland and other major land cover types, the desert or sparsely vegetated steppes, settled areas, and water bodies. Interannual variability of the time series in the maximum cropland extend recorded between 2001 and 2010 was assessed by using Pearson’s cross correlation (PCC) coefficient. Shifts of maximum one month (+/-) were tested and the highest PCC coefficient was selected. Accuracy assessment using a multi-annual MODIS classification conducted for a representative irrigation system between 2004 and 2007 returned acceptable results for the cropland mask (<90%). Comparing the inter-annual cropland dynamics revealed using PCC with both, the MODIS classifications 2004-2007 and pure pixels of aggregated ASTER based maps showed that the PCC only permits differentiation between different modalities in the time series, i.e. years of a varying number of intra-annual crop cycles. However, simply overlaying the cropland extends 2001-2010 already exhibits areas of unreliable water supply. In this light, integration of both, PCC analysis of MODIS time series and annual maps of the cropland extent can be concluded as valuable next steps for better understanding the dynamics of the irrigated cropland at regional scale not only in the Aral Sea Basin of Central Asia, but also in other arid environments, where irrigation agriculture is essential for rural income generation and food security.
Satellite remote sensing is an invaluable tool to assess the status and changes of irrigated agricultural systems.
Agricultural sites are among the most heterogeneous sites at the landscape level: spatial pattern of agricultural fields,
within-field heterogeneity, crop phenology and crop management practices vary significantly. Highly dynamic objects
(crops and crop rotations) result in large temporal variability of surface spatial heterogeneity. Technological advances
have opened the possibility to monitor agricultural sites combining satellite images with both high spatial resolution and
high revisit frequency, which could overcome these constraints. Yet depending on the field sizes and crop phenology of
the agricultural system observed, requisites in terms of the instrument´s spatial resolution and optimal timing of crop
observation will be different. The overall goal is to quantitatively define region specific satellite observation support
requirements in order to perform land use classification at the field basis. The main aspect studied here is the influence of
spatial resolution on the accuracy of land use classification over a variety of different irrigated agricultural landscapes.
This will guide in identifying an appropriate spatial resolution and input parameters for classification. The study will be
performed over distinct locations in irrigated agro-ecosystems in Central Asia, where reliable information on agricultural
crops and crop rotations is needed for sustainable land and water management.
In Central Asia, more than eight Million ha of agricultural land are under irrigation. But severe degradation problems and
unreliable water distribution have caused declining yields during the past decades. Reliable and area-wide information
about crops can be seen as important step to elaborate options for sustainable land and water management. Experiences
from RapidEye classifications of crop in Central Asia are exemplarily shown during a classification of eight crop classes
including three rotations with winter wheat, cotton, rice, and fallow land in the Khorezm region of Uzbekistan covering
230,000 ha of irrigated land. A random forest generated by using 1215 field samples was applied to multitemporal
RapidEye data acquired during the vegetation period 2010. But RapidEye coverage varied and did not allow for
generating temporally consistent mosaics covering the entire region. To classify all 55,188 agricultural parcels in the
region three classification zones were classified separately. The zoning allowed for including at least three observation
periods into classification. Overall accuracy exceeded 85 % for all classification zones. Highest accuracies of 87.4 %
were achieved by including five spatiotemporal composites of RapidEye. Class-wise accuracy assessments showed the
usefulness of selecting time steps which represent relevant phenological phases of the vegetation period. The presented
approach can support regional crop inventory. Accurate classification results in early stages of the cropping season
permit recalculation of crop water demands and reallocation of irrigation water. The high temporal and spatial resolution
of RapidEye can be concluded highly beneficial for agricultural land use classifications in entire Central Asia.
The Moderate Imaging Spectroradiometer (MODIS) provides operational products of the Normalized Difference
Vegetation Index (NDVI), the Enhanced Vegetation Index (EVI), and the fraction of photosynthetic active radiation
(fPAR). FPAR can be used in productivity models, but agricultural applications depend on sub-pixel heterogeneity.
Examples for heterogeneous areas are the irrigation systems of the inner Aral Sea Basin, where the 1 km fPAR product
proved less suited. An alternative can be to upscale fPAR to the 250 m scale, but there are few studies evaluating this
approach. In this study, the use of MODIS 250 m NDVI and EVI for this approach was investigated in an irrigation
system in western Uzbekistan. The analysis was based on high resolution fPAR maps and a crop map for the growing
season 2009, derived from ground measurements and multitemporal RapidEye data. The data was used to explore
statistical relationships between RapidEye fPAR and MODIS NDVI/EVI with respect to spatial heterogeneity. The
correlations varied between products (daily NDVI, 8-day NDVI, 16-day NDVI/EVI), with results suggesting that 8-day
NDVI performed best. The analyses and the compiled fPAR maps show that, compared to 1 km MODIS fPAR, the 250 m
scale is more homogeneous, allows for crop-specific analyses, and better captures the spatial patterns in the study region.
In the face of global change, concepts for sustainable land management are increasingly requested, among others to cope
with the rapidly increasing energy demand. High resolution land use classifications can contribute spatially explicit
information suitable for land use planning. In this study, the coverage of cereal crops was derived for two regions in
Baden-Wuerttemberg and Rhineland-Palatinate - Germany, as well as in the Alsace - France, by classifying multitemporal
and multi-scale remote sensing data. The presented methodology shall be used as basic input for high resolution
bio-energy potential calculations.
Segmentation of pan-merged 15 m Landsat 7 ETM+ data and pre-classification with CORINE data was applied to derive
homogenous objects assumed to approximate the field boundaries of agricultural areas. Seven acquisitions of moderate
resolution IRS-P6 AWiFS data (60 m) recorded during the vegetation period of 2007 were used for the subsequent
classification of the objects. Multiple classification and regression trees (random forest) were selected as classification
algorithm due to their ability to consider non-linear distributions of class values in the feature space. Training and
validation was based on a subset of 1724 samplings of the official European land use survey LUCAS (Land Use/ Cover
Area Frame Statistical Survey).
Altogether, the object based approach resulted in an overall accuracy of 74 %. The use of 15 m Landsat for mapping
field objects were identified to be one major obstacle caused by the characteristically small agricultural units in
Southwest Germany. Improvements were also achieved by correcting the LUCAS samples for location errors.
Remote sensing offers the opportunity to produce land cover classifications for large and remote areas on a yearly basis and is an important tool in regions that lack these information.
However often training and validation data to generate annual land cover maps are not available in necessary quantity - being from one year only or covering only a small extent of the region of interest.
This study was focused on land use classifications at regional scale with a special emphasize on annual updates under the constraint of limited sampling data. Often, sampling is reduced to one year or to an unrepresentative area extend within the region of interest. The investigations for the period between 2004 and 2009 were conducted in the irrigation systems of the Amu Darya Delta in Central Asia, where reliable information on crop rotations is required for sustainable land and water management.
Annual training and validation data were extracted from high resolution land use classifications. For classification, statistical features based on MODIS time series of vegetation indices, reflectance and land surface temperature (LST) were calculated and a random forest algorithm was applied.
By a combination of training data from different years, the accuracy could be enhanced from an overall accuracy of 70% to more than 90% for a focused subregion and also good consistency with high resolution images for the other parts of the delta, which has to be confirmed using quantitative validation. A combination of a different number of years was tested. Already two years can be sufficient to generate a robust and transferable random forest to produce yearly land use maps.
The study shows the possibility to combine training data from different years for the annual classification of irrigated croplands on a regional scale.
Land surface biophysical parameters such as the fraction of photosynthetic active radiation (fPAR) and leaf area
index (LAI) are keys for monitoring vegetation dynamics and in particular for biomass and carbon flux simulation.
This study aimed at deriving accurate regression equations from the newly available RapidEye satellite sensor
to be able to map regional fPAR and LAI which could be used as inputs for crop growth simulations. Therefore,
multi-temporal geo- and atmospherically corrected RapidEye scenes were segmented to derive homogeneous
patches within the experimental fields. Various vegetation indices (VI) were calculated for each patch focusing
on indices that include RapidEye's red edge band and further correlated with in situ measured fPAR and LAI
values of cotton and rice. Resulting coefficients of determination ranged from 0.55 to 0.95 depending on the
indices analysed, object scale, crop type and regression function type. The general relationships between VI and
fPAR were found to be linear. Nonlinear models gave a better fit for VI-LAI relation. VIs derived from the red
edge channel did not prove to be generally superior to other VIs.
Seasonal evapotranspiration is an essential measure to model crop growth and hydrological balances particularly for irrigation agriculture in semi-arid environments. Hydrological models traditionally integrate single-spot measurements of meteorological stations to estimate potential evapotranspiration. During the last years, the application of thermal remote sensing data in combination with meteorological data of soil-vegetation-atmosphere models facilitated the estimation of actual evapotranspiration on a large scale. This study employed multi-temporal Moderate Resolution Imaging Spectroradiometer (MODIS) data to apply the Surface Energy Algorithm for Land (SEBAL) model to the heterogeneous environment of the Khorezm region, Uzbekistan. Further meteorological data was used to extrapolate actual evapotranspiration to seasonal actual evapotranspiration. The validation of the modeled actual evapotranspiration showed acceptable accuracy when compared to the limited point-based ground truth data. The integration of a rule-based land use classification with higher spatial resolution revealed the necessity to include sub-pixel knowledge of land use distribution to interpret the modeling results. First evaluations of the water distribution and consumption situation were achieved by interpretation of modeled seasonal actual evapotranspiration with hydrological GIS information.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.