Information on mangrove species plays crucial role for sustainable management of coastal ecosystems. However, the current in-depth data acquisition for sustainable management of coastal ecosystems is still collected manually. The increased demand to obtain mangrove environmental data in a short time and at affordable cost has encouraged our research to develop an automatization method for determining the species based on the images of mangrove leaf. In this paper the authors used a deep learning method that uses the Convolutional Neural Network (CNN) to overcome manual leaf sample identification during image recognition process. CNN is used to process the machine learning on a personal computer. Stages on CNN were data input, preprocessing and training. CNN was implemented by using tensorflow libraries through the transfer learning process to recognize three mangrove species of northern coast of Probolinggo, East Java, Indonesia. The recognition process is based on images of the mangrove leaf shape. This method was simple and can be reproduced by anyone without the need for in-depth computer programming knowledge. In a relatively short time, the method has been proven to give high accuracy of predicted results. Field test showed that this method can determine and distinguish the leaves of the three species of mangrove well. In the future this method will be developed to identify mangrove plants using Unmanned Aerial Vehicle (UAV).
Currently a combination of fluorescence microscopy with spectroscopic analysis in a balance way has played an important role in providing new and exciting information for the in vivo study of cell, such as diatoms, photosynthetic marine microorganisms. Diatoms contain photosynthetic pigments, carotenoid and chlorophylls molecules, in their machinery to harvest the sunlight energy for growth. Lacking of these pigments might influence to the overall metabolisms of the cells. Here we reported our work to construct a simple homebuilt confocal fluorescence spectromicroscopy to study the cells of Chaetoceros muelleri diatom. The setup was design to get simultaneous data of the image of the single fluorescence cell and the emission spectrum of it.
Soybeans is one of main crops in Indonesia but the demand for soybeans is not followed by an increase in soybeans
national production. One of the production limitation factor is the availability of lush cultivation area for soybeans
plantation. Indonesian farners are usually grow soybeans in marginal cultivation area that requires soybeans varieties
which tolerant with environmental stress such as drought, nutrition limitation, pest, disease and many others. Chlorophyll
content in leaf is one of plant health indicator that can be used to determine environmental stress tolerant soybean
varieties. However, there are difficulties in soybeans breeding research due to the manual acquisition of data that are
time consume and labour extensive. In this paper authors proposed automatic system of soybeans leaves area and
chlorophyll quantification based on low cost multispectral sensor using web camera as an indicator of soybean plant
tollerance to environmental stress particularlly drought stress. The system acquires the image of the plant that is placed
in the acquisition box from the top of the plant. The image is segmented using NDVI (Normalized Difference Vegetation
Index) from image and quantified to yield an average value of NDVI and leaf area. The proposed system showed that
acquired NDVI value has a strong relationship with SPAD value with r-square value 0.70, while the leaf area prediction
has error of 18.41%. Thus the automation system can quantify plant data with good result.