MODIFIED U-NET BY ADDING TWIN EXTRACTORS FOR MULTI-SENSOR SATELLITE IMAGES FUSION TO MAP MANGROVE FOREST

Mangrove forest is an important vegetation that has many benefits and the mangrove map is important data for many further analyses. Satellite images including optical and synthetic aperture radar (SAR) images have been widely used for mangrove forest mapping. Recently, many researchers have developed and used machine learning and deep learning algorithms for mangrove mapping using satellite imagery. U-Net is one of the deep learning semantic segmentation algorithms that is widely used for many fields including mangrove mapping and has shown promising results. The main goal of this study is to modify U-Net architecture by adding twin extractor parts that will be used for multi-sensor satellite image fusion. We used optical satellite images (Sentinel-2) and SAR satellite images (Sentinel-1). The twin extractor parts will extract the information from optical and SAR images separately and then fuse the extracted features using concatenated layer, after that the fused features will be fed to the U-Net architecture. We adopted the inception module for the twin extractor part. The study area is located in the coastal zone of Rookery Bay, Florida, USA. The target data (mangrove and non-mangrove) for this study was collected by visual interpretation based on reference data from the global mangrove watch. We compare our modified U-Net with the original U-Net architecture in the evaluation process, we just combine the Sentinel-2 and Sentinel-1 data together for the original U-Net architecture input. Based on the experiment results, the modified U-Net and the original U-Net has intersection over union (IoU) score of mangrove class of 0.9404 and 0.9333, respectively. While the F1-score of the mangrove class from modified U-Net and original U-Net are 0.9693 and 0.9655, respectively. Based on this result, by adding the fusion twin extractor parts in the U-Net architecture can improve the performance of mangrove mapping using optical and SAR imagery.