Paddy Rice Mapping in Hainan Island Using Time-Series Sentinel-1 SAR Data and Deep Learning

Rice serves as a fundamental staple food for a significant portion of the global population, and accurate monitoring of paddy rice cultivation is essential for achieving Sustainable Development Goal (SDG) 2-Zero Hunger. This study proposed two models, RiceLSTM and RiceTS, designed for the precise extraction of paddy rice areas in Hainan Island using time-series Synthetic Aperture Radar (SAR) data. The RiceLSTM model leverages a Bidirectional Long Short-Term Memory (BiLSTM) network to capture temporal variations in SAR backscatter and integrates an attention mechanism to enhance sensitivity to paddy rice phenological changes. This model achieves classification accuracies of 0.9182 and 0.9245 for early and late paddy rice, respectively. The RiceTS model extends RiceLSTM by incorporating a U-Net architecture with MobileNetV2 as its backbone, further improving the classification performance, with accuracies of 0.9656 and 0.9808 for early and late paddy rice, respectively. This enhancement highlights the model's capability to effectively integrate both spatial and temporal features, leading to more precise paddy rice mapping. To assess the model's generalizability, the RiceTS model was applied to map paddy rice distributions for the years 2020 and 2023. The results demonstrate strong spatial and temporal transferability, confirming the model's adaptability across varying environmental conditions. Additionally, the extracted rice distribution patterns exhibit high consistency with statistical data, further validating the model's effectiveness in accurately delineating paddy rice areas. This study provides a robust and reliable approach for paddy rice mapping, particularly in regions that are characterized by frequent cloud cover and heavy rainfall, where optical remote sensing is often limited.