Accurate crop classification with Synthetic Aperture Radar (SAR) data is a significant area of research and translating into practice from local to regional scale crop inventory mapping. With the growing accessibility to abundant data sources from both current and upcoming dual-polarimetric SAR missions, the capability to generate precise crop maps is set to enhance substantially. The geometric and dielectric properties of targets highly influence radar backscatter. Especially for agricultural crops, which exhibit dynamic changes in target properties and physiological structure throughout their phenology, discriminating between crops using SAR data remains a significant challenge. This study introduces a novel Gaussian process classifier model called the Evidence Modified Gaussian Process Classifier (EM-GPC) that employs a regression approach for multi-class crop classification with a modified evidence. We utilise dual-polarimetric SAR data acquired over two study sites to perform crop classification utilising EM-GPC. At first, we perform a phenology-based single-date crop classification using ESAR C- and L-band SAR data acquired over the DEMMIN site in Germany. The performance evaluation of the EM-GPC model revealed robust accuracy during various crop phenological stages, showcasing its adaptability to temporal variations. Further, we perform a multi-date crop classification using C-band RADARSAT-2 and L-band simulated NISAR product from UAVSAR data acquired over Manitoba, Canada. In this study, EM-GPC successfully classifies major crop types (wheat, canola, soybeans, corn, barley, oats, and rye). The efficacy of the proposed model establishes its capability for crop classification utilising dual-polarimetric SAR data in operational settings.
Vegetation serves as a vital carbon sink, crucial for regulating CO2 and O2 levels in the atmosphere. However, the declining health of vegetation can contribute to a rise in greenhouse gas emissions. Utilizing remote sensing satellite imagery, we can effectively monitor global changes in vegetation health in near-real time. While various indices have been proposed for monitoring specific biochemical properties of vegetation, they often fail to detect health deterioration caused by multiple stressors like excessive heat, salinity, and water scarcity. All of the stress caused by these stressors may not be adequately identified by indices primarily sensitive to single-leaf parameters. Thus, this study introduces a novel vegetation health indicator that identifies vegetation stress-induced changes in chlorophyll, water, and protein content. This index was validated through lab-based spectroscopy experiments and global sensitivity analysis using physical models. Results from spectroscopy experiments highlight the limitations of the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Moisture Index (NDMI) in detecting specific stressors. However, the proposed index demonstrates proficiency in detecting a broader spectrum of stresses. Global sensitivity analysis indicates promising results, showing the sensitivity to chlorophyll and water content variations in the proposed index. Further analysis, focusing on the phenology of corn crops using Sentinel-2 data, demonstrates the usefulness of our new index (SVHI) in distinguishing characteristic vegetation changes while effectively differentiating non-vegetated areas like water bodies.