Maize is one of most widely grown crop among the cereals and accurate estimation of maize area was crucial for effective agricultural management and food security. Integration of Synthetic Aperture Radar (SAR) data and ground truth data emerged as a valuable remote sensing tool for maize area estimation in the Amaravathi River Basin, Tamil Nadu, during rabi season of 2024–25. This research leverages multi-temporal Sentinel-1 A SAR backscatter time series, which can penetrate cloud cover, to capture maize crop dynamics, phenology, and spatial distribution. By analyzing temporal backscatter signatures, we identify maize phenological stages and determine optimal SAR features for accurate crop discrimination under cloud-prone conditions. The backscatter signature of maize showed a minimum VH backscatter dB value at sowing indicating the Start of Season (SoS). The multi-temporal Synthetic Aperture Radar (SAR) imagery underwent automated processing, extracting features crucial for maize classification. Classification accuracy assessment revealed robust performance, with 89.3% accuracy for maize and 90% for non-maize locations, supported by a Kappa index of 0.79. The findings emphasize that effective agricultural planning must be customized to local conditions. When planners have access to thorough analysis and accurate land measurements, they can efficiently do planning for rural development.
Sabharwal et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: