Technology-driven chickpea yield estimation using remote sensing and crop modeling

This study estimated chickpea area and yield in Vidisha district, Madhya Pradesh, during Rabi 2022-23 by integrating Sentinel-1A SAR satellite data with the CROPGRO-Chickpea crop simulation model. Sentinel-1A VH-polarized GRD data (20 m spatial resolution) were processed using MAPscape software at 12-day intervals. Temporal backscatter analysis identified distinct growth-stage signatures, enabling accurate crop classification. The total classified chickpea area was 109112 ha. Classification accuracy was 86.8 %, with a Kappa coefficient of 0.74. The DSSAT model simulated chickpea growth and yield, with maximum Leaf Area Index ranging from 1.8 to 4.9 and yields from 1410 to 2449 kg ha-1. Remote sensing-based chickpea yield estimates ranged between 1420 and 2330 kg ha-1. Validation showed strong agreement between observed and simulated values, with accuracies of 89.1 % for LAI and 91.7 % for yield. This study underscores the effectiveness of integrating remote sensing and crop modelling for precise, scalable agricultural monitoring, supporting sustainable crop management and food security.