Integrating Soil Spectral Library and PRISMA Data to Estimate Soil Organic Carbon in Crop Lands

The increasing demand for precise soil organic carbon (SOC) monitoring in croplands, crucial for food security (SDG 2), has led to the exploration of fusing soil spectral libraries (SSL) with hyperspectral sensing data for SOC estimation. However, the widespread adoption of SSL for SOC estimation faces challenges, particularly in developing nations, due to inconsistent calibration libraries and reliable estimation models. Further, SSL rely on regular soil sample collection and spectral data recording using spectroradiometers, which is impractical in agricultural-predominant countries like India with limited time for sample collection between crop rotations. To address this challenge, we developed synthesised SSL in lab conditions and integrated it with hyperspectral data using Machine Learning (ML) algorithms to bridge the gap between synthesised SSL and hyperspectral data for local-scale SOC mapping. This approach was tested by mapping SOC in Mysore, India, using spectroradiometer hyperspectral measurements and PRISMA sensor data. The proposed approach and synthesised SSL exhibited better performance, with R2 prediction accuracies of 0.92 and 0.79 and RMSE values of 2.31 g/kg and 9.91 g/kg, respectively, for PRISMA and lab spectroscopy data. These results highlight the potential of synthesised SSL for SOC prediction in alluvial soils, leveraging local datasets and hyperspectral data. Our future work will expand the synthesis approach to new Indian study areas, particularly those with alluvial soil origins, further enhancing the applicability of this methodology for SOC estimation and aiding food security efforts.