A Review Of Soil Organic Carbon (SOC) Prediction Techniques In Agricultural Lands Using Remote Sensing

The geological, ecological, and biological ecosystems of the planet have changed because of the global climate crisis, and this poses a serious threat to humanity as well as the conservation of agricultural productivity and food security. The European Commission outlined the continent's objective to become climate neutral by 2050 with zero net Greenhouse Gas (GHG) emissions. Soil organic carbon (SOC) is closely related to soil quality and has a significant impact on how soil and plants interact. SOC monitoring gives a unique role in agricultural sustainability thus precise prediction and monitoring of SOC is essential. Remote Sensing (RS) evolution, big data accessibility and Deep Learning (DL) architectures present enormous potential for extensive SOC monitoring. Several RS applications (e.g., Sentinels, MODIS, Landsat etc.) along with machine learning and DL methodologies (e.g., RF, ANN, CNN etc.) used in literature for SOC prediction. The current review paper emphasizes on the latest RS approaches used for SOC monitoring.