Predictive mapping of deep soil organic carbon stocks across land use systems in Southern assam, India.

ABSTRACT: Deep soil organic carbon (SOC) is a critical component of the global carbon cycle; consequently, researchers have shown increasing interest in digital soil mapping (DSM) in recent years. Globally, several studies have used geospatial technology and machine-learning models to predict the spatial distribution of SOC stock. However, similar work is lacking in India and most of the previous studies are focused mainly up to 100 cm of soil depth and data on deep SOC stock is lacking. Therefore, the present study aims to evaluate different machine-learning algorithms for predicting deep SOC stock (up to 5 m of soil depth) of different land use systems, to identify the variable importance in predicting deep SOC stock, and to compute the pedologic deep SOC stock for diverse land uses in southern As

SUBMITTER: Bania JK 

PROVIDER: S-EPMC12489057 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature