Assessment of Machine Learning Models for Predicting Aboveground Biomass in the Indian Subcontinent

Abstract. Understanding the distribution of aboveground biomass (AGB) is vital for evaluating carbon stocks & ecosystem dynamics, especially in regions with diverse landscapes like Indian subcontinent. This study evaluates three machine learning models—Random Forest (RF), Gradient Tree Boosting (GTB), & Classification and Regression Trees (CART)—for predicting AGB across the subcontinent. Independent variable in these models is AGB, while dependent variables include a range of vegetation & topographic layers: Normalized Difference Vegetation Index, Enhanced Vegetation Index, Leaf Area Index, Fraction of Photosynthetically Active Radiation, land cover, elevation, aspect, slope, & hillshade. These predictors are essential for capturing ecological & topographical characteristics that influence biomass distribution. The models were evaluated using coefficient of determination (R2) & Pearson's correlation coefficient (r) to assess…