Advancing Concession-Scale Carbon Stock Prediction in Oil Palm Using Machine Learning and Multi-Sensor Satellite Indices

Reliable estimation of oil palm carbon stock is essential for climate mitigation, concession management, and sustainability certification. While satellite-based approaches offer scalable solutions, redundancy among spectral indices and inter-sensor variability complicate model development. This study evaluates machine learning regressors for predicting oil palm carbon stock at tree (CO_tree, kg C tree−1) and hectare (CO_ha, Mg C ha−1) scales using spectral indices derived from Landsat-8, Landsat-9, and Sentinel-2. Fourteen vegetation indices were screened for multicollinearity, resulting in a lean feature set dominated by NDMI, EVI, MSI, NDWI, and sensor-specific indices such as NBR2 and ARVI. Ten regression algorithms were benchmarked through cross-validation. Ensemble models, particularly Random Forest, Gradient Boosting, and XGBoost, outperformed linear and kernel methods, achieving R2 values of 0.86–0.88 and RMSE of 59–64 kg tree−1 or 8–9 Mg ha−1. Feature importance analysis consistently identified NDMI as the strongest predictor of standing carbon. Spatial predictions showed stable carbon patterns across sensors, with CO_tree ranging from 200–500 kg C tree−1 and CO_ha from 20–70 Mg C ha−1, consistent with published values for mature plantations. The study demonstrates that ensemble learning with sensor-specific index sets provides accurate, dual-scale carbon monitoring for oil palm. Limitations include geographic scope, dependence on allometric equations, and omission of belowground carbon. Future work should integrate age dynamics, multi-year composites, and deep learning approaches for operational carbon accounting.