Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass Estimation

Above-ground biomass (AGB) is a core indicator for evaluating grassland ecosystem health and carbon storage. Traditional ground-based AGB measurements are labor-intensive and ill suited for large-scale monitoring. This study addresses this gap by developing a Multilayer Perceptron (MLP) model integrating Landsat 9 OLI/TIRS imagery acquired on 15 August 2024, with ground data from 78 sampling points (62 training, 16 testing). Incorporating fourteen multi-source features (seven vegetation indices, e.g., Modified Vegetation Index (MVI) and Green Chlorophyll Index (CIg); four meteorological variables; three soil properties), all data were standardized via z-score normalization before training. The MLP model, optimized via six-fold cross-validation, achieved an R2 of 0.765 and RMSE of 38.066 g/m2, outperforming XGBoost (R2 = 0.723, RMSE = 41.354 g/m2) with a statistically significant 5.8% accuracy improvement (p < 0.05). Spatial analysis revealed a north-to-south AGB gradient, strongly correlated with precipitation gradients (250–350 mm/year) and soil organic carbon (R = 0.428). These findings provide a robust framework for climate-adaptive grassland management and carbon assessment in semi-arid regions.