The main aim of this study was to utilize remote sensing data to establish regression models through machine learning to predict locust density in the upcoming year. First, a dataset for monitoring grassland locust density was constructed based on meteorological data and multi-source remote sensing data in the study area. Subsequently, an SVR (support vector regression) model, BP neural network regression model, random forest regression model, BP neural network regression model with the PCA (principal component analysis), and deep belief network regression model were built on the dataset. The experimental results show that the random forest regression model had the best prediction performance among the five models. Specifically, the model achieved a coefficient of determination (R²) of 0.9685 and a root mean square error (RMSE) of 1.0144 on the test set, which were the optimal values achieved among all the models tested. Finally, the locust density in the study area for 2023 was predicted and, by comparing the predicted results with actual measured data, it was found that the prediction accuracy was high. This is of great significance for local grassland ecological management, disaster warning, scientific decision-making support, scientific research progress, and sustainable agricultural development.

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.