This study employs multi-source remote sensing information and machine learning methods to comprehensively assess the geological background, structural features, alteration anomalies, and spectral characteristics of the Malkansu Manganese Ore Belt in Xinjiang. Manganese mineralization is predicted, and areas with high mineralization potential are delineated. The results of the feature factor weight analysis indicate that structural density and lithological characteristics contribute most significantly to manganese mineralization. Notably, linear structures are aligned with the direction of the manganese belt, and areas exhibiting high controlling structural density are closely associated with the locations of mineral deposits, suggesting that structure plays a crucial role in manganese production in this region. The Area Under the Curve (AUC) values for the Random Forest (RF), Naïve Bayes (NB), and eXtreme Gradient Boosting (XGBoost) models were 0.975, 0.983, and 0.916, respectively, indicating that all three models achieved a high level of performance and interpretability. Among these, the NB model demonstrated the highest performance. By algebraically overlaying the predictions from these three machine learning models, a comprehensive mineralization favorability map was generated, identifying 11 prospective mineralization zones. The performance metrics of the machine learning models validate their robustness, while regional tectonics and stratigraphic lithology provide valuable characteristic factors for this approach. This study integrates multi-source remote sensing information with machine learning methods to enhance the effectiveness of manganese prediction, thereby offering new research perspectives for manganese forecasting in the Malkansu Manganese Ore Belt.

Under climate change and human activities, ecosystem service (ES) research lacks systematic approaches and scientific depth. This study develops a comprehensive framework integrating advanced models to predict ESs, analyze interactions, identify key drivers, and assess spatial effects on the Zoigê Plateau. The results indicate the following: (1) From 2000 to 2020 and across three 2040 scenarios, water conservation (WC) improves, while carbon storage (CS) and habitat quality (HQ) decline, leading to overall ES degradation. Core ES areas face rising degradation risks from 9% to 29% under increasing environmental stress (SSP119 to SSP585). (2) ES importance follows HQ > CS > SC > WC, with bivariate interactions outperforming single-factor effects. Future scenarios show weakened interactions, correlating with higher ecological stress, indicating ES stability risks. (3) Land use (>40% explanatory power) is the primary driver, while urban expansion, slope, evapotranspiration, and precipitation contribute (6–12%). (4) ES drivers showed weak spatial patterns from 2000 to 2020 but became more stable under future scenarios, suggesting stronger environmental control. This study provides a methodological paradigm for ES analysis and supports ecological planning in alpine wetland–grassland regions.