Identifying suitable areas for ecosystem services (ES) development is essential for balancing economic growth with environmental sustainability in ecologically fragile regions. However, existing studies often neglect integrating future climate and socioeconomic drivers into ES optimization, hindering the design of robust strategies for sustainable resource management. In this study, we propose a novel framework integrating the System Dynamics (SD) model, the Patch-based Land Use Simulation (PLUS) model, the Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model, and the Dynamic Bayesian Network (DBN) to optimize ES patterns in the Sanjiangyuan region under three climate scenarios (SSP126, SSP245, and SSP585) from 2030 to 2060. Our results show the following: (1) Ecological land (forest) expanded by 0.86% under SSP126, but declined by 11.54% under SSP585 due to unsustainable land use intensification. (2) SSP126 emerged as the optimal scenario for ES sustainability, increasing carbon storage and sequestration, habitat quality, and water conservation by 3.2%, 1%, and 1.4%, respectively, compared to SSP585. (3) The central part of the Sanjiangyuan region, characterized by gentle topography and adequate rainfall, was identified as a priority zone for ES development. This study provides a transferable framework for aligning ecological conservation with low-carbon transitions in global biodiversity hotspots.

Accurate tree species classification using high-resolution unmanned aerial vehicle (UAV) images is crucial for forest carbon cycle research, biodiversity conservation, and sustainable management. However, challenges persist due to high interspecies feature similarity, complex canopy boundaries, and computational demands. To address these, we propose an enhanced DeepLabV3+ model integrating Object-Based Image Analysis (OBIA) and a lightweight attention mechanism. First, an OBIA-based multiscale segmentation algorithm optimizes object boundaries. Key discriminative features, including spectral, positional, and vegetation indices, are then identified using Recursive Feature Elimination with Cross-Validation (RFECV). High-precision training labels are efficiently constructed by combining Random Forest classification with visual interpretation (RFVI). The DeepLabV3+ model is augmented with a lightweight attention module to focus on critical regions while significantly reducing model parameters. Evaluations demonstrate that the improved DeepLabV3+ model achieved overall accuracy (OA) of 94.91% and Kappa coefficient (Kappa) of 92.89%, representing improvements of 2.91% and 4.11% over the original DeepLabV3+ model, while reducing parameters to 5.91 M (78.35% reduction). It significantly outperformed U-Net, PSPNet, and the original DeepLabV3+. This study provides a high-accuracy yet lightweight solution for automated tree species mapping, offering vital technical support for forest carbon sink monitoring and ecological management.

Fractional Vegetation Cover (FVC) dynamics on the Qinghai–Tibetan Plateau (QTP) are critical indicators for assessing ecosystem condition. However, uncertainties persist in the accuracy of existing FVC products over the QTP due to retrieval differences, scale effects, and limited validation data. This study utilized the Google Earth Engine platform to integrate unmanned aerial vehicle (UAV) observations, Sentinel-2, MODIS, climate, and topography datasets, and proposed a comprehensive framework incorporating dual-index screening, machine learning optimization, and multidimensional validation to systematically assess the accuracy of GEOV3, GLASS, and MuSyQ FVC products in the alpine grasslands. The dual-index screening reduced validation uncertainty by improving the spatial representativeness of ground data. To build a high-precision evaluation dataset with limited inter-class coverage, recursive feature elimination and grid search were applied to optimize five ML models, and CatBoost achieved the superior performance (R² = 0.880, RMSE = 0.122), followed by XGBoost, GBM, LightGBM, and RF models. Four validation scenarios were implemented, including direct validation using 250 m UAV plot FVC and multi-scale validation using a 10 m FVC reference aggregated to product grids. Results show that GEOV3 (R² = 0.909–0.925, RMSE = 0.082–0.103) outperformed GLASS (R² = 0.742–0.771, RMSE = 0.138–0.175) and MuSyQ (R² = 0.739–0.746, RMSE = 0.138–0.181), both of which exhibited systematic underestimation. This framework significantly enhances FVC product validation reliability, providing a robust solution for remote sensing product validation in alpine grassland ecosystems.