High spatial resolution snow depth (SD) is crucial for hydrological, ecological, and disaster research. However, passive microwave SD product (10/25 km) is increasingly insufficient to meet contemporary requirements due to its coarse spatial resolution, particularly in heterogeneous alpine areas. In this study, we develop a superior SD downscaling algorithm based on the FT-Transformer (Feature Tokenizer + Transformer) model, termed FTSD. This algorithm fuses the latest calibrated enhanced resolution brightness temperature (CETB) (3.125/6.25 km) with daily cloud-free optical snow data (500 m), including snow cover fraction (SCF) and snow cover days (SCD). Developed and evaluated using 42,692 ground measurements across China from 2000 to 2020, FTSD demonstrated notable improvements in accuracy and spatial resolution of SD retrieval. Specifically, the RMSE of temporal and spatiotemporal independent validation for FTSD is 7.64 cm and 9.74 cm, respectively, indicating reliable generalizability and stability. Compared with the long-term series of SD in China (25 km, RMSE = 10.77 cm), FTSD (500 m, RMSE = 7.67 cm) provides superior accuracy, especially improved by 48% for deep snow (> 40 cm). Moreover, with the higher spatial resolution, FTSD effectively captures the SD’s spatial heterogeneity in the mountainous regions of China. When compared with downscaling algorithms utilizing the raw TB data and the traditional random forest model, the CETB data and FT-Transformer model optimize the RMSE by 10.08% and 4.84%, respectively, which demonstrates the superiority of FTSD regarding data sources and regression methods. Collectively, these results demonstrate that the innovative FTSD algorithm exhibits reliable performance for SD downscaling and has the potential to provide a robust data foundation for meteorological and environmental research.

Under the ongoing trend of climate warming and increasing humidity on the Qinghai–Tibet Plateau, the Three River Source Region (TRSR) has shown strong sensitivity to global climate change. Its vegetation change is particularly worthy of attention and research. The Normalized Difference Vegetation Index (NDVI) is a key indicator for assessing the growth status of vegetation. However, the insufficiency of existing NDVI datasets in terms of spatiotemporal continuity has limited the accuracy of long-term vegetation change studies. This study proposed a machine learning-based downscaling framework that integrates the Moderate-resolution Imaging Spectroradiometer (MODIS) NDVI and the Global Inventory Monitoring and Modeling System (GIMMS) NDVI data to reconstruct a long-term, high-resolution NDVI dataset. Unlike conventional statistical fusion approaches, the proposed framework employs machine learning-based nonlinear relationships to generate long-term, high-resolution NDVI data. Three machine learning algorithms—Random Forest (RF), LightGBM, and CatBoost—were evaluated. Their performance was validated using the MODIS NDVI as reference, with the coefficient of determination (R²), root mean square error (RMSE), mean absolute error (MAE), and Pearson’s correlation coefficient (R) as evaluation metrics. Based on model comparison, the CatBoost model was identified as the optimal algorithm for spatiotemporal data fusion (R² = 0.9014, RMSE = 0.0674, MAE = 0.0445), significantly outperforming RF and LightGBM models and demonstrating stronger capability for NDVI spatiotemporal reconstruction. Using this model, a long-term, 1 km monthly GIMMS-MODIS NDVI dataset from 1982 to 2014 was successfully reconstructed. On the basis of this dataset, the spatiotemporal variation characteristics of vegetation in the TRSR from 1982 to 2014 were systematically analyzed. The research results show that: (1) The constructed long-series high-resolution NDVI dataset has a high consistency with MODIS NDVI data; (2) From 1982 to 2014, the NDVI in the TRSR showed an increasing trend, with an average growth rate of 0.0020/10a (p < 0.05). NDVI showed obvious spatial heterogeneity, characterized by a decreasing gradient from southeast to northwest. (3) The Yellow River source exhibited the most evident vegetation recovery, the Yangtze River Source area showed a moderate improvement, whereas the Lancang River Source area displayed little noticeable change. (4) Broad-leaved forests experienced the most significant growth, while cultivated vegetation displayed a marked tendency toward degradation. This study provides both a high-accuracy long-term NDVI product for the TRSR and a methodological foundation for advancing vegetation dynamics research in other high-altitude regions.

High-resolution optical remote sensing imagery plays a crucial role in monitoring the Earth’s surface. However, cloud obstruction and spectral confusion between clouds and snow significantly compromise data quality and application reliability, leading to persistent cloud overestimation in optical remote sensing products. To address this challenge, this study developed an enhanced multi-threshold cloud detection algorithm based on AVHRR surface reflectance data, which incorporates dynamic threshold optimization within a multi-level decision tree framework. Utilizing Landsat 5 SR as reference data, the algorithm demonstrated superior cloud-snow discrimination capability, achieving an overall accuracy (OA) of 82.08%, with the user’s accuracy (UA) and F-score reaching 79.41% and 82.55%. Comparative evaluation demonstrates that the proposed algorithm outperforms two existing algorithms, with OA improvements of 17.42% and 7.93%, respectively. A particularly notable enhancement is the significant reduction in cloud misidentification, as reflected by UA increases of 21.02% and 13.21%. These improvements are most pronounced in high-altitude mountainous regions with snow cover. The algorithm maintains computational efficiency while providing reliable cloud masking, thereby offering enhanced support for snow cover monitoring and broader environmental applications.