The Qinghai–Tibet Plateau is one of the regions with the highest snow accumulation in China. Although the Fengyun-4A (FY4A) satellite is capable of monitoring snow-covered areas in real time and on a wide scale at high temporal resolution, its spatial resolution is low. In this study, the Qinghai–Tibet Plateau, which has a harsh climate with few meteorological stations, was selected as the study area. We propose a deep learning model called the Dual-Branch Super-Resolution Semantic Segmentation Network (DSRSS-Net), in which one branch focuses with super resolution to obtain high-resolution snow distributions and the other branch carries out semantic segmentation to achieve accurate snow recognition. An edge enhancement module and coordinated attention mechanism were introduced into the network to improve the classification performance and edge segmentation effect for cloud versus snow. Multi-task loss is also used for optimization, including feature affinity loss and edge loss, to obtain fine structural information and improve edge segmentation. The 1 km resolution image obtained by coupling bands 1, 2, and 3; the 2 km resolution image obtained by coupling bands 4, 5, and 6; and the 500 m resolution image for a single channel, band 2, were inputted into the model for training. The accuracy of this model was verified using ground-based meteorological station data. Snow classification accuracy, false detection rate, and total classification accuracy were compared with the MOD10A1 snow product. The results show that, compared with MOD10A1, the snow classification accuracy and the average total accuracy of DSRSS-Net improved by 4.45% and 5.1%, respectively. The proposed method effectively reduces the misidentification of clouds and snow, has higher classification accuracy, and effectively improves the spatial resolution of FY-4A satellite snow cover products.

Snow on the Tibetan Plateau (TP) is not only a freshwater resource for the major rivers in Asia but also plays a significant role in adjusting temperature by reflecting solar radiation. Fractional snow cover mapping with fine spatial and temporal resolution is of great significance for clarifying snow resources and accurately managing snow water resources. However, due to the complex TP topography, the existing FSC retrieval methods are affected by a variety of disturbance factors, resulting in a decrease in accuracy. In this study, a deep learning-based FSC retrieval method, fractional snow cover U-shape net (FSC-USNet), is proposed to improve snow cover mapping accuracy. The input images of FengYun-4A Advanced Geosynchronous Radiation Imager (FY4A/AGRI) and geographic data are extracted using the proposed spatial-channel feature extraction module to characterize the shallow features with texture information into high-dimensional feature images. Additionally, an attention mechanism is introduced to improve the feature differences between different FSC degrees. Finally, the correlation of the decoded features in the channel direction is mined using the channel refinement module to obtain the final FSC results. In this study, a backpropagation artificial neural network (BPANN), random forest, ResNet_FSC, and UNet are trained, compared and validated against the MOA10A1 FSC product. The results show that the proposed method effectively mitigates the problems of unclear texture of snow edges, poor robustness and underestimation in some areas, which exist in other models. Additionally, the proposed method has higher accuracy, with an R2 and explained variance score (EVS) reaching 0.7182 and 0.7332, respectively. Compared to the MOD10A1 snow product, the proposed method exhibits higher detection accuracy in mountainous areas with high snow cover and significantly improves the low snow cover detection rate.

The urbanization process over the past decades has resulted in increasing attention being paid to atmospheric pollution by researchers, especially changes in PM_2.5 concentration. This study attempted to explore the spatiotemporal changes in PM_2.5 concentration in China from 2000 to 2021, as well as their interaction patterns and intensities with temperature, precipitation, vegetation coverage, and land use types. This was carried out by analyzing monthly average PM_2.5 concentration data and various meteorological and geographical factors. Suggestions have also been made to reduce PM_2.5 concentration and improve air quality. The results show that in the past 22 years, the overall concentration of PM_2.5 in China has shown a downward trend, with an average annual rate of 1.42 μg/m³ from 2013 to 2021, accompanied by a clear spatial pattern and significant seasonal changes. The high pollution areas are mainly concentrated in the Tarim Basin, Sichuan Basin, North China Plain, and the Middle and Lower Yangtze Valley Plain, where the PM_2.5 concentration in autumn and winter is significantly higher than that in spring and summer. In addition, based on the national spatial scale, PM_2.5 concentration is negatively correlated with precipitation and vegetation coverage, while it is significantly positively correlated with arable land and impervious surfaces. Strengthening the control of farmland pollution, accelerating urban greening construction, further expanding the scale of forests and grasslands, and enriching vegetation types will help reduce PM_2.5 concentration and improve air quality.

Conventional passive microwave (PMW) snow depth (SD) retrieval faces dual limitations over the Qinghai-Tibetan Plateau (QTP): coarse spatial resolution (typically >25 km) obscures topographic heterogeneity, while station-based labels introduce representativity errors by treating sparse points as pixel-scale “truth.” To overcome these challenges, we propose SRSDNet (Super-Resolution Snow Depth Network)—a deep learning framework integrating FengYun-3 PMW data with auxiliary variables (topography, fractional snow cover). Crucially, SRSDNet pioneers the use of 500-m resolution Sentinel-1 SD products as area-constrained labels, eliminating point-to-pixel mismatches. Its architecture incorporates three novel modules, the bidirectional feature extract block (BFEB) extracts anisotropic features via bidirectional convolutions to resolve mountain snow textures; the optimized coordination attention (OCA) dynamically weighted multi-source channels, especially low-frequency microwaves in deep snow; and the reconstructive output block (ROB) reconstructs 6.25-km outputs with local detail and global consistency. The results of this study were systematically validated at 95 meteorological stations in QTP during the 2017-2018 snow season, SRSDNet achieves best-in-class accuracy (RMSE = 12.075 cm, MAE = 7.724 cm, R2 = 0.781). Notably, it sets a new benchmark for deep snow retrieval with an RMSE of 9.939 cm for SD >50 cm and a relative error of less than 20%. This work establishes a paradigm for high-resolution SD mapping in complex terrain, directly supporting hydrological forecasting and avalanche risk management on the QTP.

The maximum spatial resolution varies significantly across different bands in the reflectance data of FengYun-4A(FY-4A) remote sensing images. Super-resolution reconstruction of FY-4A remote sensing imagery not only enhances the spatial accuracy of low-resolution bands and achieves cross-band scale consistency, but also improves feature recognition and monitoring capabilities. This provides clearer and more reliable data support for quantitative remote sensing and applications in meteorology, ecology, agriculture, and other fields. Therefore, a Differential Enhancement Super-Resolution Network (DESR) is proposed based on scale invariance. The dual paths consist of a CNN branch and a Swin Transformer branch. The CNN branch employs Rep-Residual Blocks (RRB) to capture spatial structures, where each RRB integrates a Spatial Feature Attention (SFA) that employs large convolutional kernels with directional strides along the height and width to model long-range dependencies and spatial correlations. The Swin Transformer branch adopts Residual Swin Transformer Blocks (RSTB) to obtain a global receptive field. In addition, A Differential Feature Enhancement Module (DFEM) is further introduced to fuse features, highlight branch-specific deficiencies through subtraction, and achieve complementary enhancement. Experimental results show that DESR achieves more uniform error distribution and superior reconstruction quality compared with representative methods. On 2× and 4× super-resolution tasks, DESR reaches PSNR values of 54.1395 and 46.0942, SSIM values of 0.9899 and 0.9749, with improvements at least 1.87% and 0.59%, respectively, while also attaining the best spectral angle mapping.

The Qinghai–Tibet Plateau (QTP), one of China’s most snow-rich regions, has an extremely fragile ecosystem, with drought being the primary driver of ecological degradation. Given that the water resources in this region predominantly exist in the form of snow, high-spatiotemporal-resolution snow mapping is essential for understanding snow distribution and managing snow water resources effectively. However, although FY-4A/AGRI is capable of obtaining wide-area remote sensing data, only the first to third bands have a resolution of 1 km, which greatly limits its ability to produce high-resolution snow maps. This study proposes U-SwinFusionNet (USFNet), a deep learning-based snow cover retrieval algorithm that leverages the multi-scale advantages of FY-4A/AGRI remote sensing data in the shortwave infrared and visible bands. By integrating 1 km and 2 km resolution remote sensing imagery with auxiliary terrain information, USFNet effectively enhances snow cover mapping accuracy. The proposed model innovatively combines Swin Transformer and convolutional neural networks (CNNs) to capture both global contextual information and local spatial details. Additionally, an Attention Feature Fusion Module (AFFM) is introduced to align and integrate features from different modalities through an efficient attention mechanism, while the Feature Complementation Module (FCM) facilitates interactions between the encoded and decoded features. As a result, USFNet produces snow cover maps with a spatial resolution of 1 km. Experimental comparisons with Artificial Neural Networks (ANNs), Random Forest (RF), U-Net, and ResNet-FSC demonstrate that USFNet exhibits superior robustness, enhanced snow cover continuity, and lower error rates. The model achieves a correlation coefficient of 0.9126 and an R² of 0.7072. Compared to the MOD10A1 snow product, USFNet demonstrates an improved sensitivity to fragmented and low-snow-cover areas while ensuring more natural snow boundary transitions.