Glacial lake dynamics in high-mountain regions serve as a sensitive proxy for cryospheric responses to climate warming. This study utilizes multi-temporal Sentinel-2 imagery and digital elevation model (DEM) data to quantify glacial lake evolution in the Donglin Tsangpo Watershed, a strategically important section of the China–Nepal Economic Corridor, from 2016 to 2024. The results show a significant expansion in both the number (from 43 to 56) and total area (from 3.97 km² to 4.94 km², +24.43%) of glacial lakes, primarily driven by the rapid emergence of very small lakes (0.02–0.05 km²) and a clear upward shift in elevation distribution, with new lakes forming above 5300 m and extending to elevations exceeding 5500 m. Analysis of Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature (LST) reveals that this expansion coincided with pronounced positive thermal anomalies, particularly the 2020 extreme warm event (daytime +3.88 °C, nighttime +1.61 °C). Mechanistic analysis using the ERA5-Land reanalysis dataset further demonstrates that persistent positive downward longwave radiation (LW) anomalies (peaking at +10.71 W/m² in 2021) effectively compensated for reduced shortwave input, inhibiting nocturnal refreezing and extending the effective ablation period. Furthermore, a rising liquid-to-solid precipitation ratio and extreme melt-day anomalies (up to +39.36 days) provided intensified hydrothermal inputs, driving the pronounced expansion of glacier-contact lakes despite non-linear interannual responses. This study also estimates individual lake volumes, identifying a transition toward rapid lake development that elevates potential downstream hazard exposure. These findings provide a high-resolution dataset and a robust physical framework for transboundary environmental monitoring and risk assessment in this climate-sensitive region.

Atmospheric aerosols play an important role in the ecological environment, climate change, and human health. Aerosol optical depth (AOD) is the main measurement of aerosols. The next-generation geostationary satellite Himawari-8, loaded with the Advanced Himawari Imager (AHI), provides observation-based estimates of the hourly AOD. However, a highly accurate evaluation of AOD using AHI is still limited. In this paper, we establish a Stacked Denoising AutoEncoder (SDAE) model to retrieve highly accurate AOD using AHI. We explore the SDAE to retrieve AOD by taking the ground-observed AOD as the output and taking the AHI image, the month, hour, latitude, and longitude as the input data. This approach was tested in the Hubei province of China. Traditional machine learning methods such as Extreme Learning Machines (ELMs), BackPropagation Neural Networks (BPNNs), and Support Vector Machines (SVMs) are also used to evaluate model performance. The results show that the proposed method has the highest accuracy. We also compare the proposed method with ground-observed AOD measurements at the Wuhan University site, showing good consistency between the satellite-retrieved AOD and the ground-observed value. The study of the spatiotemporal change pattern of the hourly AOD in the Hubei province shows that the algorithm has good stability in the face of changes in the angle and intensity of sunlight.