Traditional remote sensing spatio-temporal data fusion algorithms generally use up-sampled low-resolution images (MODIS) to be fused with high-resolution images (Landsat), this makes both images less spatially consistent and many hybrid image elements in low-resolution images, so uncertainty errors propagate into the fusion results. To address this issue, we propose a framework for combining deep learning-based super-resolution techniques with traditional spatio-temporal fusion methods. By reconstructing low-resolution images using super-resolution image reconstruction techniques, we obtain low-resolution images with more spatial details and better spatial consistency with high-resolution images. These reconstructed images are then fused using spatio-temporal fusion methods. In this study, we selected Flexible Spatio-Temporal Data Fusion (FSDAF) and Residual Channel Attention Network (RCAN) to carry out a detailed study to prove the effectiveness of this kind of framework. That is, a new RCAN-FSDAF model is developed. After testing, RCAN-FSDAF has the following advantages::(1) The band reflectance predicted by RCAN-FSDAF is closer to base reflectance than FSDAF, DMNet, and GAN-STFM, as shown by greater correlation and smaller error. (2) RCAN-FSDAF better decomposes image elements among heterogeneous features and more accurately identifies boundaries between different features and changes in land cover type. (3) High spatial and temporal resolution NDVI data obtained by the inversion of the prediction results of RCAN-FSDAF are more accurate. The framework developed in this study can be extended to other spatial and temporal data fusion applications.

Global warming has led to an increase in interest in river hydrology. Water surface slope is a basic parameter of river morphology and is critical in understanding riverine ecosystems. The Yarlung Zangbo River is an important international river. Scientific understanding of its hydrology has been severely limited by its harsh topography and the sparse distribution of measurement stations. This paper describes the first attempt to use ICESat-2 satellite altimetry data to calculate river water slope and introduces a new technique for studying river hydrology. Water level data for different stretches of the Yarlung Zangbo River were obtained from high spatial resolution ICESat-2 altimetry data. The data were analyzed to determine the water surface slope of the Yarlung Zangbo River, and variation in the water surface slope was examined for several river sections. The water surface slope of the Yarlung Zangbo River was greatest in summer and autumn and least in winter and spring. There may be seasonal cyclic changes in the water surface slope. The range for water surface slope was large and the difference in extremes is significant; the maximum average water surface slope was 1935.17 cm/km and the minimum water surface slope was 0.08 cm/km. The water surface slope of the Yarlung Zangbo River can be characterized as small in the upper and middle reaches and large in the lower reaches; it is related to dry and wet conditions determined by topography and climate. The upper and middle reaches of the Yarlung Zangbo River are semi-arid and the lower reaches of the Yarlung Zangbo River span three climate zones: semi-arid, semi-humid and humid. In addition, the water level information measured by ICESat-2 data is basically similar to the water level information measured by Hydroweb data, except that the water level information of individual virtual stations is quite different due to special reasons. It was found that ICESat-2 data had higher-accuracy water level data results and more river location information. Therefore, ICESat-2 satellite altimetry data can provide a baseline reference for the study of the Yarlung Zangbo River hydrology, and the technique used is applicable to other rivers.