Flood events are among the most destructive natural catastrophes worldwide and pose serious threats to socioeconomic systems, ecological environments, and the safety of human life and property. With the advancement of remote sensing technology, synthetic aperture radar (SAR) has provided new means for flood monitoring. However, traditional methods have limitations when dealing with high noise levels and complex terrain backgrounds. To address this issue, in this study, we adopt an improved U-Net model incorporating the Kolmogorov–Arnold Network (KAN), referred to as UKAN, for the efficient extraction of flood inundation extents from multisource remote sensing data. UKAN integrates the efficient nonlinear mapping capabilities of KAN layers with the multiscale feature fusion mechanism of U-Net, enabling better capturing of complex nonlinear relationships and global features. Experiments were conducted on the C2S-MS Floods and MMFlood datasets, and the results indicate that the UKAN model outperforms traditional models in terms of metrics such as the intersection over union (IoU), precision, recall, and F1 score. On the C2S-MS Floods dataset and the MMFlood dataset, UKAN achieves IoUs of 87.95% and 78.31%, respectively, representing improvements of approximately 3.5 and three percentage points, respectively, over those of the traditional U-Net. Moreover, the model has significant advantages in terms of parameter efficiency and computational efficiency. These findings suggest that the UKAN model possesses greater accuracy and robustness in flood inundation area extraction tasks, which is highly important for increasing the monitoring and early warning capabilities of flood disasters.
This study systematically analyzes land use changes in the Russian Far East from 2000 to 2020, identifying key transformations and their driving factors. Using multi-temporal remote sensing images combined with land use dynamics analysis, transition matrices, and gray relational analysis, this research comprehensively evaluates land use evolution and its influencing factors. The purpose of this study is to elucidate how land use patterns shift under the influence of natural conditions, demographic trends, and cross-border cooperation with a particular emphasis on the border areas adjacent to northeast China. The findings reveal that during the observed period, the Far East underwent substantial expanses in arable land and built-up areas, while forest areas underwent a decline. Grassland areas demonstrated relative stability, water bodies continued to decrease, and unused land exhibited fluctuating trends, initially increasing and then decreasing. In the three border regions (Amur Oblast, the Jewish Autonomous Region, and Primorsky Krai), these transformations were more pronounced compared to the Far East overall, reflecting intensified agricultural development and urban growth in these strategic zones. Gray relational analysis shows that climate change and local population growth are the principal drivers of land use change, while regional trade—particularly China–Russia trade in industrial raw materials, agriculture, and food exports—plays a moderate role. The evolving land use patterns in the Far East carry significant implications for resource acquisition, ecological security, and regional cooperation. The study underscores the necessity of formulating scientifically sound land management policies to balance economic development with ecological protection, thus fostering sustainable development and regional stability.