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.

As major components of terrestrial ecosystems, forest ecosystems play an important role in sequestering carbon and hence mitigating climate change. Canopy height is a crucial factor characterizing the structure and function of forest ecosystems, yet the driving mechanism of forest canopy height receives less attentions in China. Here, we utilize the satellite-based forest canopy height product with several environmental and climate factors (e.g. forest age, temperature, etc.) to delineate the spatial distributions of forest canopy height and its drivers in China at 1 km spatial resolution during the period of 2014 to 2018. The random forest is employed for identifying the dominant factors at province level, while Shapley additive explanations (SHAP) analysis is further incorporated at pixel-level to dig into the specific contributions of each driver. The results show that forest age primarily dominates the spatial distributions of forest canopy height across different forest ecosystems of China, followed by mean annual precipitation, soil type, and aspect. SHAP analysis further indicates that other factors, such as soil moisture and wind speed, also play critical roles to shape the spatial patterns of forest canopy height in China, which could not be revealed from province-level random forest analyses. Such results emphasize the priority of incorporating SHAP analysis with random forest to advance our understanding of forest canopy height distributions and benefit future projections. Our study highlights the necessity to characterize the spatial heterogeneity of forest canopy height, which is critical for accurate estimations of forest and even terrestrial carbon sink in China, facilitating the achievement of the goal of “carbon peak in 2030 and carbon neutrality in 2060”.

National parks face ecological threats from climate change and human activities. Sanjiangyuan National Park (SNP), a major ecological area in China, lacks a systematic evaluation of its ecological environmental quality changes and their driving factors. This study explores these dynamics to provide a scientific basis for regional ecological management. By constructing the remote sensing ecological index (RSEI) and using the optimal multivariate-stratification geographical detector (OMGD) model, we assessed ecological changes from 2014 to 2024. The results showed the RSEI remained stable at approximately 0.66, peaking at 0.732 in 2022, indicating a general improvement in ecological quality. The vegetation coverage rate (NDVI) increased from 0.591 to 0.680. Driving factor analysis revealed considerable regional variation, with temperature and human activities as the primary drivers. Higher RSEI values were associated with conditions where precipitation was moderate (~100 mm), evapotranspiration levels were high (>50 mm), temperatures were above average (>4 °C), and nighttime light indices were low (<0.6). These findings suggest that specific combinations of these factor thresholds may enhance ecological quality, informing protection strategies for SNP and providing a reference for similar plateau ecosystems.

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.