China’s vulnerability to fluvial floods necessitates extensive exposure studies. Previous large-scale regional analyses often relied on a limited set of assessment indicators due to challenges in data acquisition, compounded by the scarcity of corresponding large-scale flood distribution data. The integration of public datasets offers a potential solution to these challenges. In this study, we obtained four key exposure indicators—population, built-up area (BA), road length (RL), and average gross domestic product (GDP)—and conducted an innovative analysis of their correlations both overall and locally. Utilising these indicators, we developed a comprehensive exposure index employing entropy-weighting and k-means clustering methods and assessed fluvial flood exposure across multiple return periods using fluvial flood maps. The datasets used for these indicators, as well as the flood maps, are primarily derived from remote sensing products. Our findings indicate a weak correlation between the various indicators at both global and local scales, underscoring the limitations of using singular indicators for a thorough exposure assessment. Notably, we observed a significant concentration of exposure and river flooding east of the Hu Line, particularly within the eastern coastal region. As flood return periods extended from 10 to 500 years, the extent of areas with flood depths exceeding 1 m expanded markedly, encompassing 2.24% of China’s territory. This expansion heightened flood risks across 15 administrative regions with varying exposure levels, particularly in Jiangsu (JS) and Shanghai (SH). This research provides a robust framework for understanding flood risk dynamics, advocating for resource allocation towards prevention and control in high-exposure, high-flood areas. Our findings establish a solid scientific foundation for effectively mitigating river flood risks in China and promoting sustainable development.
The North China Plain (NCP) serves as a core grain production base and one of the most water-scarce regions in China. Under global warming and intensified human activities (irrigation, groundwater exploitation, and returning farmland to forests and grasslands), soil drought has become a critical constraint on regional agricultural sustainability. This study systematically explored temporal trends, spatial disparities, and abrupt changes of soil drought using remote sensing-based soil moisture dataset. Adopting gridded Modified Mann–Kendall test, wavelet coherence analysis and SHapley Additive exPlanations (SHAP), this paper quantitatively revealed multi-scale driving mechanisms and teleconnection responses of soil drought. Drought in 2002 followed a unimodal pattern with continuous expansion from May to October. The drought-affected area peaked at 77.6% in September. Regional soil moisture increased significantly during 1982–2024, accompanied by sustained drought alleviation. Breaks for Additive Seasons and Trend (BFAST) detection verified a regional abrupt change in 2003. Drought deteriorated before 2003 and obviously relieved afterwards. Wavelet analysis indicated that precipitation dominated drought evolution. This study clarifies the evolutionary trend of drought transition from intensification to alleviation across the NCP, providing scientific evidence for the optimal allocation of water resources, regulation of farmland irrigation, and development of agricultural drought resistance.
Remote sensing imagery provides a primary data source for large-scale surface water body monitoring, which is crucial for quantifying climate-related hydrological impacts, supporting flood control, and sustaining integrated water resource management. However, remote sensing images generally face the trade-off between spatial resolution and temporal coverage. To address this issue, the Real-ESRGAN super-resolution algorithm is employed to reconstruct temporally continuous, wide-coverage medium-resolution imagery to a 2.5 m resolution, effectively improving its capability to identify sub-pixel river boundaries. Water body segmentation (WBS) is an effective method for fine-detail surface water extraction. Nonetheless, when applied in complex hydrological environments, it still faces several limitations, such as ambiguous delineation of land–water boundaries and the difficulty in capturing multiscale water body characteristics. To address these issues, a Dynamic Weight Fusion SegFormer (DWFSeg) network is constructed, integrating a MixVision Transformer (MVT) encoder with a multiscale decoding architecture. Specifically, a Dynamic Multiscale Feature Fusion (DMFF) mechanism is proposed, which adaptively assigns semantic-guided fusion weights to multiscale feature water bodies. Furthermore, the Dual Attention-Enhanced (DAE) module strengthens discriminative essential features and suppresses background noise in both channel and spatial dimensions. Evaluated on a self-constructed super-resolution imagery dataset (SID) and the public GID, DWFSeg achieves overall accuracies of 98.08% and 96.14%, respectively. It outperforms representative benchmark models across multiple quantitative metrics, while maintaining competitive inference efficiency and favorable segmentation stability. Ablation studies verify the effectiveness and necessity of each proposed component. The presented network provides a reliable technical solution and supports refined water resource evaluation and sustainable watershed management.
Accurate crop classification provides fundamental data for agricultural resource management and ecological research. Hyperspectral image (HSI) classification is the core technique for achieving precise crop mapping. However, existing models often suffer from excessive parameters, limited robustness under few-shot conditions, and a trade-off between efficiency and robustness. To address these issues, this paper proposes a Multi-Scale Wavelet Kolmogorov–Arnold Network (MSWKN). The model employs a Two-Branch Feature Extractor (TBFE) to capture both spectral correlations and spatial textures. a Channel Cross-Spatial (CCS) module to suppress background clutter and highlight discriminative regions. A group convolution-based Fixed Wavelet Multi-Scale Convolutional Layer (FW-MSCL) that leverages the time–frequency localization of wavelets and learnable linear combinations to enhance robustness against spectral distortion while reducing parameters. And a Fourier-based Transformer encoder to enable global frequency–space modeling. Experiments on the WHU-Hi-HanChuan and WHU-Hi-HongHu hyperspectral crop datasets show that MSWKN achieves high overall accuracy and performs favorably on few-shot categories. Under lower parameter counts and fast inference conditions, the model demonstrates a reasonable trade-off between accuracy and computational efficiency. Ablation studies and wavelet kernel comparisons further confirm the contribution of each module and the advantage of the wavelet. The proposed framework provides an efficient and robust solution for fine-grained hyperspectral crop classification.