Jianzhong Guo

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.

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.

Hyperspectral image (HSI) classification in few-shot scenarios faces two core challenges. Limited samples and high spectral similarity lead to insufficient inter-class feature discriminability, and commonly used deep models suffer from the risk of overfitting. To address these problems, this paper proposes a Class-Adaptive Dictionary Reconstruction with Broad Learning (CADR-BL) method. Specifically, the method constructs an exclusive adaptive dictionary for each category and adopts an alternating minimization strategy to achieve sparse reconstruction of intra-class pixels, thereby enhancing intra-class spectral consistency and suppressing inter-class interference. On this basis, an improved Hyperspectral Broad Learning (HS-BL) model is introduced to efficiently classify the reconstructed features. Random feature mapping and closed-form solutions of output weights are utilized to alleviate overfitting in few-shot learning. Experiments conducted on three benchmark datasets, namely Indian Pines, Salinas, and WHU-Hi-HanChuan, show that CADR-BL outperforms several mainstream few-shot classification methods in terms of overall accuracy, average accuracy, and Kappa coefficient. Notably, CADR-BL maintains robust performance even with extremely limited training samples, and is less sensitive to variations in sample size than other comparative methods, demonstrating strong generalization ability. The proposed method provides a reliable technical reference for few-shot HSI classification in applications such as precision agriculture, environmental monitoring, and resource exploration.

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.

Cross-view image geolocalization aims to achieve accurate localization of geo-tagged images without geo-tagging by matching ground-view images with satellite images. However, there are huge imaging differences between ground and satellite viewpoints, and existing methods usually rely on a large number of accurately labeled cross-view image pairs. Therefore, to address issues such as significant perspective differences, high annotation costs, and low utilization of unpaired data, this paper proposes a cross-view generation model that integrates multi-scale contrastive learning and dynamic optimization, designs a multi-scale contrast loss function to strengthen the semantic consistency between the generated images and the target domain, adaptively balances the quality and quantity of pseudo-labels according to a dynamic threshold screening mechanism, and introduces a hard-sample triplet loss to enhance the model discriminative ability. Ablation experiments on the CVUSA and CVACT datasets show that the BEV-CycleGAN+CL (Bird’s-Eye View Cycle-Consistent Generative Adversarial Network with Contrastive Learning) model proposed in this paper significantly outperforms the comparative models in PSNR, SSIM, and RMSE metrics. Specifically, on the CVACT dataset, compared with the BEV-CycleGAN, BEV, and CycleGAN baselines, PSNR increased by 2.83%, 16.02%, and 42.30%, SSIM increased by 6.12%, 8.00%, and 18.48%, and RMSE decreased by 9.28%, 15.51%, and 25.35%, respectively. Similar advantages are observed on the CVUSA dataset. Compared with current state-of-the-art models, the dynamic threshold pseudo-label localization method in this paper demonstrates overall superiority in recall metrics such as R@1, R@5, R@10, and R@1%, for example achieving an R@1 of 98.94% on CVUSA, outperforming the best comparative model, Sample4G^†, which reached 98.68%. This study provides innovative methodological support for disaster emergency response, high-precision map construction for autonomous driving, military reconnaissance, and other applications.

The Gravity Recovery and Climate Experiment (GRACE) tracks drought events by detecting changes in the global gravitational field and capturing abnormal information on the reserves of surface water, soil water, and groundwater, which makes it possible for a more comprehensive and unified global and regional monitoring of groundwater drought. This study adopted the gravity satellite GRACE data and combined it with the hydrological model dataset. Additionally, we assessed the temporal evolution and spatial pattern of groundwater drought in the Yangtze River Basin (YRB) and its sub-basins from 2003 to 2022, determined the change points of the hidden seasonal and trend components in groundwater drought, and identified the direct/indirect driving contributions of the main climatic and circulation factors to groundwater drought. The results show that (1) as a normalized index, the groundwater drought index (GDI) can reflect direct evidence of any surplus and deficit in groundwater availability. During the study period, the minimum value (−1.66) of the GDI occurred in July 2020 (severe drought). (2) The average value of GDI in the entire basin ranged from −1.66 (severe drought) to 0.52 (no drought). (3) The average Z_s values (Mann–Kendall Z-statistic) of GDI were −0.23, −0.16, −0.43, and 0.14, respectively, and the proportions of areas with aggravated drought reached 65.21%, 61.05%, 89.70% and 43.67%, respectively. (4) Partial wavelet coherence analysis can simultaneously reveal the local correlations of time series at different time scales and frequencies. Based on partial wavelet analysis, precipitation was the best factor for explaining the dynamic changes in groundwater drought. (5) The North Pacific Index (NPI), the Pacific/North American Index (PNA), and the Sunspot Index (SSI) can serve as the main predictors that can effectively capture the drought changes in groundwater in the YRB. The GRACE satellite can provide a new tool for monitoring, tracking, and assessing groundwater drought situations, which is of great significance for guiding the development of the drought early warning system in the YRB and effectively preventing and responding to drought disasters.

Under the extensive influence of the monsoon climate, droughts in the Yangtze River Basin (YRB) occur frequently and pose a serious threat to grain security. To better understand the evolution and drivers of soil drought, this study employed remote sensing-based soil moisture and atmospheric circulation data from 2000 to 2022. It assessed the spatiotemporal characteristics of soil drought across the YRB and its sub-basins, identified the main mutation points and types, and quantified the relative contributions of climatic and circulation factors. The results show that: (1) the most severe soil drought month occurred in August 2022 (Standardized Soil Moisture Index SSMI = –1.69), with two major mutation points in May 2011 (“decrease to increase”) and June 2019 (“increase to decrease”); (2) drought mutations were mainly categorized as “interrupted decrease” (9 sub-basins) and “increase to decrease” (1 sub-basin), most occurring after 2010; (3) the year 2022 experienced the most severe annual drought (SSMI = –0.94), with extreme drought covering 39.36% of the basin in August; (4) precipitation (PC) was the dominant climatic factor influencing drought (percentage area of significant coherence PASC = 15.48%), while the Interannual Pacific Oscillation (IPO), Pacific Decadal Oscillation (PDO), and Dipole Mode Index (DMI) all showed significant remote-correlation effects, with mean Shapley additive explanations (SHAP) values of 0.138, 0.111, and 0.090, respectively. This study clarifies the spatiotemporal patterns and drivers of soil drought in the YRB, providing a scientific basis for improved drought monitoring and agricultural risk management.

Terrestrial water storage includes soil water storage, groundwater storage, surface water storage, snow water equivalent, plant canopy water storage, biological water storage, etc., which can comprehensively reflect the total change in water volume during processes such as precipitation, evapotranspiration, runoff, and human water use in the basin hydrological cycle. The Gravity Recovery and Climate Experiment (GRACE) satellite provides a powerful tool and a new approach for observing changes in terrestrial water storage and groundwater storage. The North China Plain (NCP) is a major agricultural region in the northern arid area of China, and long-term overexploitation of groundwater has led to increasingly prominent ecological vulnerability issues. This study uses GRACE and Global Land Data Assimilation System (GLDAS) hydrological model data to assess the spatiotemporal patterns of groundwater drought in the NCP and its various sub-regions from 2003 to 2022, identify the locations, occurrence probabilities, and confidence intervals of seasonal and trend mutation points, quantify the complex interactive effects of multiple climate factors on groundwater drought, and reveal the propagation time from groundwater drought to agricultural drought. The results show that: (1) from 2003 to 2022, the linear tendency rate of groundwater drought index (GDI) was −0.035 per 10 years, indicating that groundwater drought showed a gradually worsening trend during the study period; (2) on an annual scale, the most severe groundwater drought occurred in 2021 (GDI = −1.59). In that year, the monthly average GDI in the NCP ranged from −0.58 to −2.78, and the groundwater drought was most severe in July (GDI = −2.02); (3) based on partial wavelet coherence, the best univariate, bivariate for groundwater drought were soil moisture (PASC = 19.13%); and (4) in Beijing, Tianjin and Hebei, the propagation time was mainly concentrated in 1–5 months, with average lag times of 2.87, 3.20, and 2.92 months, respectively. This study can not only reduce and mitigate the harm of groundwater drought to agricultural production, social life, and ecosystems by monitoring changes in groundwater storage, but also provide a reference for the quantitative identification of the dominant factors of groundwater drought.

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research towards the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we introduce a set of metrics considering both quantitative and qualitative aspects of the road network. Compared to traditional neural networks, our HAN model demonstrates superior accuracy and F1-score, particularly for road types with comparable samples. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation.