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.
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.