Accurate monitoring of total suspended matter (TSM) concentration is essential for aquatic ecosystem protection and water quality assessment. Multispectral remote sensing provides an effective approach for large-scale TSM monitoring. However, robust retrieval models are difficult to develop due to limited in situ data. This study presents a Deep Feature Extraction–Machine Learning fusion framework that integrates a pre-trained back-propagation neural network (BPNN) with support vector regression (SVR) to enhance TSM retrieval. High-level spectral features extracted by BPNN are used as inputs to SVR (termed DFE-SVR) for regional TSM retrieval, using in situ measurements from five inland lakes in Jiangsu and Anhui Provinces, China. The generated TSM maps showed spatial patterns consistent with TSM concentration distributions visually observed in true-color imagery. Validation results demonstrated that DFE-SVR outperformed BPNN and SVR models, achieving R2 of 0.85 and 0.90 and RMSE of 7.95 and 4.76 mg/L for GF-1 and Sentinel-2 imagery, respectively. Compared with SVR models using principal component analysis or band combinations, DFE-SVR reduced RMSE by over 20%. Under reduced training samples, the DFE-SVR model also maintained higher stability and accuracy. These findings showed its potential for multispectral water quality monitoring with limited in situ data.
High-resolution hyperspectral computational imaging is critical for applications such as environmental monitoring, urban planning, and precision agriculture. In practical hyperspectral imaging systems, physical hardware constraints inevitably lead to coupled degradations across spatial and spectral dimensions, making it difficult to simultaneously achieve high spatial resolution and high spectral fidelity. As a representative and widely studied hyperspectral computational imaging task, hyperspectral pansharpening aims to reconstruct high-resolution hyperspectral images by integrating low-resolution hyperspectral images with high-resolution panchromatic images. Existing methods frequently suffer from spectral distortion or blurred spatial details due to unidirectional fusion strategies or isolated processing branches that inadequately model the intrinsic spatial–spectral coupling in the imaging process. To overcome these limitations, we propose a bidirectional driving framework that enables synergistic mutual guidance between spatial detail infusion and spectral fidelity preservation. Specifically, spatial coordinate-aware representations are dynamically integrated into a spectral self-attention module, while spectral importance scores are utilized to modulate multi-receptive-field convolutions via channel-wise weighting. This bidirectional interaction mechanism forms a closed-loop coupling between spatial and spectral representations, ensuring enhanced spatial reconstruction while rigorously preserving spectral integrity. Furthermore, to bridge the gap between simulated experiments and real-world applications, we constructed a large-scale dataset derived from the ZY-1-02D satellite. This dataset features high-fidelity PAN (17,820 × 16,128) and HSI (1485 × 1344) pairs, which we have made publicly available to the community to facilitate future research. Extensive experiments on both benchmark simulations and the proposed ZY-1-02D dataset demonstrate that our method achieves state-of-the-art performance in both spatial fidelity and spectral preservation.