Accurate registration of optical and synthetic aperture radar (SAR) images is a fundamental prerequisite for multi-source remote sensing data fusion and analysis. However, due to the substantial differences in imaging mechanisms, optical–SAR image pairs often exhibit significant radiometric discrepancies and spatially varying geometric inconsistencies, which severely limit the robustness of traditional feature or region-based registration methods in cross-modal scenarios. To address these challenges, this paper proposes an end-to-end Optical–SAR Registration Network (OSR-Net) based on multi-constraint joint optimization. The proposed framework explicitly decouples cross-modal feature alignment and geometric correction, enabling robust registration under large appearance variation. Specifically, a multi-modal feature extraction module constructs a shared high-level representation, while a multi-scale channel attention mechanism adaptively enhances cross-modal feature consistency. A multi-scale affine transformation prediction module provides a coarse-to-fine geometric initialization, which stabilizes parameter estimation under complex imaging conditions. Furthermore, an improved spatial transformer network is introduced to perform structure-preserving geometric refinement, mitigating spatial distortion induced by modality discrepancies. In addition, a multi-constraint loss formulation is designed to jointly enforce geometric accuracy, structural consistency, and physical plausibility. By employing a dynamic weighting strategy, the optimization process progressively shifts from global alignment to local structural refinement, effectively preventing degenerate solutions and improving robustness. Extensive experiments on public optical–SAR datasets demonstrate that the proposed method achieves accurate and stable registration across diverse scenes, providing a reliable geometric foundation for subsequent multi-source remote sensing data fusion.
High-resolution remote sensing building extraction often requires large amounts of manually labeled data, and models trained on one dataset may not perform equally well on another without additional annotations. To reduce this dependency on labeled target data, we propose SIGA-UNet3+, which combines a Spectral Index Gated Attention (SIGA) module with a transfer learning strategy. The SIGA module fuses DSBI, NDVI, and NDWI to emphasize building features and suppress vegetation/water interference. Pre-training on the public SpaceNet dataset followed by fine-tuning on a self-built GF-2 dataset (Changchun, China) allows the model to adapt with limited local labels. On SpaceNet, SIGA-UNet3+ achieves F1 = 83.21% and IoU = 70.19%, obtaining the best overall segmentation performance among the compared methods. On the GF-2 dataset, it attains F1 = 84.56% and IoU = 72.17%. Moreover, using only 10% of the GF-2 training samples, transfer learning improves the F1 score by 6–8 percentage points compared to training from scratch. These results indicate that SIGA-UNet3+ can provide a promising and data-efficient approach for high-resolution remote sensing building extraction.
Recent blind hyperspectral image unmixing methods have achieved effective spectral–spatial representation, yet the reliability of estimated abundances remains difficult to assess because errors in jointly estimated endmembers and abundances can compensate for each other. To address this issue, we propose Residual Diagnosis-Guided Abundance Correction (RDAC), a post-correction framework that preserves the initial abundance estimate as an anchor and characterizes its mismatch using structured reconstruction residuals. Abundance candidates are then combined with structured residual information, while only 1% reference abundances are used to learn the correction. RDAC was evaluated on the Jasper Ridge, Samson, and Urban datasets. With UNMamba as the primary blind-unmixing backbone, RDAC achieved A-RMSEs of 0.0229, 0.0175, and 0.0359, reducing the initial errors by 55.05%, 70.80%, and 59.63%, respectively. It also achieved the lowest mean A-RMSE among the compared methods on Jasper Ridge and Samson while remaining competitive on Urban. Further experiments showed that reconstruction error alone does not reliably indicate abundance accuracy. When applied to NMF, RDAC reduced A-RMSE by 80.45%, 89.25%, and 77.61% on the three datasets. The results indicate that structured residual diagnosis can support abundance correction under limited supervision, and the NMF experiment shows that the same correction framework can also be used with an alternative blind-unmixing backbone.
Soil organic carbon (SOC) plays a critical role in the global carbon cycle and agroecosystem productivity. However, existing hyperspectral inversion models often exhibit significant predictive biases when applied across large geographic scales, primarily due to the spatial heterogeneity of pedogenic environments and background mineralogy. This study proposes a cross-regional SOC prediction method based on an optimal spectral feature set (SOC-OSFS). Leveraging laboratory hyperspectral and SOC data from 17,730 samples collected across the black soil regions of Northeast China and Europe, a core spectral feature set comprising 31 diagnostic bands was extracted using the competitive adaptive reweighted sampling (CARS) algorithm combined with the successive projections algorithm (SPA). Although this SOC-OSFS accounts for merely 1.55% of the original full-spectrum dimensionality (31 out of 2000 bands), it demonstrated robust analytical capability in local modeling across all study regions, yielding coefficients of determination (R2 = 0.6714–0.8854). When transferring the prediction model calibrated in the core source domain (n = 10,000) to the other seven independent typical black soil target domains, the direct cross-regional prediction consistently reduced the root mean square error (RMSE) by over 15% compared to that of the full-spectrum models. By further incorporating 20% of the local background samples for intercept correction, the cross-regional predictive accuracy was substantially improved; the goodness-of-fit for the Northeast China target domains increased sharply (maximum R2 = 0.8567), and the European target domains, which feature substantially different pedogenic environments, were successfully corrected from negative to positive linear fits. This study validates the efficacy of extracting physiochemically meaningful spectral bands in mitigating the interference caused by spatial heterogeneity, thereby providing a mechanistically grounded and practically viable framework for large-scale SOC estimation via remote sensing.
Graph attention improves neighbor discrimination, but it remains limited by local receptive fields and by a strong dependence on the input topology, which is often unreliable on heterophilous graphs. We propose Geometric Graph Learning Network (G2LNet), a structure-learning framework that infers message-passing probabilities from an explicit geometric topology learned in latent Euclidean or hyperbolic spaces. G2LNet combines (i) a geometric mapping module, (ii) distance- or inner-product-based relation operators with perceptual connectivity to control the influence of the given graph, and (iii) end-to-end constraint objectives enforcing stability, sparsity, and (optional) symmetry of the learned topology. This design yields unified local, non-local, and graph-free neighborhoods, enabling systematic analysis of when non-local aggregation helps. Experiments on node classification across nine publicly available benchmark datasets demonstrate that G2LNet’s controlled variant consistently achieves higher accuracy than representative strong baseline models–both local and non-local–on most datasets. This establishes a robust alternative for smaller scale node classification tasks.
Ground control point (GCP) selection is a critical step in the automated high-precision geometric correction of remote sensing imagery. While the quantity, quality, and distribution of GCPs are three factors which may affect the accuracy of geometric correction, traditional automated selection methods predominantly focus on optimizing spatial distribution, often neglecting the inherent quality heterogeneity within matched point sets. This paper proposes a Reliability-weighted Spatial Coverage Sampling (SCS+R) method, which integrates matching reliability into the spatial coverage sampling framework via an adaptive weight factor (α). Experiments using Gaofen-2 (GF-2) imagery demonstrate that with 58 GCPs selected by SCS+R, the relative geometric consistency with the reference imagery is improved to a sub-pixel level (1.55–2.23 m) for multispectral images and within two pixels (0.99–1.81 m) for panchromatic images. Compared to the standard SCS, Voronoi, and weighted Voronoi methods, SCS+R improves the average accuracy by approximately 25%, 16%, and 8%, respectively. These results verify the enhanced stability and robustness of the proposed method in complex environments. Moreover, the optimal adaptive reliability weight α consistently stabilizes in a low range of 0.1–0.3, quantitatively revealing a key principle for small-sample GCP selection: spatial uniformity provides the foundation, while point reliability is the key to achieving high precision.