In recent years, advancements in remote sensing image observation technology have significantly enriched the surface feature information captured in remote sensing images, posing greater challenges for semantic information extraction from remote sensing imagery. While convolutional neural networks (CNNs) excel at understanding relationships between adjacent image regions, processing multidimensional data requires reliance on attention mechanisms. However, due to the inherent complexity of remote sensing images, most attention mechanisms designed for natural images underperform when applied to remote sensing data. To address these challenges in remote sensing image semantic segmentation, we propose a highly generalizable multi-branch attention fusion method based on shallow and deep features. This approach applies pixel-wise, spatial, and channel attention mechanisms to feature maps fused with shallow and deep features, thereby enhancing the network’s semantic information extraction capability. Through evaluations on the Cityscapes, LoveDA, and WHDLD datasets, we validate the performance of our method in processing remote sensing data. The results demonstrate consistent improvements in segmentation accuracy across most categories, highlighting its strong generalization capability. Specifically, compared to baseline methods, our approach achieves average mIoU improvements of 0.42% and 0.54% on the WHDLD and LoveDA datasets, respectively, significantly enhancing network performance in complex remote sensing scenarios.

Accurate fine-scale forest mapping is fundamental for ecological monitoring and resource management. While deep learning semantic segmentation methods have advanced the interpretation of high-resolution UAV imagery, their generalization across diverse forest regions remains challenging due to high spatial heterogeneity. To address this, we propose two enhanced versions based on the PP-LiteSeg architecture for robust cross-regional forest segmentation. Version 01 (V01) integrates a multi-branch attention fusion module composed of parallel channel, spatial, and pixel attention branches. This design enables fine-grained feature enhancement and precise boundary delineation in structurally regular artificial forests, such as the Huayuan Forest Farm. As a result, V01 achieves a mIoU of 92.64% and an F1-score of 96.10%, representing an approximately 18 percentage-point mIoU improvement over PSPNet and DeepLabv3+. Building on this, Version 02 (V02) introduces a lightweight residual connection that directly shortcuts the fused features, thereby improving feature stability and robustness under complex textures and illumination, and demonstrates stronger performance in naturally heterogeneous forests (Longhai Township), attaining an mIoU of 91.87% and an F1-score of 95.77% (5.72 percentage-point mIoU gain over DeepLabv3+). We further conduct comprehensive comparisons against conventional CNN baselines as well as representative lightweight and transformer-based models (BiSeNetV2 and SegFormer-B0). In bidirectional cross-region transfer (train on one region and directly test on the other), V02 exhibits the most stable performance with minimal degradation, highlighting its robustness under domain shift. On a combined cross-regional dataset, V02 achieves a leading mIoU of 91.50%, outperforming U-Net, DeepLabv3+, and PSPNet. In summary, V01 excels in boundary delineation for regular plantation forests, whereas V02 shows more stable generalization across highly varied natural forest landscapes, providing practical solutions for region-adaptive UAV forest segmentation.

The Solar Upper Transition Region Imager (SUTRI) onboard SATech-01 acquires full-disk solar images at 46.5 nm. Affected by intense radiation in polar regions and the South Atlantic Anomaly, the Level 0 (L0) raw data are severely contaminated by bright anomalies such as cosmic-ray (CR) hits and by dark spots from instrumental dust, both of which must be corrected prior to scientific analysis. The SUTRI L0.9 pipeline uses median filtering to remove CRs and low-pass filtering to fill dark spots, but the former misclassifies genuine solar structures as noise, while the latter yields over-smoothed, textureless fillings. To this end, this paper proposes a deep-learning method combining anomaly detection and image completion; it comprises three components: (1) a multi-morphology anomaly simulation strategy; (2) a U-Net inpainting network with Pyramidal Multi-Scale Channel Attention (PMSCA) trained with a composite loss combining weighted relative L1, multi-scale SSIM, and per-type L1 terms; and (3) an anomaly detector that identifies the regions to be repaired, guiding backfill-based completion. Compared with SUTRI L0.9, the proposed method achieves better dark-spot repair while maintaining effective CR repair. The code and data used in this paper are publicly available on GitHub: https://github.com/qzplucky/SUTRI-Images-Completion.