The core challenge in remote sensing semantic segmentation lies in balancing local detail extraction with global contextual modeling. Existing methods often suffer from limited local receptive fields and inadequate global semantic interaction, leading to the attenuation of small-object features during hierarchical downsampling and fusion. To address these issues, we propose STRNet, a heterogeneous dual-stream encoder–decoder network that integrates a ResNet50 primary encoder and a Swin Transformer auxiliary encoder. This architecture jointly enhances local detail representation and global dependency modeling. Specifically, we design a feature refinement module (FRM) within the ResNet50 encoder to dynamically emphasize task-relevant features via channel attention, improving the recognition of small targets and complex regions. Meanwhile, the swin transformer branch incorporates a detail-preserving compression module (DPCM), which combines deformable convolutions and multi-scale pooling to optimize patch-token downsampling, thereby mitigating spatial detail loss during self-attention encoding. To effectively integrate multi-level features from both branches, we introduce a feature fusion module (FFM) that employs cross-branch channel-attention weighting and multi-scale alignment. The decoder adopts a progressive skip-connection strategy, fusing low-level spatial details with high-level semantics to construct a multi-resolution decoding pyramid for refined segmentation. Extensive experiments conducted on the ISPRS Vaihingen,ISPRS Potsdam, and LoveDA datasets demonstrate that STRNet significantly improves the segmentation accuracy of small objects and achieves competitive performance across all categories, validating its effectiveness for remote sensing semantic segmentation tasks. The code is available at https://github.com/Z09157/STRNet.

The aboveground biomass (AGB) of forests reflects the productivity and carbon-storage capacity of the forest ecosystem. Although AGB estimation techniques have become increasingly sophisticated, the relationships between AGB, spatial distribution, and growth stages still require further exploration. In this study, the Picea schrenkiana (Picea schrenkiana var. tianschanica) forest area in the Kashi River Basin of the Ili River Valley in the western Tianshan Mountains was selected as the research area. Based on forest resources inventory data, Gaofen-1 (GF-1), Gaofen-6 (GF-6), Gaofen-3 (GF-3) Polarimetric Synthetic Aperture Radar (PolSAR), and DEM data, we classified the Picea schrenkiana forests in the study area into three cases: the Whole Forest without vertical zonation and stand age, Vertical Zonality Classification without considering stand age, and Stand-Age Classification without considering vertical zonality. Then, for each case, we used eXtreme Gradient Boosting (XGBoost), Back Propagation Neural Network (BPNN), and Residual Networks (ResNet), respectively, to estimate the AGB of forests in the study area. The results show that: (1) The integration of multi-source remote-sensing data and the ResNet can effectively improve the remote-sensing estimation accuracy of the AGB of Picea schrenkiana. (2) Furthermore, classification by vertical zonality and stand ages can reduce the problems of low-value overestimation and high-value underestimation to a certain extent.

Remote sensing technology plays an important role in woodland identification. However, in mountainous areas with complex terrain, accurate extraction of woodland boundary information still faces challenges. To address this problem, this paper proposes a multiple mixed attention U-Net (MMA-U-Net) semantic segmentation model using 2015 and 2022 GF-1 PMS images as data sources to improve the ability to extract the boundary features of Picea schrenkiana var. tianschanica forest. The U-Net architecture serves as its underlying network, and the feature extraction ability of the Picea schrenkiana var. tianschanica is improved by adding hybrid attention CBAM and replacing the original skip connection with the DCA module to improve the accuracy of the model segmentation. The results show that on the remote sensing dataset with GF-1 PMS images, compared with the original U-Net and other models, the accuracy of the multiple mixed attention U-Net model is increased by 5.42%–19.84%. By statistically analyzing the spatial distribution of Picea schrenkiana var. tianschanica as well as their changes, the area was 3471.38 km² in 2015 and 3726.10 km² in 2022. Combining the predicted results with the DEM data, it was found that the Picea schrenkiana var. tianschanica were most distributed at an altitude of 1700–2500 m. The method proposed in this study can accurately identify Picea schrenkiana var. tianschanica and provides a theoretical basis and research direction for forest monitoring.