2026-05-28T13:46:26Zhttps://riubu.ubu.es/oai/request

oai:riubu.ubu.es:10259/117232026-05-27T06:16:27Zcom_10259_9476com_10259.4_106com_10259_2604col_10259_9477

Gui, Baoling Sam, Lydia Bhardwaj, Anshuman Soto Gómez, Diego González Peñaloza, Félix Buchroithner, Manfred F. Green, David R. 2026-05-26T08:20:19Z 2026-05-26T08:20:19Z 2025-09 0924-2716 https://hdl.handle.net/10259/11723 10.1016/j.isprsjprs.2025.06.004 Growing global population, changing climate, and shrinking land resources demand for quicker, efficient, and more accurate methods of mapping and monitoring vegetation cover in remote sensing datasets. Many deep learning-based methods have been widely applied for semantic segmentation tasks in remote sensing images of vegetated environments. However, most existing models are pixel-based, which introduces challenges such as high time consumption, cumbersome implementation, and limited scalability. This paper presents the SAGRNet model, a Graph Convolutional Neural Network (GCN) that incorporates sampling aggregation and self-attention mechanisms, while leveraging the ResNet residual network structure. A key innovation of SAGRNet is its ability to fuse features extracted through diverse algorithms, enabling comprehensive representation and enhanced classification performance. The SAGRNet model demonstrates superior performance over leading pixel-based neural networks, such as U-Net++ and DeepLabV3, in terms of both time efficiency and accuracy in vegetation image classification tasks. We achieved an overall mapping accuracy of ~90 % using SAGRNet, compared to ~87% and ~85% from U-Net++ and DeepLabV3, respectively. Additionally, it offers more convenience in data processing. Furthermore, the model significantly outperforms cutting-edge graph-based convolutional networks, including Graph U-Net (achieved overall accuracy ~65%) and TGNN (achieved overall accuracy ~75%), showcasing exceptional generalization capability and classification accuracy. This paper provides a comprehensive analysis of the various processing aspects of this object-based GCN for vegetation mapping and emphasizes its significant potential for practical use. The model’s versatility can also be expanded to other image processing domains, offering unprecedented possibilities of information extraction from satellite imagery The authors acknowledge BBSRC International Partnership Award (Ref: RG17324-19) and the University of Aberdeen to fund the research activities. We would like to thank the UK Centre for Ecology and Hydrology (UKCEH) for providing the high-resolution land cover maps of the United Kingdom, which served as an essential reference in our regional experiments. We also express our appreciation to ESRI for releasing the Global Land Cover dataset through the Living Atlas platform, which enabled the global-scale validation of our model. These openly accessible and high-quality datasets significantly supported the development and evaluation of our work application/pdf eng Elsevier ISPRS Journal of Photogrammetry and Remote Sensing. 2025, V. 227, p. 99-124 https://doi.org/10.1016/j.isprsjprs.2025.06.004 Atribución 4.0 Internacional http://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess Object-based classification Graph convolutional Vegetation mapping Deep learning Remote sensing Aprendizaje automático Cartografía de la vegetación Machine learning Vegetation mapping SAGRNet: A novel object-based graph convolutional neural network for diverse vegetation cover classification in remotely-sensed imagery info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion ISPRS Journal of Photogrammetry and Remote Sensing 227 99 124