{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T06:17:27Z","timestamp":1788157047782,"version":"build-2803163510"},"reference-count":45,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Hyperspectral imaging provides rich spectral\u2013spatial information for fine-grained material discrimination, but effective and interpretable modeling remains challenging because land-cover regions often have irregular spatial structures and class-specific spectral responses. Conventional methods typically rely on fixed grid patches or local neighborhoods, which may not align with natural object boundaries, whereas pure superpixel or graph models may lose fine pixel-level details. This paper proposes an explainable superpixel-guided graph vision transformer (ESG-ViT) for hyperspectral image classification and analysis. The proposed framework contains two complementary branches: a graph superpixel vision transformer (GS-ViT) that represents hyperspectral scenes as adaptive superpixel tokens and injects graph topology into self-attention, and a windowed pixel vision transformer (WP-ViT) that preserves dense local spectral\u2013spatial details through efficient local attention. The two representations are adaptively fused for pixel-wise classification. To support interpretability, the model further derives class-wise superpixel relevance maps and spectral channel importance from gradient responses, revealing both the spatial regions and wavelength channels that contribute to each category. Experiments on multiple benchmark hyperspectral datasets demonstrate that the proposed method improves classification accuracy while producing clearer, more human-aligned explanations. Visualization results show that the model highlights meaningful class-related superpixel regions and assigns distinct spectral-channel importance patterns to different classes. These results indicate that the proposed framework provides an accurate and explainable alternative to conventional patch-based transformers for hyperspectral image analysis.<\/jats:p>","DOI":"10.3390\/s26175513","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:55:56Z","timestamp":1788155756000},"page":"5513","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Superpixel-Guided Graph Vision Transformer for Hyperspectral Image Analysis"],"prefix":"10.3390","volume":"26","author":[{"given":"Jieli","family":"Chen","sequence":"first","affiliation":[{"name":"School of Advanced Technology, Xian Jiaotong-Liverpool University, Suzhou 215123, China"},{"name":"Department of Electrical Engineering & Electronics, University of Liverpool, Liverpool L69 3BX, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kah Phooi","family":"Seng","sequence":"additional","affiliation":[{"name":"Faculty of Innovation and Technology, Taylor\u2019s University, Selangor 47500, Malaysia"},{"name":"School of Science, Technology and Engineering, University of Sunshine Coast, Petrie, QLD 4502, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3033-4688","authenticated-orcid":false,"given":"Chee Shen","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xian Jiaotong-Liverpool University, Suzhou 215123, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-Minn","family":"Ang","sequence":"additional","affiliation":[{"name":"School of Science, Technology and Engineering, University of Sunshine Coast, Petrie, QLD 4502, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering & Electronics, University of Liverpool, Liverpool L69 3BX, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"6690","DOI":"10.1109\/TGRS.2019.2907932","article-title":"Deep Learning for Hyperspectral Image Classification: An Overview","volume":"57","author":"Li","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sudharsan, S., Hemalatha, R., and Radha, S. (2019, January 21\u201323). A Survey on Hyperspectral Imaging for Mineral Exploration Using Machine Learning Algorithms. Proceedings of the 2019 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET), Chennai, India.","DOI":"10.1109\/WiSPNET45539.2019.9032740"},{"key":"ref_3","unstructured":"Shirmard, H., and Farahbakhsh, E. (2023). Mineral Exploration Using Multispectral and Hyperspectral Remote Sensing Data. Geoinformatics for Geosciences, Elsevier."},{"key":"ref_4","unstructured":"Mercier, G., and Lennon, M. (2003, January 21\u201325). Support Vector Machines for Hyperspectral Image Classification with Spectral-Based Kernels. Proceedings of the IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings, Toulouse, France."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4843","DOI":"10.1109\/TIP.2017.2725580","article-title":"Going Deeper with Contextual CNN for Hyperspectral Image Classification","volume":"26","author":"Lee","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4604","DOI":"10.1109\/TGRS.2020.2964627","article-title":"Hyperspectral Image Classification with Convolutional Neural Network and Active Learning","volume":"58","author":"Cao","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"8657","DOI":"10.1109\/TGRS.2020.3037361","article-title":"CNN-Enhanced Graph Convolutional Network with Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification","volume":"59","author":"Liu","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.neunet.2023.08.059","article-title":"CEGAT: A CNN and Enhanced-GAT Based on Key Sample Selection Strategy for Hyperspectral Image Classification","volume":"168","author":"Shi","year":"2023","journal-title":"Neural Netw."},{"key":"ref_9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021). An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_12","unstructured":"Kipf, T.N., and Welling, M. (2017, January 24\u201326). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the 5th International Conference on Learning Representations (ICLR), Toulon, France."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5966","DOI":"10.1109\/TGRS.2020.3015157","article-title":"Graph Convolutional Networks for Hyperspectral Image Classification","volume":"59","author":"Hong","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","first-page":"5519718","article-title":"Multistage Superpixel-Guided Hyperspectral Image Classification with Sparse Graph Attention Networks","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5521813","DOI":"10.1109\/TGRS.2024.3418583","article-title":"Dual-Branch Subpixel-Guided Network for Hyperspectral Image Classification","volume":"62","author":"Han","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1080\/2150704X.2023.2258467","article-title":"A Global+ Multiscale Hybrid Network for Hyperspectral Image Classification","volume":"14","author":"Zhao","year":"2023","journal-title":"Remote Sens. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1007\/s00530-026-02300-2","article-title":"GCGV: A Dual-Branch Hybrid Network Integrating Graph Attention, CNNs, and Vision Transformers for Enhanced Hyperspectral Image Classification","volume":"32","author":"Ji","year":"2026","journal-title":"Multimed. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"22050","DOI":"10.1109\/JSTARS.2026.3703001","article-title":"Hyperspectral Image Classification Using a Hybrid Vision Transformer and Graph Convolutional Network","volume":"19","author":"Mahdavipour","year":"2026","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11\u201317). Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows. Proceedings of the 2021 IEEE International Conference on Computer Vision (ICCV), Virtual.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5518615","DOI":"10.1109\/TGRS.2021.3130716","article-title":"SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers","volume":"60","author":"Hong","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5522214","DOI":"10.1109\/TGRS.2022.3221534","article-title":"Spectral\u2013Spatial Feature Tokenization Transformer for Hyperspectral Image Classification","volume":"60","author":"Sun","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3095","DOI":"10.1109\/TIP.2022.3162964","article-title":"Deep Hierarchical Vision Transformer for Hyperspectral and LiDAR Data Classification","volume":"31","author":"Xue","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"120828","DOI":"10.1016\/j.eswa.2023.120828","article-title":"Local Aggregation and Global Attention Network for Hyperspectral Image Classification with Spectral-Induced Aligned Superpixel Segmentation","volume":"232","author":"Chen","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhu, A.Z., Mei, J., Qiao, S., Yan, H., Zhu, Y., Chen, L.-C., and Kretzschmar, H. (2023, January 1\u20135). Superpixel Transformers for Efficient Semantic Segmentation. Proceedings of the 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA.","DOI":"10.1109\/IROS55552.2023.10341519"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5532816","DOI":"10.1109\/TGRS.2024.3468876","article-title":"PSFormer: Pyramid Superpixel Transformer for Hyperspectral Image Classification","volume":"62","author":"Zou","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"84517","DOI":"10.1109\/ACCESS.2026.3699482","article-title":"Transform-Aware Deep Learning and Explainable AI in Remote Sensing: A Comprehensive Meta-Analysis","volume":"14","author":"Kasetty","year":"2026","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"\u015eahin, \u0130., Ert\u00fcrk, A., and Aptoula, E. (2023, January 5\u20138). Band-Based Interpretability with SHAP for Hyperspectral Classification. Proceedings of the 2023 31st Signal Processing and Communications Applications Conference (SIU), Istanbul, Turkey.","DOI":"10.1109\/SIU59756.2023.10223795"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Oveis, A.H., Giusti, E., Meucci, G., Ghio, S., and Martorella, M. (November, January 31). Explainability In Hyperspectral Image Classification: A Study of Xai Through the Shap Algorithm. Proceedings of the 2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), Athens, Greece.","DOI":"10.1109\/WHISPERS61460.2023.10430776"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"108316","DOI":"10.1016\/j.patcog.2021.108316","article-title":"Explainable Scale Distillation for Hyperspectral Image Classification","volume":"122","author":"Shi","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, J., Lan, J., Zeng, Y., Luo, W., Zhuang, Z., and Zou, J. (2025). Explainability Feature Bands Adaptive Selection for Hyperspectral Image Classification. Remote Sens., 17.","DOI":"10.3390\/rs17091620"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"8500105","DOI":"10.1109\/LGRS.2023.3251652","article-title":"Interpretable Deep Learning Framework for Land Use and Land Cover Classification in Remote Sensing Using SHAP","volume":"20","author":"Temenos","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"108381","DOI":"10.1016\/j.compeleceng.2022.108381","article-title":"Towards Explainable AI for Hyperspectral Image Classification in Edge Computing Environments","volume":"103","author":"Lapegna","year":"2022","journal-title":"Comput. Electr. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Abnar, S., and Zuidema, W. (2020, January 5\u201310). Quantifying Attention Flow in Transformers. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), Virtual.","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref_34","unstructured":"Amin, K. (2025). Hyperspectral Remote Sensing Datasets: Indian Pines, Pavia University, Botswana and Salinas, IEEE DataPort."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"112012","DOI":"10.1016\/j.rse.2020.112012","article-title":"WHU-Hi: UAV-Borne Hyperspectral with High Spatial Resolution (H2) Benchmark Datasets and Classifier for Precise Crop Identification Based on Deep Convolutional Neural Network with CRF","volume":"250","author":"Zhong","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, R., Zheng, S., Duan, C., Yang, Y., and Wang, X. (2020). Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network. Remote Sens., 12.","DOI":"10.20944\/preprints201912.0059.v2"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ma, W., Yang, Q., Wu, Y., Zhao, W., and Zhang, X. (2019). Double-Branch Multi-Attention Mechanism Network for Hyperspectral Image Classification. Remote Sens., 11.","DOI":"10.3390\/rs11111307"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wang, W., Dou, S., Jiang, Z., and Sun, L. (2018). A Fast Dense Spectral\u2013Spatial Convolution Network Framework for Hyperspectral Images Classification. Remote Sens., 10.","DOI":"10.3390\/rs10071068"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1109\/TGRS.2017.2755542","article-title":"Spectral\u2013Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework","volume":"56","author":"Zhong","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"5530215","DOI":"10.1109\/TGRS.2022.3220748","article-title":"A Fast Dynamic Graph Convolutional Network and CNN Parallel Network for Hyperspectral Image Classification","volume":"60","author":"Liu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.1109\/TIP.2022.3144017","article-title":"Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network for Hyperspectral Image Classification","volume":"31","author":"Dong","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_42","unstructured":"Baatz, M., and Sch\u00e4pe, A. (2000, January 5\u20137). Multiresolution Segmentation: An Optimization Approach for High Quality Multi-Scale Image Segmentation. Proceedings of the AGIT Symposium (Angewandte Geographische Informations-Verarbeitung XII), Salzburg, Austria."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.1109\/JSTARS.2013.2290296","article-title":"A Support Vector Conditional Random Fields Classifier with a Mahalanobis Distance Boundary Constraint for High Spatial Resolution Remote Sensing Imagery","volume":"7","author":"Zhong","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/S0034-4257(98)00064-9","article-title":"Imaging Spectroscopy and the Airborne Visible\/Infrared Imaging Spectrometer (AVIRIS)","volume":"65","author":"Green","year":"1998","journal-title":"Remote Sens. Environ."},{"key":"ref_45","unstructured":"IPI, Hannover (1998). Electronic Performance of the Imaging Spectrometer ROSIS-03. Proceedings of the ISPRS PROCEEDINGS Joint Workshop \u201cSensors and Mapping form Space\u201d, ISPRS."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5513\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T06:01:32Z","timestamp":1788156092000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":45,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26175513"],"URL":"https:\/\/doi.org\/10.3390\/s26175513","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]}}}