{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:58:23Z","timestamp":1781150303459,"version":"3.54.1"},"reference-count":39,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Yunnan Provincial Major Science and Technology Special Project and Key R&D Program","award":["202403ZC380001"],"award-info":[{"award-number":["202403ZC380001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Hyperspectral images (HSIs) and Light Detection and Ranging (LiDAR) data offer complementary spectral and spatial information and are extensively applied to land cover classification. Nevertheless, current fusion\u2013classification approaches frequently suffer from cross-modal feature entanglement and insufficient exploitation of LiDAR physical priors, particularly the Digital Surface Model (DSM), which limits the interpretability of learned features and restricts classification accuracy. To address these issues, this study presents a Physics-Guided Adaptive Decoupling and Collaborative Enhancement Network (ADCE-Net) that embeds explicit geometric guidance into multimodal feature learning. In ADCE-Net, the DSM serves as an explicit geometric conditioning signal to guide feature decoupling, decomposing input representations into modality-shared semantic features (SSF) and modality-specific discriminative features (MSF), thereby mitigating cross-modal interference at an early stage. Based on this decomposition, an adaptive collaborative enhancement mechanism is designed using bidirectional cross-attention and dynamic gating to achieve context-aware mutual refinement between SSF and MSF, facilitating more effective utilization of cross-modal complementary information. Furthermore, a multi-level collaborative classification architecture is constructed to integrate multi-scale contextual representations, enhancing spatial consistency and boundary delineation. Extensive experiments on three benchmark datasets\u2014Trento, Houston 2013, and Muufl Gulfport\u2014demonstrate that ADCE-Net achieves overall accuracies of 99.69%, 97.37%, and 94.90%, respectively, surpassing multiple representative methods including support vector machines, 3D convolutional neural networks, transformer-based models, and recurrent neural networks. Noticeable improvements are also achieved for minority classes and classes with highly similar spectral signatures. The DSM-driven physics guidance boosts both classification performance and feature interpretability, providing a reliable and explainable paradigm for multimodal remote sensing classification.<\/jats:p>","DOI":"10.3390\/a19060473","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:59:31Z","timestamp":1781146771000},"page":"473","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Modal Remote Sensing Image Classification Method Based on Physics-Guided Feature Decoupling and Adaptive Collaborative Fusion of HSI\u2013LiDAR"],"prefix":"10.3390","volume":"19","author":[{"given":"Xiaochen","family":"Liu","sequence":"first","affiliation":[{"name":"School of Land and Resources, Kunming University of Science and Technology, Kumming 650093, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junsan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Land and Resources, Kunming University of Science and Technology, Kumming 650093, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5847-2556","authenticated-orcid":false,"given":"Guoping","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Land and Resources, Kunming University of Science and Technology, Kumming 650093, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"5525416","DOI":"10.1109\/TGRS.2024.3430373","article-title":"Multiple information collaborative fusion network for joint classification of hyperspectral and LiDAR data","volume":"62","author":"Tang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Liu, J., Xue, X., Zuo, Q., and Ren, J. (2024). Classification of hyperspectral\u2013LiDAR dual-view data using hybrid feature and trusted decision fusion. Remote Sens., 16.","DOI":"10.3390\/rs16234381"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Liu, G., Song, J., Chu, Y., Zhang, L., Li, P., and Xia, J. (2025). Deep fuzzy fusion network for joint hyperspectral and LiDAR data classification. Remote Sens., 17.","DOI":"10.3390\/rs17172923"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.arcontrol.2021.03.003","article-title":"A comprehensive review of hyperspectral data fusion with LiDAR and SAR data","volume":"51","author":"Kahraman","year":"2021","journal-title":"Annu. Rev. Control"},{"key":"ref_5","first-page":"103955","article-title":"An implicit transformer-based fusion method for hyperspectral and multispectral remote sensing image","volume":"131","author":"Zhu","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinform."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hang, R., Sun, W., Leng, Q., Guo, Y., Zhang, X., and Ma, L. (2023). Feature\u2013decision level collaborative fusion network for hyperspectral and LiDAR classification. Remote Sens., 15.","DOI":"10.3390\/rs15174148"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ge, H., Wang, L., Pan, H., Liu, Y., Li, C., Lv, D., and Ma, H. (2024). Cross attention-based multi-scale convolutional fusion network for hyperspectral and LiDAR joint classification. Remote Sens., 16.","DOI":"10.3390\/rs16214073"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1074","DOI":"10.1080\/2150704X.2024.2399864","article-title":"Classification of hyperspectral and LiDAR data by transformer-based enhancement","volume":"15","author":"Pan","year":"2024","journal-title":"Remote Sens. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wang, M., Sun, Y., Xiang, J., Sun, R., and Zhong, Y. (2024). Joint classification of hyperspectral and LiDAR data based on adaptive gating mechanism and learnable transformer. Remote Sens., 16.","DOI":"10.3390\/rs16061080"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, L., and Deng, S. (2025). Hypergraph convolution network classification for hyperspectral and LiDAR data. Sensors, 25.","DOI":"10.3390\/s25103092"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/s10462-025-11169-y","article-title":"A review of hyperspectral image classification based on graph neural networks","volume":"58","author":"Zhao","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1007\/s11063-024-11584-2","article-title":"Hyperspectral image classification based on 3D\u20132D hybrid convolution and graph attention mechanism","volume":"56","author":"Zhang","year":"2024","journal-title":"Neural Process. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/s10462-025-11265-z","article-title":"Deep learning for land use classification: A systematic review of HS\u2013LiDAR imagery","volume":"58","author":"Rehman","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, R., Sun, L., and Zheng, Y. (2024). Multi-Feature cross attention-induced transformer network for hyperspectral and LiDAR data classification. Remote Sens., 16.","DOI":"10.3390\/rs16152775"},{"key":"ref_15","first-page":"5505315","article-title":"Joint classification of hyperspectral and LiDAR data using height information guided hierarchical fusion-and-separation network","volume":"62","author":"Song","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","first-page":"4408914","article-title":"Feature reconstruction guided fusion network for hyperspectral and LiDAR classification","volume":"63","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5512815","DOI":"10.1109\/TGRS.2024.3374324","article-title":"Cross hyperspectral and LiDAR attention transformer: An extended self-attention for land use and land cover classification","volume":"62","author":"Roy","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_18","first-page":"5515815","article-title":"LiDAR-guided cross-attention fusion for hyperspectral band selection and image classification","volume":"62","author":"Yang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5533716","DOI":"10.1109\/TGRS.2024.3467674","article-title":"Interactive enhanced network based on multihead self-attention and graph convolution for classification of hyperspectral and LiDAR data","volume":"62","author":"Gao","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"127757","DOI":"10.1016\/j.neucom.2024.127757","article-title":"Center-bridged interaction fusion for hyperspectral and LiDAR classification","volume":"590","author":"Huo","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.isprsjprs.2023.12.004","article-title":"Physics inspired hybrid attention for SAR target recognition","volume":"207","author":"Huang","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Hussain, K., Zhao, Y., Zhou, Y., Ali, A., and Muzammil, K. (2025). Cross-Attention Bridge for hyperspectral and LiDAR dual-modality classification. Remote Sens., 17.","DOI":"10.3390\/rs17162836"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"028504","DOI":"10.1117\/1.JRS.19.028504","article-title":"Improved multi-scale self-calibrated convolution and cross-attention fusion network for HSI-LiDAR classification","volume":"19","author":"Pan","year":"2025","journal-title":"J. Appl. Remote Sens."},{"key":"ref_24","first-page":"666","article-title":"Deep multimodal unmixing of hyperspectral images using convolutional block attention module (CBAM) and LiDAR features","volume":"28","author":"Sreejam","year":"2025","journal-title":"Egypt. J. Remote Sens. Space Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5516816","DOI":"10.1109\/TGRS.2025.3579433","article-title":"Collaborative classification of hyperspectral and LiDAR data based on dynamic multiple fractional Fourier domains fusion","volume":"63","author":"Qin","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","first-page":"5503817","article-title":"Joint classification of hyperspectral and LiDAR data using hierarchical multimodal feature aggregation-based multihead axial attention transformer","volume":"63","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_27","first-page":"5531817","article-title":"Local-to-global cross-modal attention-aware fusion for HSI-X semantic segmentation","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1109\/JSTARS.2024.3502761","article-title":"MGMNet: Mutual-guidance mechanism for joint classification of multisource remote sensing data","volume":"18","author":"Zhang","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_29","first-page":"5525517","article-title":"S2DBFT: Spectral\u2013spatial dual-branch fusion transformer for hyperspectral image classification","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, F., Du, X., Zhang, W., Nie, L., Wang, H., Zhou, S., and Ma, J. (2024). Remote sensing LiDAR and hyperspectral classification with multi-scale graph encoder\u2013decoder network. Remote Sens., 16.","DOI":"10.3390\/rs16203912"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"103225","DOI":"10.1016\/j.inffus.2025.103225","article-title":"Cross-source transformer-based neighborhood contrastive learning for joint classification of hyperspectral and LiDAR data","volume":"124","author":"Liu","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.11834\/jrs.20210354","article-title":"Dimensionality reduction for hyperspectral remote sensing: Advances, challenges, and prospects","volume":"26","author":"Su","year":"2022","journal-title":"Natl. Remote Sens. Bull."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Feng, Q., Zhu, D., Yang, J., and Li, B. (2019). Multisource hyperspectral and LiDAR data fusion for urban land-use mapping based on a modified two-branch convolutional neural network. ISPRS Int. J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8010028"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4340","DOI":"10.1109\/TGRS.2020.3016820","article-title":"More diverse means better: Multimodal deep learning meets remote-sensing imagery classification","volume":"59","author":"Hong","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"141627","DOI":"10.1109\/ACCESS.2019.2943604","article-title":"A comparison of loss weighting strategies for multi task learning in deep neural networks","volume":"7","author":"Gong","year":"2019","journal-title":"IEEE Access"},{"key":"ref_36","first-page":"5505614","article-title":"HyperMLP: Superpixel prior and feature aggregated perceptron networks for hyperspectral and LiDAR hybrid classification","volume":"62","author":"Li","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"4939","DOI":"10.1109\/TGRS.2020.2969024","article-title":"Classification of Hyperspectral and LiDAR Data Using Coupled CNNs","volume":"58","author":"Hang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5514415","DOI":"10.1109\/TGRS.2023.3284671","article-title":"Extended Vision Transformer (ExViT) for Land Use and Land Cover Classification: A Multimodal Deep Learning Framework","volume":"61","author":"Yao","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.inffus.2022.12.020","article-title":"Coupled adversarial learning for fusion classification of hyperspectral and LiDAR data","volume":"93","author":"Lu","year":"2023","journal-title":"Inf. Fusion"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/6\/473\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:18:37Z","timestamp":1781147917000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/6\/473"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":39,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["a19060473"],"URL":"https:\/\/doi.org\/10.3390\/a19060473","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]}}}