{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T18:13:57Z","timestamp":1788200037983,"version":"build-2803163510"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Huzhou Natural Science Foundation Project","award":["2024YZ27"],"award-info":[{"award-number":["2024YZ27"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Effective monitoring of desert rangeland ecosystems is of crucial significance to regional ecological security. Unmanned aerial vehicle (UAV) hyperspectral remote sensing provides an effective means for the fine identification of vegetation species. However, in practical applications, vegetation classification using hyperspectral images often faces the problem of limited labeled samples, which makes it difficult for traditional deep learning methods to obtain stable and accurate classification results. To address these issues, this study proposes a meta-learning with Mamba (MetaMamba) method for vegetation classification in desert rangeland. This method constructs a local-global dual-branch structure in the feature extraction stage to achieve effective fusion of local and global spatial context information. Specifically, the local branch uses convolutional neural networks (CNNs) to extract fine-grained spatial features, while the global branch models long-distance spatial dependencies based on the Mamba model. Additionally, a meta-learning strategy is introduced to enhance the feature learning and generalization abilities of the model under few-shot conditions. Experimental results show that the proposed method outperforms existing methods across multiple evaluation metrics. The overall classification accuracy (OA) reaches 90.85%, the average accuracy (AA) reaches 91.67%, and the Kappa coefficient reaches 87.77%. The method shows good stability and adaptability under different sample sizes. The MetaMamba model can achieve high-precision classification of desert rangeland vegetation species under few-shot conditions, providing an effective technical approach for ecological monitoring and rangeland resource management.<\/jats:p>","DOI":"10.1371\/journal.pone.0352744","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T17:24:32Z","timestamp":1788197072000},"page":"e0352744","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["MetaMamba: Meta-learning with mamba for few-shot vegetation species classification using UAV-based hyperspectral imagery in desert rangeland"],"prefix":"10.1371","volume":"21","author":[{"given":"Fei","family":"Hao","sequence":"first","affiliation":[{"name":"Hohhot Polytechnic University","place":["Hohhot, Inner Mongolia, China"],"department":["Intelligent Manufacturing College"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinchao","family":"Gao","sequence":"additional","affiliation":[{"name":"Hebei Petroleum University of Technology","place":["Chengde, Hebei, China"],"department":["College of Mechanical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6643-013X","authenticated-orcid":true,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inner Mongolia Agricultural University","place":["Hohhot, Inner Mongolia, China"],"department":["College of Mechanical and Electrical Engineering"]},{"name":"Guiyang University","place":["Guiyang, Guizhou, China"],"department":["School of Mechanical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianmin","family":"Du","sequence":"additional","affiliation":[{"name":"Inner Mongolia Agricultural University","place":["Hohhot, Inner Mongolia, China"],"department":["College of Mechanical and Electrical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengli","family":"Wang","sequence":"additional","affiliation":[{"name":"Inner Mongolia Agricultural University","place":["Hohhot, Inner Mongolia, China"],"department":["College of Mechanical and Electrical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"He","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China","place":["Huzhou, Zhejiang, China"],"department":["Yangtze Delta Region Institute (Huzhou)"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"pone.0352744.ref001","doi-asserted-by":"crossref","first-page":"101278","DOI":"10.1016\/j.ecoinf.2021.101278","article-title":"3D-CNN based UAV hyperspectral imagery for grassland degradation indicator ground object classification research","volume":"62","author":"W Pi","year":"2021","journal-title":"Ecol Inform"},{"key":"pone.0352744.ref002","doi-asserted-by":"crossref","first-page":"127411","DOI":"10.1016\/j.eswa.2025.127411","article-title":"ResMamba: A state\u2013space model approach and benchmark dataset for precise forage identification in desert rangelands","volume":"280","author":"T Zhang","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"pone.0352744.ref003","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/grs.12379","article-title":"Research on deep learning method recognition and a classification model of grassland grass species based on unmanned aerial vehicle hyperspectral remote sensing","volume":"69","author":"X Zhu","year":"2022","journal-title":"Grassl Sci"},{"key":"pone.0352744.ref004","doi-asserted-by":"crossref","first-page":"103663","DOI":"10.1016\/j.ecoinf.2026.103663","article-title":"UAV-based remote sensing for rangeland monitoring, a generalized and transparent workflow with an Australian lead","volume":"94","author":"TA Soomro","year":"2026","journal-title":"Ecol Inform"},{"issue":"3","key":"pone.0352744.ref005","doi-asserted-by":"crossref","first-page":"485","DOI":"10.3390\/land15030485","article-title":"Grassland Productivity and Ewes\u2019 Forage Intake Monitoring by Combined Multispectral Vegetation Indices and Machine Learning Approaches for Precision Grazing Management","volume":"15","author":"P Caparra","year":"2026","journal-title":"Land"},{"issue":"4","key":"pone.0352744.ref006","doi-asserted-by":"crossref","first-page":"655","DOI":"10.3390\/rs18040655","article-title":"Transferring RGB-Pretrained CNNs to Multispectral UAV Imagery for Salt Marsh Vegetation Classification","volume":"18","author":"SO Macaulay","year":"2026","journal-title":"Remote Sensing"},{"key":"pone.0352744.ref007","doi-asserted-by":"crossref","first-page":"111001","DOI":"10.1016\/j.compag.2025.111001","article-title":"Cross-domain adversarial learning for forage mapping and alpha-diversity assessment from UAV hyperspectral imagery in desert rangelands","volume":"239","author":"T Zhang","year":"2025","journal-title":"Comput Electron Agr"},{"issue":"4","key":"pone.0352744.ref008","article-title":"Estimation of soil salt content in the oasis tillage layer based on hyperspectral transformation and model combination","volume":"21","author":"Y Guo","year":"2026","journal-title":"PLoS One"},{"issue":"22","key":"pone.0352744.ref009","doi-asserted-by":"crossref","first-page":"12245","DOI":"10.3390\/app132212245","article-title":"The unmanned aerial vehicle (UAV)-based hyperspectral classification of desert grassland plants in Inner Mongolia, China","volume":"13","author":"S Wang","year":"2023","journal-title":"Appl Sci-Basel"},{"issue":"5","key":"pone.0352744.ref010","article-title":"Research on multi-sensor fusion architecture for highway area hazard monitoring based on UAVs","volume":"21","author":"H Wu","year":"2026","journal-title":"PLoS One"},{"issue":"1","key":"pone.0352744.ref011","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1007\/s11063-021-10632-5","article-title":"PCA Dimensionality Reduction Method for Image Classification","volume":"54","author":"B Zhao","year":"2021","journal-title":"Neural Process Lett"},{"key":"pone.0352744.ref012","doi-asserted-by":"crossref","first-page":"100694","DOI":"10.1016\/j.rsase.2022.100694","article-title":"Classification of hyperspectral remote sensing images using different dimension reduction methods with 3D\/2D CNN","volume":"25","author":"H F\u0131rat","year":"2022","journal-title":"Remote Sensing Applications: Society and Environment"},{"key":"pone.0352744.ref013","doi-asserted-by":"crossref","first-page":"1711972","DOI":"10.3389\/fpls.2025.1711972","article-title":"Identification of tobacco leaf diseases using hyperspectral imaging and machine learning with SHAP interpretability analysis","volume":"16","author":"P Luo","year":"2026","journal-title":"Front Plant Sci"},{"issue":"4","key":"pone.0352744.ref014","doi-asserted-by":"crossref","first-page":"486","DOI":"10.3390\/agriculture16040486","article-title":"ViaNet: Interpretable and Lightweight Deep Hyperspectral Classification of Pepper Seed Viability","volume":"16","author":"L Zhu","year":"2026","journal-title":"Agriculture"},{"key":"pone.0352744.ref015","doi-asserted-by":"crossref","first-page":"1692649","DOI":"10.3389\/fpls.2026.1692649","article-title":"LightWaveNet: a lightweight wavelet-enhanced high-low-frequency-aware network with multi-stage supervision for rice disease recognition","volume":"17","author":"W Pi","year":"2026","journal-title":"Front Plant Sci"},{"issue":"2","key":"pone.0352744.ref016","doi-asserted-by":"crossref","first-page":"37","DOI":"10.3390\/jimaging11020037","article-title":"Semantic-Guided Transformer Network for Crop Classification in Hyperspectral Images","volume":"11","author":"W Pi","year":"2025","journal-title":"J Imaging"},{"issue":"20","key":"pone.0352744.ref017","doi-asserted-by":"crossref","first-page":"7587","DOI":"10.1080\/01431161.2025.2557586","article-title":"Lightweight deep learning with spatial-spectral feature optimization for UAV hyperspectral monitoring of grassland degradation","volume":"46","author":"S Wang","year":"2025","journal-title":"International Journal of Remote Sensing"},{"key":"pone.0352744.ref018","doi-asserted-by":"crossref","first-page":"111386","DOI":"10.1016\/j.compag.2025.111386","article-title":"Cross-task collaborative learning for aboveground biomass estimation from UAV hyperspectral imagery in sample-scarce desert rangelands","volume":"243","author":"T Zhang","year":"2026","journal-title":"Comput Electron Agr"},{"issue":"5","key":"pone.0352744.ref019","doi-asserted-by":"crossref","first-page":"696","DOI":"10.3390\/rs18050696","article-title":"Local Climate Zone Mapping by Integrating Hyperspectral and Multispectral Data with a Spectral\u2013Spatial Fusion Network","volume":"18","author":"X Liu","year":"2026","journal-title":"Remote Sensing"},{"key":"pone.0352744.ref020","doi-asserted-by":"crossref","first-page":"4559","DOI":"10.1109\/JSTARS.2026.3653391","article-title":"Dual-Branch Prototype Enhancement Network for Few-Shot Hyperspectral Image Classification","volume":"19","author":"K Li","year":"2026","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"},{"issue":"4","key":"pone.0352744.ref021","doi-asserted-by":"crossref","first-page":"2290","DOI":"10.1109\/TGRS.2018.2872830","article-title":"Deep Few-Shot Learning for Hyperspectral Image Classification","volume":"57","author":"B Liu","year":"2019","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0352744.ref022","doi-asserted-by":"crossref","first-page":"4748","DOI":"10.1109\/JSTARS.2020.3017544","article-title":"Global Prototypical Network for Few-Shot Hyperspectral Image Classification","volume":"13","author":"C Zhang","year":"2020","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"},{"issue":"6","key":"pone.0352744.ref023","doi-asserted-by":"crossref","first-page":"923","DOI":"10.3390\/rs12060923","article-title":"Deep Relation Network for Hyperspectral Image Few-Shot Classification","volume":"12","author":"K Gao","year":"2020","journal-title":"Remote Sensing"},{"key":"pone.0352744.ref024","first-page":"1","article-title":"Deep Cross-Domain Few-Shot Learning for Hyperspectral Image Classification","volume":"60","author":"Z Li","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"pone.0352744.ref025","first-page":"1","article-title":"RSMamba: Remote Sensing Image Classification With State Space Model","volume":"21","author":"K Chen","year":"2024","journal-title":"IEEE Geosci Remote Sensing Lett"},{"key":"pone.0352744.ref026","first-page":"1","article-title":"MambaHSI: Spatial\u2013Spectral Mamba for Hyperspectral Image Classification","volume":"62","author":"Y Li","year":"2024","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0352744.ref027","first-page":"1","article-title":"IGroupSS-Mamba: Interval Group Spatial\u2013Spectral Mamba for Hyperspectral Image Classification","volume":"62","author":"Y He","year":"2024","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0352744.ref028","doi-asserted-by":"crossref","first-page":"114531","DOI":"10.1016\/j.knosys.2025.114531","article-title":"Few-Shot hyperspectral image classification with mamba and manifold convolution fusion network","volume":"330","author":"H Cao","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"pone.0352744.ref029","unstructured":"Gu A, Dao T. Mamba: linear-time sequence modeling with selective state spaces. In: Philadelphia, Pennsylvania, USA, 2024. 1\u201336."},{"key":"pone.0352744.ref030","doi-asserted-by":"crossref","first-page":"9393","DOI":"10.1109\/JSTARS.2026.3670851","article-title":"Center-Guided Dynamic Convolutional Network for Hyperspectral Image Classification","volume":"19","author":"Z Zhang","year":"2026","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"},{"issue":"6","key":"pone.0352744.ref031","doi-asserted-by":"crossref","first-page":"2109","DOI":"10.1080\/01431161.2024.2326042","article-title":"Convolutional transformer attention network with few-shot learning for grassland degradation monitoring using UAV hyperspectral imagery","volume":"45","author":"T Zhang","year":"2024","journal-title":"International Journal of Remote Sensing"},{"key":"pone.0352744.ref032","doi-asserted-by":"crossref","first-page":"109838","DOI":"10.1016\/j.compag.2024.109838","article-title":"An efficient and precise dynamic neighbor graph network for crop mapping using unmanned aerial vehicle hyperspectral imagery","volume":"230","author":"T Zhang","year":"2025","journal-title":"Comput Electron Agr"},{"key":"pone.0352744.ref033","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2026.3652369","article-title":"Spatial-Frequency Joint Learning Mamba for Hyperspectral Image Classification","volume":"23","author":"Z Meng","year":"2026","journal-title":"IEEE Geosci Remote Sensing Lett"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T17:24:39Z","timestamp":1788197079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352744"}},"subtitle":[],"editor":[{"given":"Yaseen","family":"Al-Mulla","sequence":"first","affiliation":[{"name":"Sultan Qaboos University","place":["OMAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":33,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0352744","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]}}}