MetaMamba: Meta-learning with mamba for few-shot vegetation species classification using UAV-based hyperspectral imagery in desert rangeland
5 affiliations
- 1Intelligent Manufacturing College, Hohhot Polytechnic University, Hohhot, Inner Mongolia, China
- 2College of Mechanical Engineering, Hebei Petroleum University of Technology, Chengde, Hebei, China
- 3College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot, Inner Mongolia, China
- 4School of Mechanical Engineering, Guiyang University, Guiyang, Guizhou, China
- 5Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China, Huzhou, Zhejiang, China
Abstract
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.
Related
- Fine-grained hierarchical crop type classification from integrated hyperspectral EnMAP data and multispectral sentinel-2 time series: A large-scale dataset and dual-stream transformer method
- Riparian Tugai Forest Ecosystems of Azerbaijan: Vegetation Structure, Classification and Ecological Characteristics
- Vegetation cover change and classification-based zonation of Fanjing Mountain using google earth engine
- GCOM-C/SGLI ground-area-based chlorophyll content estimation: a computationally efficient algorithm free from LAI and vegetation classification
- A multimodal deep learning for rice crop health monitoring using vegetation index feature selection
BibTeX
@article{hao2026metamamba,
title = {{MetaMamba: Meta-learning with mamba for few-shot vegetation species classification using UAV-based hyperspectral imagery in desert rangeland}},
author = {Fei Hao and Xinchao Gao and Tao Zhang and Jianmin Du and Shengli Wang and Xiaoyan He},
journal = {PLOS One},
year = {2026},
month = aug,
doi = {10.1371/journal.pone.0352744},
url = {https://doi.org/10.1371/journal.pone.0352744},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - MetaMamba: Meta-learning with mamba for few-shot vegetation species classification using UAV-based hyperspectral imagery in desert rangeland
AU - Fei Hao
AU - Xinchao Gao
AU - Tao Zhang
AU - Jianmin Du
AU - Shengli Wang
AU - Xiaoyan He
PY - 2026
DA - 2026/08/31
JO - PLOS One
DO - 10.1371/journal.pone.0352744
UR - https://doi.org/10.1371/journal.pone.0352744
AB - 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.
SN - 1932-6203
ER -