CMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agriculture

Abstract Hyperspectral imaging acquired from unmanned aerial vehicles (UAVs) offers detailed spectral and spatial data that holds transformative potential for precision agriculture applications, such as crop classification, health monitoring, and yield estimation. However, traditional methods strugg...

Full description

Saved in:
Bibliographic Details
Main Authors: Xihong Guo, Quan Feng, Faxu Guo
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-97052-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849726222830927872
author Xihong Guo
Quan Feng
Faxu Guo
author_facet Xihong Guo
Quan Feng
Faxu Guo
author_sort Xihong Guo
collection DOAJ
description Abstract Hyperspectral imaging acquired from unmanned aerial vehicles (UAVs) offers detailed spectral and spatial data that holds transformative potential for precision agriculture applications, such as crop classification, health monitoring, and yield estimation. However, traditional methods struggle to effectively capture both local and global features, particularly in complex agricultural environments with diverse crop types, varying growth stages, and imbalanced data distributions. To address these challenges, we propose CMTNet, an innovative deep learning framework that integrates convolutional neural networks (CNNs) and Transformers for hyperspectral crop classification. The model combines a spectral-spatial feature extraction module to capture shallow features, a dual-branch architecture that extracts both local and global features simultaneously, and a multi-output constraint module to enhance classification accuracy through cross-constraints among multiple feature levels. Extensive experiments were conducted on three UAV-acquired datasets: WHU-Hi-LongKou, WHU-Hi-HanChuan, and WHU-Hi-HongHu. The experimental results demonstrate that CMTNet achieved overall accuracy (OA) values of 99.58%, 97.29%, and 98.31% on these three datasets, surpassing the current state-of-the-art method (CTMixer) by 0.19% (LongKou), 1.75% (HanChuan), and 2.52% (HongHu) in OA values, respectively. These findings indicate its superior potential for UAV-based agricultural monitoring in complex environments. These results advance the precision and reliability of hyperspectral crop classification, offering a valuable solution for precision agriculture challenges.
format Article
id doaj-art-e4931fb8f7c84a0cbbbf226e783f2990
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e4931fb8f7c84a0cbbbf226e783f29902025-08-20T03:10:14ZengNature PortfolioScientific Reports2045-23222025-04-0115111810.1038/s41598-025-97052-wCMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agricultureXihong Guo0Quan Feng1Faxu Guo2Dingxi Sanniu Agricultural Machinery Manufacturing Co., Ltd.College of Mechanical and Electrical Engineering, Gansu Agriculture UniversityCollege of Mechanical and Electrical Engineering, Gansu Agriculture UniversityAbstract Hyperspectral imaging acquired from unmanned aerial vehicles (UAVs) offers detailed spectral and spatial data that holds transformative potential for precision agriculture applications, such as crop classification, health monitoring, and yield estimation. However, traditional methods struggle to effectively capture both local and global features, particularly in complex agricultural environments with diverse crop types, varying growth stages, and imbalanced data distributions. To address these challenges, we propose CMTNet, an innovative deep learning framework that integrates convolutional neural networks (CNNs) and Transformers for hyperspectral crop classification. The model combines a spectral-spatial feature extraction module to capture shallow features, a dual-branch architecture that extracts both local and global features simultaneously, and a multi-output constraint module to enhance classification accuracy through cross-constraints among multiple feature levels. Extensive experiments were conducted on three UAV-acquired datasets: WHU-Hi-LongKou, WHU-Hi-HanChuan, and WHU-Hi-HongHu. The experimental results demonstrate that CMTNet achieved overall accuracy (OA) values of 99.58%, 97.29%, and 98.31% on these three datasets, surpassing the current state-of-the-art method (CTMixer) by 0.19% (LongKou), 1.75% (HanChuan), and 2.52% (HongHu) in OA values, respectively. These findings indicate its superior potential for UAV-based agricultural monitoring in complex environments. These results advance the precision and reliability of hyperspectral crop classification, offering a valuable solution for precision agriculture challenges.https://doi.org/10.1038/s41598-025-97052-wHyperspectral imagingCrop classificationMulti-output feature constraintsConvolutional neural networksTransformer
spellingShingle Xihong Guo
Quan Feng
Faxu Guo
CMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agriculture
Scientific Reports
Hyperspectral imaging
Crop classification
Multi-output feature constraints
Convolutional neural networks
Transformer
title CMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agriculture
title_full CMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agriculture
title_fullStr CMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agriculture
title_full_unstemmed CMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agriculture
title_short CMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agriculture
title_sort cmtnet a hybrid cnn transformer network for uav based hyperspectral crop classification in precision agriculture
topic Hyperspectral imaging
Crop classification
Multi-output feature constraints
Convolutional neural networks
Transformer
url https://doi.org/10.1038/s41598-025-97052-w
work_keys_str_mv AT xihongguo cmtnetahybridcnntransformernetworkforuavbasedhyperspectralcropclassificationinprecisionagriculture
AT quanfeng cmtnetahybridcnntransformernetworkforuavbasedhyperspectralcropclassificationinprecisionagriculture
AT faxuguo cmtnetahybridcnntransformernetworkforuavbasedhyperspectralcropclassificationinprecisionagriculture