Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field
Barnyard grass, a pernicious weed thriving in rice fields, poses a significant challenge to agricultural productivity. Detection of barnyard grass before the four-leaf stage is critical for effective control measures. However, due to their striking visual similarity, separating them from rice seedli...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2025.1507442/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206696270626816 |
|---|---|
| author | Siqiao Tan Qiang Xie Wenshuai Zhu Yangjun Deng Lei Zhu Xiaoqiao Yu Zheming Yuan Zheming Yuan Yuan Chen Yuan Chen |
| author_facet | Siqiao Tan Qiang Xie Wenshuai Zhu Yangjun Deng Lei Zhu Xiaoqiao Yu Zheming Yuan Zheming Yuan Yuan Chen Yuan Chen |
| author_sort | Siqiao Tan |
| collection | DOAJ |
| description | Barnyard grass, a pernicious weed thriving in rice fields, poses a significant challenge to agricultural productivity. Detection of barnyard grass before the four-leaf stage is critical for effective control measures. However, due to their striking visual similarity, separating them from rice seedlings at early growth stages is daunting using traditional visible light imaging models. To explore the feasibility of hyperspectral identification of barnyard grass and rice in the seedling stage, we have pioneered the DeepBGS hyperspectral feature parsing framework. This approach harnesses the power of deep convolutional networks to automate the extraction of pertinent information. Initially, a sliding window-based technique is employed to transform the one-dimensional spectral band sequence into a more interpretable two-dimensional matrix. Subsequently, a deep convolutional feature extraction module, ensembled with a bilayer LSTM module, is deployed to capture both global and local correlations inherent within hyperspectral bands. The efficacy of DeepBGS was underscored by its unparalleled performance in discriminating barnyard grass from rice during the critical 2-3 leaf stage, achieving a 98.18% accuracy rate. Notably, this surpasses the capabilities of other models that rely on amalgamations of machine learning algorithms and feature dimensionality reduction methods. By seamlessly integrating deep convolutional networks, DeepBGS independently extracts salient features, indicating that hyperspectral imaging technology can be used to effectively identify barnyard grass in the early stages, and pave the way for the development of advanced early detection systems. |
| format | Article |
| id | doaj-art-25afa6bf73fe467d83e2621c6a00ee1c |
| institution | Kabale University |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-25afa6bf73fe467d83e2621c6a00ee1c2025-02-07T06:49:56ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-02-011610.3389/fpls.2025.15074421507442Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy fieldSiqiao Tan0Qiang Xie1Wenshuai Zhu2Yangjun Deng3Lei Zhu4Xiaoqiao Yu5Zheming Yuan6Zheming Yuan7Yuan Chen8Yuan Chen9College of Information and Intelligent Science and Technology, Hunan Agricultural University, Changsha, Hunan, ChinaCollege of Information and Intelligent Science and Technology, Hunan Agricultural University, Changsha, Hunan, ChinaCollege of Plant Protection, Hunan Agricultural University, Changsha, Hunan, ChinaCollege of Information and Intelligent Science and Technology, Hunan Agricultural University, Changsha, Hunan, ChinaCollege of Information and Intelligent Science and Technology, Hunan Agricultural University, Changsha, Hunan, ChinaCollege of Plant Protection, Hunan Agricultural University, Changsha, Hunan, ChinaHunan Engineering and Technology Research Centre for Agricultural Big Data Analysis and Decision-Making, Hunan Agricultural University, Changsha, Hunan, ChinaEcological Simulation Breeding and Phenotype ldentification Platform, Yuelu Mountain Laboratory of Hunan Province, Changsha, Hunan, ChinaHunan Engineering and Technology Research Centre for Agricultural Big Data Analysis and Decision-Making, Hunan Agricultural University, Changsha, Hunan, ChinaEcological Simulation Breeding and Phenotype ldentification Platform, Yuelu Mountain Laboratory of Hunan Province, Changsha, Hunan, ChinaBarnyard grass, a pernicious weed thriving in rice fields, poses a significant challenge to agricultural productivity. Detection of barnyard grass before the four-leaf stage is critical for effective control measures. However, due to their striking visual similarity, separating them from rice seedlings at early growth stages is daunting using traditional visible light imaging models. To explore the feasibility of hyperspectral identification of barnyard grass and rice in the seedling stage, we have pioneered the DeepBGS hyperspectral feature parsing framework. This approach harnesses the power of deep convolutional networks to automate the extraction of pertinent information. Initially, a sliding window-based technique is employed to transform the one-dimensional spectral band sequence into a more interpretable two-dimensional matrix. Subsequently, a deep convolutional feature extraction module, ensembled with a bilayer LSTM module, is deployed to capture both global and local correlations inherent within hyperspectral bands. The efficacy of DeepBGS was underscored by its unparalleled performance in discriminating barnyard grass from rice during the critical 2-3 leaf stage, achieving a 98.18% accuracy rate. Notably, this surpasses the capabilities of other models that rely on amalgamations of machine learning algorithms and feature dimensionality reduction methods. By seamlessly integrating deep convolutional networks, DeepBGS independently extracts salient features, indicating that hyperspectral imaging technology can be used to effectively identify barnyard grass in the early stages, and pave the way for the development of advanced early detection systems.https://www.frontiersin.org/articles/10.3389/fpls.2025.1507442/fullhyperspectral featuresricebarnyard grassconvolutional neural networkDeepBGSsliding window |
| spellingShingle | Siqiao Tan Qiang Xie Wenshuai Zhu Yangjun Deng Lei Zhu Xiaoqiao Yu Zheming Yuan Zheming Yuan Yuan Chen Yuan Chen Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field Frontiers in Plant Science hyperspectral features rice barnyard grass convolutional neural network DeepBGS sliding window |
| title | Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field |
| title_full | Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field |
| title_fullStr | Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field |
| title_full_unstemmed | Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field |
| title_short | Deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field |
| title_sort | deep learning and hyperspectral features for seedling stage identification of barnyard grass in paddy field |
| topic | hyperspectral features rice barnyard grass convolutional neural network DeepBGS sliding window |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2025.1507442/full |
| work_keys_str_mv | AT siqiaotan deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT qiangxie deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT wenshuaizhu deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT yangjundeng deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT leizhu deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT xiaoqiaoyu deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT zhemingyuan deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT zhemingyuan deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT yuanchen deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield AT yuanchen deeplearningandhyperspectralfeaturesforseedlingstageidentificationofbarnyardgrassinpaddyfield |