数字农科院2.0

Spectroscopic detection of cotton Verticillium wilt by spectral feature selection and machine learning methods

文献类型： 外文期刊

作者： Li, Weinan;Liu, Lisen;Li, Jianing;Yang, Weiguang;Guo, Yang;Huang, Longyu;Yang, Zhaoen;Peng, Jun;Jin, Xiuliang;Lan, Yubin

作者机构：

关键词： Gossypium hirsutum;Verticillium dahliae;spectral feature;feature selection;disease detection

期刊名称： FRONTIERS IN PLANT SCIENCE

ISSN： 1664-462X

年卷期： 2025 年 16 卷

页码：

收录情况： SCIE（2025版）

摘要： Introduction Verticillium wilt is a severe soil-borne disease that affects cotton growth and yield. Traditional monitoring methods, which rely on manual investigation, are inefficient and impractical for large-scale applications. This study introduces a novel approach combining machine learning with feature selection to identify sensitive spectral features for accurate and efficient detection of cotton Verticillium wilt.Methods We conducted comprehensive hyperspectral measurements using handheld devices (350-2500 nm) to analyze cotton leaves in a controlled greenhouse environment and employed Unmanned Aerial Vehicle (UAV) hyperspectral imaging (400-995 nm) to capture canopy-level data in field conditions. The hyperspectral data were pre-processed to extract wavelet coefficients and spectral indices (SIs), enabling the derivation of disease-specific spectral features (DSSFs) through advanced feature selection techniques. Using these DSSFs, we developed detection models to assess both the incidence and severity of leaf damage by Verticillium wilt at the leaf scale and the incidence at the canopy scale. Initial analysis identified critical spectral reflectance bands, wavelet coefficients, and SIs that exhibited dynamic responses as the disease progressed.Results Model validation demonstrated that the incidence detection models at the leaf scale achieved a peak classification accuracy of 85.83%, which is about 10% higher than traditional methods without feature selection. The severity detection models showed improved precision as disease severity of damage increased, with accuracy ranging from 46.82% to 93.10%. At the canopy scale, UAV-based hyperspectral data achieved a remarkable classification accuracy of 93.0% for disease incidence detection.Discussion This study highlights the significant impact of feature selection on enhancing the performance of hyperspectral-based remote sensing models for cotton wilt monitoring. It also explores the transferability of sensitive spectral features across different scales, laying the groundwork for future large-scale early warning systems and monitoring cotton Verticillium wilt.

分类号：

  • 相关文献

[1]Comparative expression analysis in susceptible and resistant Gossypium hirsutum responding to Verticillium dahliae infection by cDNA-AFLP. Wang, Sheng-Zheng,Liu, Kai,Si, Ning,Qi, Fang-Jun,Jian, Gui-Liang.

[2]Cotton gene expression profiles in resistant Gossypium hirsutum cv. Zhongzhimian KV1 responding to Verticillium dahliae strain V991 infection. Jian, Gui-Liang,Jiang, Teng-Fei,Wang, Sheng-Zheng,Qi, Fang-Jun,Xu, Shi-Chang.

[3]Colonization in cotton plants by a green fluorescent protein labelled strain of Verticillium dahliae. Jiang, Teng-Fei,Cui, Xiao,Qi, Fang-Jun,Jian, Gui-Liang.

[4]Generation of transcriptome profiling and gene functional analysis in Gossypium hirsutum upon Verticillium dahliae infection. Zhang, Huachong,Qi, Fangjun,Jian, Guiliang.

[5]The genes involved in the protective effects of phytohormones in response to Verticillium dahliae infection in Gossypium hirsutum. Zhang, Wenwei,Jian, Guiliang,Qi, Fangjun,Si, Ning.

[6]Influence of plant genotype and soil on the cotton rhizosphere microbiome. Chuanzhen Yang,Hongchen Yue,Zheng Ma,Zili Feng,Hongjie Feng,Lihong Zhao,Yalin Zhang,Greg Deakin,Xiangming Xu,Heqin Zhu,Feng Wei. 2022

[7]Long Non-Coding RNAs profiling in pathogenesis of Verticillium dahliae: New insights in the host-pathogen interaction. Nana Liu,Ping Wang,Xiancai Li,Yakun Pei,Yun Sun,Xiaowen Ma,Xiaoyang Ge,Yutao Zhu,Fuguang Li,Yuxia Hou. 2022

[8]Cotton miR393-TIR1 Module Regulates Plant Defense Against Verticillium dahliae via Auxin Perception and Signaling. Shi, Gege,Wang, Saisai,Wang, Peng,Zhan, Jingjing,Tang, Ye,Zhao, Ge,Li, Fuguang,Ge, Xiaoyang,Wu, Jiahe. 2022

[9]GhODO1, an R2R3-type MYB transcription factor, positively regulates cotton resistance to Verticillium dahliae via the lignin biosynthesis and jasmonic acid signaling pathway. Yutao Zhu,Xiaoqian Hu,Ping Wang,Hongwei Wang,Xiaoyang Ge,Fuguang Li,Yuxia Hou. 2022

[10]The cotton miR530-SAP6 module activated by systemic acquired resistance mediates plant defense against Verticillium dahliae. Guang Hu,Bingting Wang,Pei Jia,Pan Wu,Chengzhe Lu,Yunjiao Xu,Linfang Shi,Feiyan Zhang,Naiqin Zhong,Aimin Chen,Jiahe Wu. 2023

[11]The phospholipase D gene GhPLDδ confers resistance to Verticillium dahliae and improves tolerance to salt stress. Yutao Zhu,Xiaoqian Hu,Ping Wang,Hongwei Wang,Xiaoyang Ge,Fuguang Li,Yuxia Hou. 2022

[12]The cotton MYB33 gene is a hub gene regulating the trade-off between plant growth and defense in Verticillium dahliae infection. Hu Guang,Ge Xiaoyang,Wang Zhian,Wang Ye,Wang Peng,Shi Linfang,Wang Bingting,Zhang Anhong,Li Fuguang,Wu Jiahe. 2024

[13]Cotton RSG2 Mediates Plant Resistance against Verticillium dahliae by miR482b Regulation. Wu, Pan,Lu, Chengzhe,Wang, Bingting,Zhang, Feiyan,Shi, Linfang,Xu, Yunjiao,Chen, Aimin,Si, Huaijun,Su, Junji,Wu, Jiahe. 2023

[14]GhWRKY55 as a negative regulator of cotton resistance to Verticillium dahliae via lignin biosynthetic and jasmonic acid signaling pathways. Xueyuan Ma,Bin Chen,Li Yang,Rui Hao,Xingxing Wang,Guanjing Hu,Xianpeng Xiong. 2024

[15]Verticillium dahliae Elicitor VdSP8 Enhances Disease Resistance Through Increasing Lignin Biosynthesis in Cotton. Wang, Yajuan,Qin, Jun,Wei, Mengmeng,Liao, Xiwen,Shang, Wenjing,Chen, Jieyin,Subbarao, Krishna V.,Hu, Xiaoping. 2024

[16]陆地棉开花相关基因GhFLP1的克隆与功能验证. 张盼,范术丽,宋美珍,庞朝友,魏恒玲,喻树迅. 2016

[17]Estimation of Aboveground Biomass of Potatoes Based on Characteristic Variables Extracted from UAV Hyperspectral Imagery. Liu, Yang,Feng, Haikuan,Yue, Jibo,Li, Zhenhai,Jin, Xiuliang,Fan, Yiguang,Feng, Zhihang,Yang, Guijun. 2022

[18]An improved YOLOv5 model based on visual attention mechanism: Application to recognition of tomato virus disease. Jiangtao Qi,Xiangnan Liu,Kai Liu,Farong Xu,Hui Guo,Xinliang Tian,Mao Li,Zhiyuan Bao,Yang Li. 2022

[19]Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection. Jiayu Zhang,Chao Qi,Peter Mecha,Yi Zuo,Zongyou Ben,Haolu Liu,Kunjie Chen. 2022

[20]Xoo-YOLO: a detection method for wild rice bacterial blight in the field from the perspective of unmanned aerial vehicles. Pan Pan,Wenlong Guo,Xiaoming Zheng,Lin Hu,Guomin Zhou,Jianhua Zhang. 2023

作者其他论文 更多>>