A study on the identification of wheat powdery mildew using chlorophyll fluorescence imaging
- 1School of Geomatics and Aerospace Information, Henan Polytechnic University, Jiaozuo, China
- 2Observation and Research Station of Land Ecology and Land Use in the Grain-Producing Area of Central China, Ministry of Natural Resources, Jiaozuo, China
Abstract
Introduction: Wheat powdery mildew poses a serious threat to global wheat production, and its accurate identification is key to smart agriculture.
Methods: This study combines chlorophyll fluorescence imaging with deep learning algorithms to investigate the temporal dynamics of key fluorescence parameters (such as maximum photochemical efficiency, QYmax) during the progression of powderymildew. A QYmax-based chlorophyll fluorescence image dataset for wheat powdery mildew was constructed. Building on this, the LCRNet model was proposed, which effectively processes fluorescence image data through a collaborative mechanism integrating the Large Selective Adaptive Fusion (LSAF) and Coordinated Attention (CA) modules.
Results: On an independent test set, the model achieved an accuracy of 94% and an F1 score of 94.1%, outperforming comparison models.
Discussion: This study proposes a method for classifying the severity of powdery mildew in wheat that reduces the computational cost of fluorescence data processing, providing important methodological support and technical insights for advancing the intelligent, precise, and green transformation of crop disease prevention and control systems.
Related
- CRISPR-Cas9 Editing of Grapevine Clade V-Related MLO Genes: Grapevine Powdery Mildew Resistance (Erysiphe necator) and Plant Development Effects
- Genome-Wide Association and Genomic Prediction of Powdery Mildew and CYSDV Resistance in Melon
- Molecular Cytogenetic and Transcriptome Characterization of a Novel Wheat-Thinopyrum intermedium 2J(2D) Disomic Substitution Line with Resistance to Powdery Mildew
- Effector-host networks in the barley powdery mildew pathosystem reveal significant targeting of ubiquitin-associated proteins and transcriptional regulators
- Integrated Multi-Omics Analysis of the Response of Lycium barbarum ‘Ningqi-1’ to Powdery Mildew Infection and Functional Characterization of LbMLO6
BibTeX
@article{chen2026study,
title = {{A study on the identification of wheat powdery mildew using chlorophyll fluorescence imaging}},
author = {Yijia Chen and Chengyuan Hao and Zhiyu Li and Xupeng An and Jingxiang Huang and Xinchang Chen and Shidong Wang and Zhichao Chen},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1837843},
url = {https://doi.org/10.3389/fpls.2026.1837843},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A study on the identification of wheat powdery mildew using chlorophyll fluorescence imaging
AU - Yijia Chen
AU - Chengyuan Hao
AU - Zhiyu Li
AU - Xupeng An
AU - Jingxiang Huang
AU - Xinchang Chen
AU - Shidong Wang
AU - Zhichao Chen
PY - 2026
DA - 2026/10/12
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1837843
UR - https://doi.org/10.3389/fpls.2026.1837843
AB - Introduction: Wheat powdery mildew poses a serious threat to global wheat production, and its accurate identification is key to smart agriculture. Methods: This study combines chlorophyll fluorescence imaging with deep learning algorithms to investigate the temporal dynamics of key fluorescence parameters (such as maximum photochemical efficiency, QYmax) during the progression of powderymildew. A QYmax-based chlorophyll fluorescence image dataset for wheat powdery mildew was constructed. Building on this, the LCRNet model was proposed, which effectively processes fluorescence image data through a collaborative mechanism integrating the Large Selective Adaptive Fusion (LSAF) and Coordinated Attention (CA) modules. Results: On an independent test set, the model achieved an accuracy of 94% and an F1 score of 94.1%, outperforming comparison models. Discussion: This study proposes a method for classifying the severity of powdery mildew in wheat that reduces the computational cost of fluorescence data processing, providing important methodological support and technical insights for advancing the intelligent, precise, and green transformation of crop disease prevention and control systems.
SN - 1664-462X
ER -