Fusarium head blight monitoring in wheat ears using machine learning and multimodal data from asymptomatic to symptomatic periods

Ghulam Mustafa; Hengbiao Zheng; Wei Li; Yuming Yin; Yongqing Wang; Meng Zhou; Peng Liu; Muhammad Bilal; Haiyan Jia; Guoqiang Li; Tao Cheng; Yongchao Tian; Weixing Cao; Yan Zhu; Xia Yao

doi:10.3389/fpls.2022.1102341

Fusarium head blight monitoring in wheat ears using machine learning and multimodal data from asymptomatic to symptomatic periods

Front Plant Sci. 2023 Jan 16:13:1102341. doi: 10.3389/fpls.2022.1102341. eCollection 2022.

Authors

Ghulam Mustafa^{1

2}, Hengbiao Zheng^{1

2}, Wei Li^{1

2}, Yuming Yin^{1

2}, Yongqing Wang^{1

2}, Meng Zhou^{1

2}, Peng Liu^{1

2}, Muhammad Bilal^{1

2}, Haiyan Jia³, Guoqiang Li³, Tao Cheng^{1

2}, Yongchao Tian^{1

2}, Weixing Cao^{1

2}, Yan Zhu^{1

2}, Xia Yao^{1

2}

Affiliations

¹ National Engineering and Technology Center for Information Agriculture, Key Laboratory for Crop System Analysis and Decision Making, Ministry of Agriculture, Jiangsu Collaborative Innovation Center for Modern Crop Production, Nanjing Agricultural University, Nanjing, China.
² National Engineering and Technology Center for Information Agriculture, Jiangsu Key Laboratory for Information Agriculture, Ministry of Agriculture, Jiangsu Collaborative Innovation Center for Modern Crop Production, Nanjing Agricultural University, Nanjing, China.
³ Crop Genomics and Bioinformatics Center and National Key Laboratory of Crop Genetics and Germplasm Enhancement, Nanjing Agricultural University, Nanjing, Jiangsu, China.

Abstract

The growth of the fusarium head blight (FHB) pathogen at the grain formation stage is a deadly threat to wheat production through disruption of the photosynthetic processes of wheat spikes. Real-time nondestructive and frequent proxy detection approaches are necessary to control pathogen propagation and targeted fungicide application. Therefore, this study examined the ch\lorophyll-related phenotypes or features from spectral and chlorophyll fluorescence for FHB monitoring. A methodology is developed using features extracted from hyperspectral reflectance (HR), chlorophyll fluorescence imaging (CFI), and high-throughput phenotyping (HTP) for asymptomatic to symptomatic disease detection from two consecutive years of experiments. The disease-sensitive features were selected using the Boruta feature-selection algorithm, and subjected to machine learning-sequential floating forward selection (ML-SFFS) for optimum feature combination. The results demonstrated that the biochemical parameters, HR, CFI, and HTP showed consistent alterations during the spike-pathogen interaction. Among the selected disease sensitive features, reciprocal reflectance (RR=1/700) demonstrated the highest coefficient of determination (R ²) of 0.81, with root mean square error (RMSE) of 11.1. The multivariate k-nearest neighbor model outperformed the competing multivariate and univariate models with an overall accuracy of R ² = 0.92 and RMSE = 10.21. A combination of two to three kinds of features was found optimum for asymptomatic disease detection using ML-SFFS with an average classification accuracy of 87.04% that gradually improved to 95% for a disease severity level of 20%. The study demonstrated the fusion of chlorophyll-related phenotypes with the ML-SFFS might be a good choice for crop disease detection.

Keywords: asymptomatic detection; disease estimation; fusarium head blight; machine learning classifier; multimodal data; sequential floating forward selection.

Grants and funding

This work was supported by the National Key R&D Program of China (2021YFD2000101), the Jiangsu Agricultural Science and Technology Innovation Fund (CX(22)3201), the Key Projects (Advanced Technology) of Jiangsu Province (BE 2019383), and Jiangsu Collaborative Innovation Center for Modern Crop Production (JCICMCP).