Research Article | Open Access

Volume 2025 |Article ID 100038 | https://doi.org/10.1016/j.plaphe.2025.100038

Rapid diagnosis of herbicidal activity and mode of action using spectral image analysis and machine learning

Tae-Kyeong Noh,¹ Min-Jung Yook,¹ Taek-Sung Lee,² Do-Soon Kim ^1,3

¹Department of Agriculture, Forestry and Bioresources, Research Institute of Agriculture and Life Sciences, College of Agriculture and Life Sciences, Seoul National University, Seoul, Republic of Korea
²Smart Farm Research Center, Korea Institute of Science and Technology, Gangneung, Republic of Korea
³Department of International Agricultural Technology, Graduate School of International Agricultural Technology, Seoul National University, Republic of Korea

Abstract

Herbicide screening requires a substantial amount of time, effort, and cost, making a new herbicide discovery expensive and time-consuming. Various diagnostic methods have been developed, but most of them are destructive and require significant time and effort to identify herbicide activity. Therefore, this study was conducted to apply spectral image analysis for early and rapid diagnosis of herbicidal activity and modes of action (MOAs). RGB, chlorophyll fluorescence (CF), and infrared (IR) thermal images were acquired after treating herbicides with different MOAs to a model plant, oilseed rape (Brassica napus), and analyzed using MATLAB 2021b to quantify NDI, ExG, Fd/Fm, and plant leaf temperature. NDI, ExG and Fd/Fm decreased, while plant leaf temperature increased after herbicide treatment. Distinctive spectral responses were found depending on the herbicide MOAs. PSII and PPO inhibitors showed rapid responses in IR thermal and CF images within 1 day after herbicide treatment. HPPD inhibitor showed a continuous decrease in Fd/Fm, while EPSPS inhibitor showed gradual changes in all spectral indices. Machine learning by Subspace Discriminant algorithm of spectral indices acquired at 6 h enabled the diagnosis of herbicide MOAs with 89.6 % accuracy, which gradually increased by adding new spectral indices acquired later time points until 3 DAT, when validation accuracy scored 100 %. The indices acquired at 6 h, and Fd/Fm and leaf temperature data were shown to contribute to higher accuracies of identifying herbicide MOAs. Overall test accuracy scored 87.5 %, verifying the possibility of diagnosing herbicide MOAs based on spectral indices. Therefore, we could conclude that herbicide activity and MOAs can be diagnosed by analyzing spectral images combined with machine learning, suggesting the possibility of high-throughput screening of herbicide MOAs using plant image analysis.