AUTHOR=Weng Shizhuang , Ma Junjie , Tao Wentao , Tan Yujian , Pan Meijing , Zhang Zixi , Huang Linsheng , Zheng Ling , Zhao Jinling 

TITLE=Drought stress identification of tomato plant using multi-features of hyperspectral imaging and subsample fusion

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1073530

DOI=10.3389/fpls.2023.1073530

ISSN=1664-462X

ABSTRACT=Detecting tomato plant drought stress (DS) is of great significance for optimizing irrigation and improving fruit quality. In this study, a DS identification method using the multi-features of hyperspectral imaging (HSI) and subsample fusion was proposed. First, the high-quality HSI images were measured by supplementing blue lights to remove high-frequency noise. The reflectance spectra were extracted from the HSI images of young and mature leaves at different DS levels (well-watered, reduced-watered, and deficient-watered treatment), and effective wavelengths (EWs) were screened by genetic algorithm. Second, the reference image was determined by ReliefF, and the first four reflectance images of EWs that are weakly correlated with the reference image and mutually irrelevant are obtained using Pearson’s correlation analysis. The reflectance image set (RIS) was determined by evaluating the effects of different combinations of successively increasing above reflectance image on identification. The spectra of EWs and the image features extracted from RIS by LeNet-5 were adopted to construct DS identification models based on support vector machine (SVM), random forest, and dense convolutional network. Third, subsample fusion integrating the spectra and image features of young and mature leaves was used to further improve the identification. Global optimal classification performance was achieved by SVM and subsample fusion with a classification accuracy of 95.90% and 95.78% for calibration and prediction sets, respectively. Overall, the proposed method can provide an accurate and reliable analysis for tomato plant DS and will hopefully be applied to other crop stresses.