Integrating non-invasive VIS-NIR and bioimpedance spectroscopies for stress classification of sweet basil (Ocimum basilicum L.) with machine learning

Plant stress diagnosis is essential for efficient crop management and productivity increase. Under stress, plants undergo physiological and compositional changes. Vegetation indices obtained from leaf reflectance spectra and bioimpedance spectroscopy provide information about the external and internal aspects of plant responses, respectively. In this study, bioimpedance and vegetation indices were noninvasively acquired from sweet basil (Ocimum basilicum L.) leaves exposed to three types of stress (drought, salinity, and chilling). Integrating the vegetation index, a novel approach, contains information about the surface of plants and bioimpedance data, which indicates the internal changes of plants. The fusion of these two datasets was examined to classify the types and severity of stress. Among the eight supervised machine learning models (three linear and five non-linear), the support vector machine (SVM) exhibited the highest accuracy in classifying stress types. Bioimpedance spectroscopy alone exhibited an accuracy of 0.86 and improved to 0.90 when fused with vegetation indices. Additionally, for drought and salinity stresses, it was possible to classify the early stage of stress with accuracies of 0.95 and 0.93, respectively. This study will allow us to classify the different types and severity of plant stress, prescribe appropriate treatment methods for efficient cost and time management of crop production, and potentially apply them to low-cost field measurement systems.