Machine learning enabled identification and real-time prediction of living plants’ stress using terahertz waves

Considering the ongoing climate transformations, appropriate and reliable phenotyping information of plant leaves is quite significant for early detection disease, yield improvement. In real-life digital agricultural environment, real-time prediction identification living plants has immensely grown in recent years. Hence, cost-effective automated timely plans species vital sustainable agriculture. This paper presents a novel, non-invasive method aiming to establish feasible, viable technique precise observation altering behaviour at cellular level four consecutive days by integrating machine learning (ML) THz with swissto12 materials characterization kit (MCK) frequency range 0.75 1.1 THz. For this purpose, measurements observations data seven various were determined incorporate three different ML algorithms such as random forest (RF), support vector machine, (SVM), K-nearest neighbour (KNN). The results demonstrated that RF exhibited higher accuracy 98.87% followed KNN SVM an 94.64% 89.67%, respectively, observing their morphological features. addition, outperformed other classifiers determination water-stressed having 99.42%. It envisioned proposed study can be proven beneficial agriculture technology significantly help mitigate economic losses improve crops quality.