JERUSALEM — Israeli researchers have developed an artificial intelligence (AI) automated method to predict stress in agricultural crops, the Israel Institute of Technology (Technion) said Tuesday.
In their study, Technion researchers developed the smart technology for the monitoring and prediction of water and heat stress in crops.
“The detection of drought stress enables the plant to be saved, allows for the identification of diseases and the prediction of crop yield quantities, all of which are crucial information for the grower,” the researchers explained.
Thus, using deep learning, color photographs and thermal imaging, the researchers were able to predict stress and leaf development with great success.
In a test of the technology on banana seedlings, an impressive prediction level of over 90 percent accuracy was achieved.
The new technology also allows leaf count and segmentation, easing the complicated task of collecting labelled data from field crops and greenhouses.
In this context, the researchers achieved unprecedented results in the identification of Arabidopsis and tobacco leaves by applying deep learning.
To train the system on a large quantity of samples, the team developed a vast database containing artificial leaf images, and then tested the technology on avocado, cucumbers and maize crops.