Identification of water stressed leaves using Artificial Intelligence: The case of eggplant

Abstract

Identification of water stress of leaves from the photos taken has a long history. Researchers have defined a parameter called Leaf Water Content (LWC) to quantify the dryness of leaves. However, in the case of automatic watering of plants, such high accuracy of LWC is not needed as a decision to water or not alone is sufficient. Furthermore, the agricultural industry cannot use methods of remote sensing that are required to find LWC as they are complex and costly. In the current practice, farmers use their knowledge and experience together with the appearance of plants to estimate the water stress and watering time point of plants. The approach presented in this paper is easily implemented and requires only a series of photos taken by a smartphone or a camera and a software app. In this paper, a method s introduced using Artificial Intelligence (AI) where the images of leaves are directly used to determine whether the leaves are water stressed. We could identify the water stressed leaves accurately using this method. Once an app based on our method is developed, it could easily be used by farmers to automatically identify whether the eggplants are water stressed and need watering.