A Machine Learning Approach to Detect Disease in Tomato Plants

Tomatoes are among the most valuable crops in the world. They fall victim to diseases almost every time, which has a devastating effect on yield and quality. Early and accurate illness identification is crucial for sustainable farming practices since it reduces economic losses. This study investigated the possibility of using machine learning models to detect tomato plant diseases using a structured dataset that contains morphological and environmental variables, such as the number of leaf spots, the leaf color index, temperature, and humidity. To find the best supervised learning model for this specific classification job, we examined Random Forest, K-Nearest Neighbor, and Support Vector Machine. Feature selection, label encoding, and dataset scaling were all part of the preprocessing.