Fostering Sustainable Farming: A Novel Model for Automated Tomato Disease Detection

The current study intends to address the pressing demand for rapid detection of illnesses in tomato plants, which is the focus of the present research. As computing methods, convolutional neural networks and random forest classifiers are used with the purpose of accomplishing this goal. A ratio of 80:20 separates the training set from the testing set in the dataset, which totals 5,497 photographs. The model achieves a very impressive overall accuracy of 70.88%, in addition to a weighted average precision of 72.06% and an F1-score of 70.92%. Examining the accuracy, recall, and F1-score values for each distinct class is one way to determine how well the model is able to categorise illnesses. The current research provides a significant advancement in the area of precision agriculture by developing a technique that is both dependable and efficient for the rapid diagnosis of illnesses affecting tomato crops. When it comes to preserving agricultural production and reducing the risk of future losses, this is of the biggest significance.