Intelligent Approach to Massive Data Analysis and Its Impact on Leaf Disease Detection Decision-Making

Abstract

Food production and economic growth depend heavily on the agricultural sector, yet plant diseases present serious risks. Maintaining food quality and avoiding losses need early detection. Through image classification, deep learning—more specifically, convolutional neural networks (CNNs)—has demonstrated potential in the identification of plant diseases. In this work, we construct a dependable leaf disease detection system using CNNs and pre-trained models, such as VGG-16 and Resnet-50. Our tests produced impressive results, using a dataset of 54,201 images from different classifications. The performance evaluation includes important performance measures including F1 score and classification accuracy. With a remarkable classification accuracy of 97.30%, VGG-16 outperforms Resnet- 50 with 93.04%. The results demonstrate the efficacy of deep learning models in the identification of leaf diseases, with VGG- 16 demonstrating the highest performance. This strategy presents practical methods to advance sustainable crop production and agriculture.