Disease Diagnosis and Sustainable Prevention in Arecanut Farming

One of India's main crops is arecanut. It is grown more in India and other subtropical climates due to its higher market value. Numerous diseases that affect this plant might result in significant losses for farmers. These illnesses are brought on by abrupt changes in temperature and other meteorological factors; early disease identification is crucial. In order to minimize losses for farmers, this work focuses on early and precise disease diagnosis. A Convolutional Neural Network is a Deep Learning technique that uses an image as input, gives different features in the image learnable weights and biases, and then uses the results to determine which features are different. This method improves process efficiency and drastically lowers the amount of manual labor needed for illness diagnosis. To train and assess the CNN with Extension model, a dataset including several images of both healthy and diseased areca nut leaves is created. It was found that the recommended approach to areca nut illness diagnosis was accurate and effective. This study supports further initiatives to use technology in agriculture to increase crop productivity and health. According to this study, the suggested approach is the most reliable for identifying illnesses in areca nut leaves. In addition to providing suitable treatments for any diseases it identified, the system was able to differentiate between healthy and sick leaves. These results highlight the potential use of deep learning techniques and convolutional neural networks in agriculture, specifically in the control of plant diseases. One of the diseases of areca nuts that the suggested system can identify and cure is yellow leaf spot. The experimental results demonstrate different levels of disease identification accuracy depending on the stage of the disease and the quality of the input image. The system's overall accuracy is estimated to be 98.9%.