Enhancing Precision in Papaya Crop Health Management: A CNN-Based Approach for Early Disease Detection and Classification

This study describes a unique Convolutional neural network, or CNN, topology that consists of three levels of convolution, three maximally pooled layers, and two fully linked layers. It is designed to accurately predict six different illnesses affecting papaya branches, including Papaya Ringspot. Virus, Papaya Mosaic Virus, Powdery Mildew, Papaya Bunchy Top Disease, Anthracnose, and Black Spot Disease. The work addresses the critical need for improved identification of diseases in papaya growing within the context of precision agriculture. It entails creating a diversified dataset with photos of both healthy and sick papaya leaves. The precisely designed CNN architecture retrieves intricate information from these photos, allowing for a categorization of various illness types. Attributes are finely adjusted using intensive training and validation techniques to ensure the model's resilience in disease prediction. The accuracy, recall, and F1-score are evaluation metrics that quantify the algorithm's performance across illness categories. The findings illustrate the model's ability to distinguish between the defined papaya leaf diseases. The expected goals include developing an efficient instrument for disease early detection and control in papaya growing, thereby helping promote precision farming that is efficient and sustainable crop health management.