Exploring a Novel Methodologies for Beetroot Leaf Disease Severity Prediction: Federated Learning and CNN

This study explains how a federated learning Convolutional Neural Network (CNN) model is used to diagnose the various degrees of beetroot leaf diseases. Beetroot crops are essential to the world's food systems, but several illnesses often affect their quality and productivity. To suggest a CNN model using federated learning to analyse data from several clients while preserving privacy for a quick and precise diagnosis. The method analyses the severity of the five stages of beetroot leaf diseases using a federated learning technique across several local clients to use precision, recall, F1-score, and accuracy as performance measurements. The review showed that performance had improved consistently for all customers. As an example, Client X had a prediction accuracy of 0.97, which increased gradually to 0.98 for both Client P and Client R. Additionally, as shown by the macro-average (94.15-94.17%), weighted average (94.67%), and micro-average (94.62%) scores for top-performing customers, the model's performance remained stable and resilient throughout all severity levels. The study's findings support using a CNN model built on federated learning for scalable, effective, and privacy-preserving disease control in agriculture. The promising results suggest the potential for extending such approaches to other agricultural products, considerably advancing efforts to ensure global food security. The research also showed that the CNN model could learn and develop continuously in a federated learning scenario, highlighting its usefulness as a dynamic tool that adapts to new illness patterns. A paradigm shift in the approach to combating agricultural illnesses and increasing food supply is heralded by this study, which reveals a potential junction between machine learning and agricultural disease management. The findings motivate more research into the model's adaptability to other crops and pests, enhancing its contribution to resilient and sustainable farming systems.