Cloud-Driven Federated Learning for Plant Disease Detection in Agriculture

Early and accurate detection of crop diseases is crucial for agriculture. This work explores Federated Learning (FL) as a solution, enabling collaborative model training on decentralized plant image data while preserving privacy. By leveraging cloud computing for data processing and scalability, FL enhances detection accuracy and generalization to new data. The proposed approach not only protects data confidentiality but also improves agricultural resilience and productivity, benefiting from the scalability and flexibility of cloud infrastructure.