Downloads: 1
Research Paper | Computer Science and Engineering | Volume 15 Issue 7, July 2026 | Pages: 840 - 843 | India
Towards Secure and Efficient Federated Learning for Wheat and Rice Disease Diagnosis
Abstract: Federated learning (FL) is a distributed machine learning paradigm that enables multiple clients (e.g. farms, sensors, or smartphones) to collaboratively train models without sharing raw data. This is highly relevant for agriculture, where data about crop health is sensitive and distributed across many smallholders. In India, wheat and rice - the country?s two most important cereals - suffer huge losses from fungal diseases (rusts, blast, etc.). FL can leverage diverse image datasets from distributed fields (e.g. smartphone or drone imagery of leaves) to improve disease detection while preserving privacy. This paper introduces FL concepts and its role in plant disease diagnosis, traces FL?s evolution, compares its advantages over centralized/cloud methods in agri-disease detection, reviews recent FL-agriculture research (including wheat/rice cases), and identifies research gaps and future directions in context of wheat and rice. A summary table compares representative FL-based approaches for diseased crops.
Keywords: Federated Learning, Crop Disease Detection, Wheat, Rice, Edge Devices
How to Cite?: Shabad Kaur, Amandeep Kaur Virk, "Towards Secure and Efficient Federated Learning for Wheat and Rice Disease Diagnosis", Volume 15 Issue 7, July 2026, International Journal of Science and Research (IJSR), Pages: 840-843, https://www.ijsr.net/getabstract.php?paperid=SR26710161525, DOI: https://dx.doi.org/10.21275/SR26710161525