Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{167892,
        author = {Aakula Akhila and Dr. K. Santhi Sree},
        title = {FL-FPM FEDERATED LEARNING BASED FLOOD PREDICTION MODEL},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {4},
        pages = {796-803},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167892},
        abstract = {This paper proposes a novel strategy that utilizations federated learning to improve flood prediction accuracy because of the developing danger of floods while resolving significant issues with information security and organization inertness. The concentrated information gathering limitations that have tormented customary flood prediction approaches have encouraged an interest for a decentralized model that can precisely expect floods with a lead time. This study presents a decentralized flood forecasting model that consolidates Feedforward Neural Network (FFNN) models from a few clients that have been prepared locally. This technique tackles protection issues by utilizing unified figuring out how to total bits of knowledge from a few datasets without risking the security of individual information. The program shows how viable it is at recognizing mind boggling flood examples and conveying convenient notices that are modified for specific regions, further developing readiness and response times for debacles. The model's ability to extraordinarily increment forecast accuracy when contrasted with conventional techniques is exhibited by approval preliminaries, highlighting the progressive capability of state of the art approaches in calamity aversion. This work sets a norm for involving federated learning in ecological gauging, with the potential for more extensive applications in lessening the impacts of regular calamities on a worldwide scale.},
        keywords = {Hydraulic, meteorological, flood forecasting system, federated learning, feed-forward neural network, Convolution2D Neural Network.},
        month = {September},
        }