An Efficient Machine Learning Framework for Flood Forecasting

Title

An Efficient Machine Learning Framework for Flood Forecasting

Creator

Anushka; George, Jossy; Nair, Akhil M.; Alapatt, Bosco Paul; Baby, Riya; Jose, Jiby

Description

Floods, a significant natural disaster which has an impact on the whole world present major risks to ecosystems and humans, particularly in semi-arid areas with variable rainfall patterns. With the help of ICRISATs historical meteorological data and machine learning algorithms, this study has developed a customized flood prediction model for use. After evaluating and contrasting various models, including the proposed model Stacked Gradient Boosting with Random Forest (SGB-RAF), KNN, Decision Tree, Random Forest, and Linear Regression, it shows that SGB-RAF has the highest R2 score and lowest RMSE comparatively to other models. While other enhancements such as Ridge Regression and polynomial feature creation were studied, SGB-RAF remained effective. Overall, this study highlights how machine learning may improve flood prediction accuracy, which is important for disaster management and for improving the semi-arid regions adaptability to climatic variability. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Source

Lecture Notes in Networks and Systems;Volume;1278;pp.433-444

Date

01-01-2025

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

Decision tree; Flood prediction; KNN; Logistic regression; Machine learning; Random forest; Support vector regression

Coverage

Anushka, School of Sciences, Christ University, Bengaluru, India; George J., School of Sciences, Christ University, Bengaluru, India; Nair A.M., Luxsh Technologies Pvt Ltd, Northwood Hills, Middlesex, United Kingdom; Alapatt B.P., School of Sciences, Christ University, Bengaluru, India; Baby R., School of Sciences, Christ University, Bengaluru, India; Jose J., School of Sciences, Christ University, Bengaluru, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 23673370; ISBN: 978-981962702-8;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-981-96-2703-5_29

https://www.scopus.com/pages/publications/105006929995?origin=resultslist