AI-Driven Flood Forecasting: Advancements, Challenges, and Future Directions

View at publisher Summarise with VIRAT
Authors: Ashwini Pansare, Amit Barve, Rajib Chattopadhyay
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Among the natural disasters experienced worldwide, floods are one of the most destructive natural hazards affecting world populations through economic and human losses. Flood preparedness is essential for reducing the damage caused by floods. If a flood is forecasted, early government authorities and local people will get sufficient time to equip themselves to tackle the disaster. This necessitates an early and accurate flood forecasting system. Researchers have developed many flood forecasting models in the past, but they have failed to model the complex and dynamic relationships present in the real world. Advances in Machine Learning (ML) and Deep Learning (DL) have encouraged researchers to apply these techniques to flood forecasting. This study critically reviewed various ML and DL models that are used for flood forecasting. Researchers have used Artificial Neural Networks (ANN), Support Vector Machines (SVM), Long Short-Term Memory (LSTM) networks, transformers, and various hybrid frameworks. The study findings recommend hybrid and ensemble ML-DL models over conventional models because of their higher accuracy and capability to efficiently handle uncertainty. The objective of this study is to guide researchers and field practitioners in developing robust, adaptive, and scalable flood-forecasting systems.

Fields of Study & Subjects

Hydrological Forecasting Using AI Flood Risk Assessment and Management Hydrology and Watershed Management Studies

Publication details

Journal / source
CRC Press eBooks
Pages
99–105
Publication date
25 March 2026
Language
EN
Document type
Book chapter