A Review of the Application of Artificial Intelligence in Climate Change-Induced Flooding—Susceptibility and Management Techniques

Abstract

Listen

Translate article

A fresh paradigm for classifying current studies on flood management systems is proposed in this review. The literature has examined methods for managing different flood management activities from a variety of fields, such as machine learning, image processing, data analysis, and remote sensing. Prediction, detection, mapping, evacuation, and relief efforts are all part of flood management. This can be improved by adopting state-of-the-art tools and technology. Preventing floods and ensuring a prompt response after floods is crucial to ensuring the lowest number of fatalities as well as minimizing environmental and financial damages. The following noteworthy research questions are addressed by the framework: (1) What are the main methods used in flood control? (2) Which stages of flood management are the majority of research currently in existence focused on? (3) Which systems are being suggested to address issues with flood control? (4) In the literature, what are the research gaps regarding the use of technology for flood management? To classify the many technologies that have been studied, a framework for classification has been provided for flood management. It was found that there were few hybrid models for flood control that combined machine learning and image processing. Furthermore, it was discovered that there was little use of machine learning-based techniques in the aftermath of a disaster. To provide efficient and comprehensive disaster management, future efforts must concentrate on integrating image processing methods, machine learning technologies, and the understanding of disaster management across all phases. The study has proposed the use of Generative Artificial Intelligence.