Know to Predict, Forecast to Warn: A Review of Flood Risk Prediction Tools
Academic Article
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
abstract
Flood prediction has advanced significantly in terms of technique and capacity to achieve policymakers objectives of accurate forecast and identification of flood-prone and impacted areas. Flood prediction tools are critical for flood hazard and risk management. However, numerous reviews on flood modelling have focused on individual models. This study presents a state-of-the-art review of flood prediction tools with a focus on analyzing the chronological growth of the research in the field of flood prediction, the evolutionary trends in flood prediction, analysing the strengths and weaknesses of each tool, and finally identifying the significant gaps for future studies. The article conducted a review and meta-analysis of 1101 research articles indexed by the Scopus database in the last five years (20172022) using Biblioshiny in r. The study drew an up-to-date picture of the recent developments, emerging topical trends, and gaps for future studies. The finding shows that machine learning models are widely used in flood prediction, while Probabilistic models like Copula and Bayesian Network (B.N.) play significant roles in the uncertainty assessment of flood risk, and should be explored since these events are uncertain. It was also found that the advancement of the remote sensing, geographic information system (GIS) and cloud computing provides the best platform to integrate data and tools for flood prediction. However, more research should be conducted in Africa, South Africa and Australia, where less work is done and the potential of the probabilistic models in flood prediction should be explored.
