Scientometric analysis of flood forecasting for Asia region and discussion on machine learning methods

Abstract

Flood forecast models have become better through research as they led to a lower risk of flooding, policy ideas, less human death, and less destruction of property, so this study uses Scientometric analysis for floods. In this analysis, citation-based data are used to uncover major publishing areas, such as the most prominent keywords, top best commonly used publications, the most highly cited journal articles, countries, and authors that have achieved consequent distinction in flood analysis. Machine learning (ML) techniques have played a significant role in the development of prediction systems, which have improved results and more cost-effective strategies. This study intends to give a review of ML methods such as decision trees, artificial neural networks, and wavelet neural networks, as well as a comparison of their precision, speed, and effectiveness. Severe flooding has been recognized as a significant source of massive deaths and property destruction in several nations, including India, China, Nepal, Pakistan, Bangladesh, and Sri Lanka. This study presents far more effective flood forecast approaches. This analysis is being used as a guide for experts and climate researchers when deciding which ML algorithm to utilize for a particular forecasting assignment.

Keywords

• scientometric analysis
• floods
• rainfall
• water
• methods
• prediction