Reviewing Flood Susceptibility Mapping Utilizing Machine Learning: Insights and Prospects for Future Research

Over the past decade, the utilization of machine learning for flood forecasting has experienced significant growth, propelled by advancements in high-performance computing, risk-informed decision-making, and collaborative efforts within the domains of weather and climate forecasting. These approaches offer the potential to enhance flood mapping methodologies and address the limitations inherent in numerical models, thus gaining traction in flood risk management. This study aims to conduct a comprehensive review of the literature on machine learning applications in flood estimation and prediction across various flood mapping contexts. The investigation will delve into diverse flood types, influential conditioning factors, and varied data sources. By studying 34 pertinent articles within the Indian context, this research endeavors to provide a comprehensive overview of current research endeavors, pinpoint existing knowledge gaps, and explore promising avenues for future research. Additionally, the paper underscores the imperative to enhance flood forecasting technologies and bridge the divide between academic inquiry, hydro-meteorological model advancement, and pragmatic flood management practices by leveraging the capabilities of probabilistic machine learning and deep learning models.