Scholarlink

<p>Floods are considered among the most devastating natural disasters worldwide, demanding advanced and proactive management strategies to mitigate their severe socio-economic and environmental impacts. This systematic review rigorously explores the evolving role of artificial intelligence (AI) in intelligent flood management. It covers key domains such as flood prediction, risk assessment, mapping, monitoring, and resilience enhancement. The study reviewed over 71 articles from 2014 to 2024, underlining the growing use of machine learning, deep learning, and hybrid models in a variety of applications. It highlights the increasing trust in multi-source data such as satellite imagery, remote sensing, sensor networks, and hydro-meteorological datasets for accurate flood forecasting and decision making. Notably, the study examines a number of techniques used to evaluate AI model performance, such as classification and regression tasks. AI has made enormous progress in recent years, and now it offers incredibly promising solutions to handle the complex and dynamic nature of flood hazards. This paper examines current trends, implementation challenges, and research requirements before presenting a future road map for developing interpretable, real-time, and integrated AI-driven flood management systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Rising with Intelligence: A Systematic Review of AI Transforming Smart Flood Management

  • 期刊论文

  • 发表日期：

    2026年5月16日

查看全文
  • Deepika Mahajan,
  • Sandeep Sharma,
  • Komal Saini

摘要

Floods are considered among the most devastating natural disasters worldwide, demanding advanced and proactive management strategies to mitigate their severe socio-economic and environmental impacts. This systematic review rigorously explores the evolving role of artificial intelligence (AI) in intelligent flood management. It covers key domains such as flood prediction, risk assessment, mapping, monitoring, and resilience enhancement. The study reviewed over 71 articles from 2014 to 2024, underlining the growing use of machine learning, deep learning, and hybrid models in a variety of applications. It highlights the increasing trust in multi-source data such as satellite imagery, remote sensing, sensor networks, and hydro-meteorological datasets for accurate flood forecasting and decision making. Notably, the study examines a number of techniques used to evaluate AI model performance, such as classification and regression tasks. AI has made enormous progress in recent years, and now it offers incredibly promising solutions to handle the complex and dynamic nature of flood hazards. This paper examines current trends, implementation challenges, and research requirements before presenting a future road map for developing interpretable, real-time, and integrated AI-driven flood management systems.