A Comprehensive Survey on Deep Learning Solutions for 3D Flood Mapping

2025-06-16

AI Summary

Confronted with the limitations of conventional 2D flood mapping in jointly characterizing spatial extent and water depth under intensifying climate change and urbanization, this paper presents a systematic review of deep learning–driven 3D flood mapping. We propose, for the first time, a methodological taxonomy distinguishing task-decomposed and end-to-end approaches. We unify the treatment of multi-source heterogeneous data—including digital elevation models (DEMs), satellite imagery, precipitation records, and hydrodynamic model outputs—and formalize their integration paradigms and synergistic pathways with physics-based models. Coverage spans core deep learning architectures: CNNs, RNNs, GNNs, and Transformers. We identify key bottlenecks—namely, insufficient annotation quality, lack of physical consistency, and poor model interpretability—that constrain predictive accuracy. To address these, we highlight critical research directions: construction of high-fidelity annotated datasets and design of physics-informed neural networks. These advances substantially enhance capabilities in disaster response, flood risk assessment, and resilient urban planning.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: 3D Computer Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Flooding remains a major global challenge, worsened by climate change and urbanization, demanding advanced solutions for effective disaster management. While traditional 2D flood mapping techniques provide limited insights, 3D flood mapping, powered by deep learning (DL), offers enhanced capabilities by integrating flood extent and depth. This paper presents a comprehensive survey of deep learning-based 3D flood mapping, emphasizing its advancements over 2D maps by integrating flood extent and depth for effective disaster management and urban planning. The survey categorizes deep learning techniques into task decomposition and end-to-end approaches, applicable to both static and dynamic flood features. We compare key DL architectures, highlighting their respective roles in enhancing prediction accuracy and computational efficiency. Additionally, this work explores diverse data sources such as digital elevation models, satellite imagery, rainfall, and simulated data, outlining their roles in 3D flood mapping. The applications reviewed range from real-time flood prediction to long-term urban planning and risk assessment. However, significant challenges persist, including data scarcity, model interpretability, and integration with traditional hydrodynamic models. This survey concludes by suggesting future directions to address these limitations, focusing on enhanced datasets, improved models, and policy implications for flood management. This survey aims to guide researchers and practitioners in leveraging DL techniques for more robust and reliable 3D flood mapping, fostering improved flood management strategies.

Problem

• Surveying deep learning solutions for 3D flood mapping to improve disaster management
• Comparing DL architectures for better flood prediction accuracy and efficiency
• Addressing challenges like data scarcity and model interpretability in flood mapping

Innovation

• Deep learning integrates flood extent and depth
• Task decomposition and end-to-end approaches used
• Multiple data sources enhance 3D mapping accuracy