Graph Attention Convolutional U-NET: A Semantic Segmentation Model for Identifying Flooded Areas

2025-02-21

AI Summary

To address insufficient accuracy in automated floodwater segmentation from aerial imagery during flood emergency response, this paper proposes a U-Net-based end-to-end semantic segmentation model integrating graph attention mechanisms with Chebyshev polynomial-based graph convolution. It is the first work to introduce graph neural networks (GNNs) into remote sensing flood segmentation, innovatively combining spectral-domain graph convolution for modeling pixel-wise topological relationships and attention mechanisms for enhancing discriminative representation of critical regions. Furthermore, it explores novel paradigms—transfer learning and model reprogramming—for few-shot remote sensing segmentation. Evaluated on a standard flood dataset, the model achieves 91% mAP, 94% Dice score, and 89% IoU, significantly outperforming state-of-the-art CNN- and Transformer-based methods. This work establishes a new methodological foundation for high-accuracy, interpretable flood perception.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Graph-based Machine Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

The increasing impact of human-induced climate change and unplanned urban constructions has increased flooding incidents in recent years. Accurate identification of flooded areas is crucial for effective disaster management and urban planning. While few works have utilized convolutional neural networks and transformer-based semantic segmentation techniques for identifying flooded areas from aerial footage, recent developments in graph neural networks have created improvement opportunities. This paper proposes an innovative approach, the Graph Attention Convolutional U-NET (GAC-UNET) model, based on graph neural networks for automated identification of flooded areas. The model incorporates a graph attention mechanism and Chebyshev layers into the U-Net architecture. Furthermore, this paper explores the applicability of transfer learning and model reprogramming to enhance the accuracy of flood area segmentation models. Empirical results demonstrate that the proposed GAC-UNET model, outperforms other approaches with 91% mAP, 94% dice score, and 89% IoU, providing valuable insights for informed decision-making and better planning of future infrastructures in flood-prone areas.

Problem

• Automated identification of flooded areas
• Enhancing flood area segmentation accuracy
• Improving disaster management and urban planning

Innovation

• Graph Attention Convolutional U-NET model
• Incorporates graph attention mechanism
• Uses Chebyshev layers in U-Net