Hierarchical Terrain Attention and Multi-Scale Rainfall Guidance For Flood Image Prediction

TL;DR

This paper introduces a novel flood prediction framework that uses hierarchical terrain attention and multi-scale rainfall embedding to improve flood map accuracy, outperforming previous methods across various rainfall scenarios.

Contribution

It proposes a new model integrating terrain attention and multi-scale rainfall features, with a rainfall regression loss for enhanced flood prediction accuracy.

Findings

Outperforms previous flood prediction methods on real datasets.

Effectively captures terrain and rainfall patterns for precise flood mapping.

Demonstrates robustness across different rainfall conditions.

Abstract

With the deterioration of climate, the phenomenon of rain-induced flooding has become frequent. To mitigate its impact, recent works adopt convolutional neural network or its variants to predict the floods. However, these methods directly force the model to reconstruct the raw pixels of flood images through a global constraint, overlooking the underlying information contained in terrain features and rainfall patterns. To address this, we present a novel framework for precise flood map prediction, which incorporates hierarchical terrain spatial attention to help the model focus on spatially-salient areas of terrain features and constructs multi-scale rainfall embedding to extensively integrate rainfall pattern information into generation. To better adapt the model in various rainfall conditions, we leverage a rainfall regression loss for both the generator and the discriminator as additional supervision. Extensive evaluations on real catchment datasets demonstrate the superior performance of our method, which greatly surpasses the previous arts under different rainfall conditions.