DamFormer: Generalizing Morphologies in Dam Break Simulations Using Transformer Model

TL;DR

This paper introduces DamFormer, a transformer-based deep learning model that simulates complex wave-structure interactions in dam break scenarios, aiming to improve flood and tsunami risk assessments.

Contribution

The paper presents a novel transformer model, DamFormer, capable of generalizing wave interactions across different structural shapes in dam break simulations.

Findings

DamFormer accurately predicts wave-structure interactions.

The model generalizes well across multiple structural geometries.

It offers a new approach for simulating dam break phenomena.

Abstract

The interaction of waves with structural barriers such as dams breaking plays a critical role in flood defense and tsunami disasters. In this work, we explore the dynamic changes in wave surfaces impacting various structural shapes, e.g., circle, triangle, and square, by using deep learning techniques. We introduce the DamFormer, a novel transformer-based model designed to learn and simulate these complex interactions. The model was trained and tested on simulated data representing the three structural forms.