Neural Latent Arbitrary Lagrangian-Eulerian Grids for Fluid-Solid Interaction

2026-02-28

AI Summary

This work addresses the challenge of modeling highly nonlinear and dynamically heterogeneous interactions in complex two-way fluid–structure interaction (FSI) problems by proposing Fisale, the first data-driven framework that integrates Arbitrary Lagrangian–Eulerian (ALE) principles with deep learning. Fisale explicitly models the coupling interface, constructs a multiscale implicit ALE mesh to provide a unified geometric-aware embedding, and introduces a partitioned coupling module to iteratively capture nonlinear dependencies. This enables collaborative, iterative learning across fluid, solid, and their mutual interactions. Evaluated on diverse 2D and 3D real-world FSI tasks, Fisale significantly outperforms existing methods and offers a scalable solution for modeling intricate dynamic bidirectional coupling.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Fluid-solid interaction (FSI) problems are fundamental in many scientific and engineering applications, yet effectively capturing the highly nonlinear two-way interactions remains a significant challenge. Most existing deep learning methods are limited to simplified one-way FSI scenarios, often assuming rigid and static solid to reduce complexity. Even in two-way setups, prevailing approaches struggle to capture dynamic, heterogeneous interactions due to the lack of cross-domain awareness. In this paper, we introduce \textbf{Fisale}, a data-driven framework for handling complex two-way \textbf{FSI} problems. It is inspired by classical numerical methods, namely the Arbitrary Lagrangian-Eulerian (\textbf{ALE}) method and the partitioned coupling algorithm. Fisale explicitly models the coupling interface as a distinct component and leverages multiscale latent ALE grids to provide unified, geometry-aware embeddings across domains. A partitioned coupling module (PCM) further decomposes the problem into structured substeps, enabling progressive modeling of nonlinear interdependencies. Compared to existing models, Fisale introduces a more flexible framework that iteratively handles complex dynamics of solid, fluid and their coupling interface on a unified representation, and enables scalable learning of complex two-way FSI behaviors. Experimentally, Fisale excels in three reality-related challenging FSI scenarios, covering 2D, 3D and various tasks. The code is available at \href{https://github.com/therontau0054/Fisale}.

Problem

• Fluid-Solid Interaction
• Two-way Coupling
• Nonlinear Dynamics
• Cross-domain Awareness
• Arbitrary Lagrangian-Eulerian

Innovation

• Fluid-Solid Interaction
• Arbitrary Lagrangian-Eulerian
• Latent Grids
• Partitioned Coupling
• Two-way Coupling