FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhu, Max, Bazaga, Adrián, Liò, Pietro
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913380467474432
author Zhu, Max
Bazaga, Adrián
Liò, Pietro
author_facet Zhu, Max
Bazaga, Adrián
Liò, Pietro
contents Learning computational fluid dynamics (CFD) traditionally relies on computationally intensive simulations of the Navier-Stokes equations. Recently, large language models (LLMs) have shown remarkable pattern recognition and reasoning abilities in natural language processing (NLP) and computer vision (CV). However, these models struggle with the complex geometries inherent in fluid dynamics. We introduce FLUID-LLM, a novel framework combining pre-trained LLMs with spatiotemporal-aware encoding to predict unsteady fluid dynamics. Our approach leverages the temporal autoregressive abilities of LLMs alongside spatial-aware layers, bridging the gap between previous CFD prediction methods. Evaluations on standard benchmarks reveal significant performance improvements across various fluid datasets. Our results demonstrate that FLUID-LLM effectively integrates spatiotemporal information into pre-trained LLMs, enhancing CFD task performance.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04501
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models
Zhu, Max
Bazaga, Adrián
Liò, Pietro
Machine Learning
Artificial Intelligence
Computation and Language
Learning computational fluid dynamics (CFD) traditionally relies on computationally intensive simulations of the Navier-Stokes equations. Recently, large language models (LLMs) have shown remarkable pattern recognition and reasoning abilities in natural language processing (NLP) and computer vision (CV). However, these models struggle with the complex geometries inherent in fluid dynamics. We introduce FLUID-LLM, a novel framework combining pre-trained LLMs with spatiotemporal-aware encoding to predict unsteady fluid dynamics. Our approach leverages the temporal autoregressive abilities of LLMs alongside spatial-aware layers, bridging the gap between previous CFD prediction methods. Evaluations on standard benchmarks reveal significant performance improvements across various fluid datasets. Our results demonstrate that FLUID-LLM effectively integrates spatiotemporal information into pre-trained LLMs, enhancing CFD task performance.
title FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2406.04501