FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models
This addresses the challenge of computationally intensive CFD simulations for researchers and engineers, though it appears incremental as it builds on existing LLM methods.
The paper tackles the problem of learning computational fluid dynamics (CFD) by introducing FLUID-LLM, a framework that combines pre-trained large language models with spatiotemporal-aware encoding to predict unsteady fluid dynamics, resulting in significant performance improvements across various fluid datasets.
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.