Simulations of Complex Visco-Thermal Fluids with an AI-based CFD Emulator

Abstract

Physical phenomena evolve in space and time following governing laws with a high level of complexity and mathematical models can help to make accurate predictions of their behavior, describing complex fluids with a good balance between accuracy and computational costs. We have long used detailed Computational Fluid Dynamics (CFD) models to simulate complex dynamics with high accuracy, but these simulations typically entail high computational costs, resulting in long execution times and the use of expensive computational resources. To overcome these limitations, we have recently integrated CFD with Artificial Intelligence (AI), in the so-called Emulators, to expand the scope of fluid modeling, improving its performance. Here, we present an AI-based CFD emulator for Smoothed Particle Hydrodynamics (SPH) simulations, which uses an Artificial Neural Network (ANN) to enhance simulations of complex fluids with viscous and thermal components.

We show the model capability to reproduce the spatio-temporal evolution of natural visco-thermal fluids. In addition, we demonstrate the emulator capacity to generalize its applicability to problems not encountered during the training phase. We also conduct a detailed error evaluation, showing that the minimal observed discrepancies do not compromise model accuracy and robustness, especially given the theoretical and computational advantages. These key points open this emulator to practical applications for natural fluids, e.g., oil, honey, or geophysical fluids such as lava, enhancing fluidmodeling performance and extending functionalities. The innovation of this method improves studies in the field of numerical simulations, for example in its use as a digital Twin of a physical phenomenon, for the study of the dynamics of the system without the need of large costs for field analysis or laboratory experiments.