A Physics-Informed Spatiotemporal Deep Learning Framework for Turbulent Systems

TL;DR

This paper introduces a physics-informed deep learning model that efficiently simulates turbulent Rayleigh-Benard convection by combining CNNs, recurrent architectures, and uncertainty quantification, reducing computational costs while maintaining physical accuracy.

Contribution

It presents a novel spatiotemporal surrogate model integrating physics constraints with deep learning for turbulent fluid systems, enhancing simulation efficiency and interpretability.

Findings

Replicates key RBC physical features accurately.

Reduces computational cost compared to DNS.

Quantifies uncertainty in turbulent predictions.

Abstract

Fluid thermodynamics underpins atmospheric dynamics, climate science, industrial applications, and energy systems. However, direct numerical simulations (DNS) of such systems can be computationally prohibitive. To address this, we present a novel physics-informed spatiotemporal surrogate model for Rayleigh-Benard convection (RBC), a canonical example of convective fluid flow. Our approach combines convolutional neural networks, for spatial dimension reduction, with an innovative recurrent architecture, inspired by large language models, to model long-range temporal dynamics. Inference is penalized with respect to the governing partial differential equations to ensure physical interpretability. Since RBC exhibits turbulent behavior, we quantify uncertainty using a conformal prediction framework. This model replicates key physical features of RBC dynamics while significantly reducing computational cost, offering a scalable alternative to DNS for long-term simulations.