Fast Prediction Method for Steady Flow Simulations over Multiple Domains

Computational fluid dynamics is an important application in the field of computational science and high-performance computing, and requires a large number of computations to be performed with high accuracy. In recent years, relying on the fast inference provided by deep learning, there has been a lot of research and development on fast prediction of numerical simulation results using a data-driven approach. We have been working on developing a method that uses deep learning to predict the results obtained from steady fluid flow simulations. We predict the flow velocity over the entire region based on the boundary conditions of the computational domain and a signed distance function representing the objects. To predict simulation results over a computational domain larger than the training data, we propose a prediction method that combines deep learning inference on a decomposed subdomain and boundary exchange between these subdomains. In this talk, we will present these approaches and results.