The Closure Challenge: a benchmark task for machine learning in turbulence modelling

TL;DR

The paper introduces a benchmark challenge for machine learning in turbulence modelling, providing datasets and evaluation tools to standardize testing and promote innovation in the field.

Contribution

It creates a standardized benchmark with datasets and evaluation code for RANS turbulence models, addressing the lack of a common testing framework.

Findings

Early submissions demonstrate the benchmark's utility.

The benchmark evaluates generalization across Reynolds number and geometry.

It aims to become the standard for ML in turbulence modelling.

Abstract

We introduce a field-wide benchmark challenge for machine learning in Reynolds-averaged Navier-Stokes (RANS) turbulence modelling. Though open-source datasets exist for training data-driven turbulence closure models, the field has been notably lacking a standard benchmark metric and test dataset. The Closure Challenge is a curated collection of open-source datasets and evaluation code that remedies this problem. We provide a variety of high-fidelity training data in a standardized format, including mean velocity gradients. The test cases (periodic hills, square duct, and NASA wall-mounted hump) evaluate Reynolds number and geometry generalization, two key issues in the field. We present results from three early submissions to the challenge. This is an ongoing challenge, intended to continuously spur innovation in machine learning for turbulence modelling. Our goal is for this benchmark to become the standard evaluation for new machine learning frameworks in RANS. The Closure Challenge is available at https://github.com/rmcconke/closure-challenge-benchmark.