Interpreted machine learning in fluid dynamics: Explaining relaminarisation events in wall-bounded shear flows

TL;DR

This paper introduces the SHAP explainability method to fluid dynamics ML models, demonstrating its ability to interpret features related to relaminarisation events in shear flows, linking ML insights with physical phenomena.

Contribution

The paper applies the SHAP algorithm to fluid dynamics data, providing the first proof of concept of explainable AI in this field with physically interpretable feature importance.

Findings

SHAP identifies key physical features like vortices and streaks in flow data.

The method reveals streak instabilities are crucial for relaminarisation prediction.

SHAP analysis connects ML predictions with known fluid dynamics mechanisms.

Abstract

Machine Learning (ML) is becoming increasingly popular in fluid dynamics. Powerful ML algorithms such as neural networks or ensemble methods are notoriously difficult to interpret. Here, we introduce the novel Shapley Additive Explanations (SHAP) algorithm (Lundberg & Lee, 2017), a game-theoretic approach that explains the output of a given ML model, in the fluid dynamics context. We give a proof of concept concerning SHAP as an explainable AI method providing useful and human-interpretable insight for fluid dynamics. To show that the feature importance ranking provided by SHAP can be interpreted physically, we first consider data from an established low-dimensional model based on the self-sustaining process (SSP) in wall-bounded shear flows, where each data feature has a clear physical and dynamical interpretation in terms of known representative features of the near-wall dynamics, i.e. streamwise vortices, streaks and linear streak instabilities. SHAP determines consistently that only the laminar profile, the streamwise vortex, and a specific streak instability play a major role in the prediction. We demonstrate that the method can be applied to larger fluid dynamics datasets by a SHAP evaluation on plane Couette flow in a minimal flow unit focussing on the relevance of streaks and their instabilities for the prediction of relaminarisation events. Here, we find that the prediction is based on proxies for streak modulations corresponding to linear streak instabilities within the SSP. That is, the SHAP analysis suggests that the break-up of the self-sustaining cycle is connected with a suppression of streak instabilities.