Additive-feature-attribution methods: a review on explainable artificial intelligence for fluid dynamics and heat transfer
It addresses the need for explainable AI in fluid dynamics and heat transfer, but it is incremental as it reviews existing methods rather than introducing new ones.
This review paper tackles the problem of interpreting data-driven models in fluid mechanics by presenting additive-feature-attribution methods, such as SHAP, and categorizing their applications into turbulence modeling, fluid-mechanics fundamentals, and applied problems in fluid dynamics and heat transfer, concluding that these methods are crucial for developing interpretable and physics-compliant deep-learning models in the field.
The use of data-driven methods in fluid mechanics has surged dramatically in recent years due to their capacity to adapt to the complex and multi-scale nature of turbulent flows, as well as to detect patterns in large-scale simulations or experimental tests. In order to interpret the relationships generated in the models during the training process, numerical attributions need to be assigned to the input features. One important example are the additive-feature-attribution methods. These explainability methods link the input features with the model prediction, providing an interpretation based on a linear formulation of the models. The SHapley Additive exPlanations (SHAP values) are formulated as the only possible interpretation that offers a unique solution for understanding the model. In this manuscript, the additive-feature-attribution methods are presented, showing four common implementations in the literature: kernel SHAP, tree SHAP, gradient SHAP, and deep SHAP. Then, the main applications of the additive-feature-attribution methods are introduced, dividing them into three main groups: turbulence modeling, fluid-mechanics fundamentals, and applied problems in fluid dynamics and heat transfer. This review shows thatexplainability techniques, and in particular additive-feature-attribution methods, are crucial for implementing interpretable and physics-compliant deep-learning models in the fluid-mechanics field.