Data-driven insights into jet turbulence: Explainable AI approaches

In this study, eXplainable Artificial Intelligence (XAI) methods are applied to analyze flow fields obtained through particle image velocimetry measurements of an axisymmetric turbulent jet. A convolutional neural network (U-Net) was trained to predict velocity fields at subsequent time steps. Three XAI methods—SHapley Additive explanations (SHAP), Gradient-SHAP, and Gradient-weighted Class Activation Mapping (Grad-CAM)—were employed to identify the flow field regions relevant for prediction. SHAP requires predefined segmentation of the flow field into relevant regions, while Gradient-SHAP and Grad-CAM avoid this bias by generating gradient-based heatmaps. The results show that the most relevant structures do not necessarily coincide with the regions of maximum vorticity, but rather with those that play a critical role in energy transfer and jet dynamics. Additionally, structures with high turbulent dissipation values are identified as the most significant. Gradient-SHAP and Grad-CAM methods reveal a uniform spatial distribution of relevant regions, emphasizing the contribution of nearly circular structures to turbulent mixing. This study advances the understanding of turbulent dynamics through XAI tools, providing an innovative approach to correlate machine learning models with physical phenomena.