Interpretable machine learning analysis and automated modeling to simulate fluid-particle flows

The present study extracts human-understandable insights from machine learning (ML)-based meso-scale closure in fluid-particle flows via several novel data-driven analysis approaches, i.e., maximal in-formation coefficient (MIC), interpretable ML, and automated ML. It is previously shown that the solid volume fraction has the greatest effect on the drag force. The present study aims to quantitatively investigate the influence of flow properties on mesoscale drag correction (Hd). The MIC results show strong correlations between the features (i.e., slip velocity (u* sy) and particle volume fraction (es)) and the label Hd. The interpretable ML analysis confirms this conclusion, and quantifies the contribution of u*sy, es and gas pressure gradient to the model as 71.9%, 27.2% and 0.9%, respectively. Automated ML without the need to select the model structure and hyperparameters is used for modeling, improving the prediction accuracy over our previous model (Zhu et al., 2020; Ouyang, Zhu, Su, & Luo, 2021).(c) 2023 Chinese Society of Particuology and Institute of Process Engineering, Chinese Academy of Sciences. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http:// creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

The present study applies several novel data-driven analysis approaches to extract human-understandable insights from machine learning-based meso-scale closure in fluid-particle flows. The study aims to quantitatively investigate the influence of flow properties on mesoscale drag correction (Hd), and the results show strong correlations between the features (i.e., slip velocity (u* sy) and particle volume fraction (es)) and the label Hd. The interpretable ML analysis confirms this conclusion and quantifies the contribution of u* sy, es, and gas pressure gradient to the model.