eprintid: 10186111 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/18/61/11 datestamp: 2024-01-25 08:47:19 lastmod: 2024-01-25 08:47:19 status_changed: 2024-01-25 08:47:19 type: article metadata_visibility: show sword_depositor: 699 creators_name: Hu, Jinwei creators_name: Zhu, Kewei creators_name: Cheng, Sibo creators_name: Kovalchuk, Nina M creators_name: Soulsby, Alfred creators_name: Simmons, Mark JH creators_name: Matar, Omar K creators_name: Arcucci, Rossella title: Explainable AI models for predicting drop coalescence in microfluidics device ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F43 keywords: Explainable AI; Drop coalescence; Machine learning; LIME; SHAP value note: Copyright © 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). abstract: In the field of chemical engineering, understanding the dynamics and probability of drop coalescence is not just an academic pursuit, but a critical requirement for advancing process design by applying energy only where it is needed to build necessary interfacial structures, increasing efficiency towards Net Zero manufacture. This research applies machine learning predictive models to unravel the sophisticated relationships embedded in the experimental data on drop coalescence in a microfluidics device. Through the deployment of SHapley Additive exPlanations values, critical features relevant to coalescence processes are consistently identified. Comprehensive feature ablation tests further delineate the robustness and susceptibility of each model. Furthermore, the incorporation of Local Interpretable Model-agnostic Explanations for local interpretability offers an elucidative perspective, clarifying the intricate decision-making mechanisms inherent to each model’s predictions. As a result, this research provides the relative importance of the features for the outcome of drop interactions. It also underscores the pivotal role of model interpretability in reinforcing confidence in machine learning predictions of complex physical phenomena that are central to chemical engineering applications. date: 2024-02-01 date_type: published publisher: Elsevier BV official_url: http://dx.doi.org/10.1016/j.cej.2023.148465 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2141638 doi: 10.1016/j.cej.2023.148465 lyricists_name: Zhu, Kewei lyricists_id: KZHUA89 actors_name: Zhu, Kewei actors_id: KZHUA89 actors_role: owner full_text_status: public publication: Chemical Engineering Journal volume: 481 article_number: 148465 issn: 1385-8947 citation: Hu, Jinwei; Zhu, Kewei; Cheng, Sibo; Kovalchuk, Nina M; Soulsby, Alfred; Simmons, Mark JH; Matar, Omar K; Hu, Jinwei; Zhu, Kewei; Cheng, Sibo; Kovalchuk, Nina M; Soulsby, Alfred; Simmons, Mark JH; Matar, Omar K; Arcucci, Rossella; - view fewer <#> (2024) Explainable AI models for predicting drop coalescence in microfluidics device. Chemical Engineering Journal , 481 , Article 148465. 10.1016/j.cej.2023.148465 <https://doi.org/10.1016/j.cej.2023.148465>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10186111/1/Explainable%20AI%20models%20for%20predicting%20drop%20coalescence%20in%20microfluidics%20device.pdf