arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.20397cs.LGphysics.chem-ph
收藏

多相催化中吸附能的可解释数据驱动建模

Explainable Data-driven Modeling of Adsorption Energy in Heterogeneous Catalysis

Carnegie Mellon University(卡内基梅隆大学)

Tirtha Vinchurkar, Janghoon Ock, Amir Barati Farimani

AI总结:

本文结合浅层机器学习与事后 XAI、符号回归,在 OC20 上预测并解释多相催化吸附能,识别关键特征并发现催化剂电负性平方与吸附能成正比。

摘要:

机器学习(ML)在催化领域日益普及,激发了人们利用这些技术改进催化剂设计的兴趣。本研究旨在通过将机器学习技术与可解释人工智能(XAI)相结合,弥合基于物理的研究与数据驱动方法之间的差距。具体而言,我们采用两种 XAI 技术:事后 XAI 分析和符号回归。这些技术帮助我们揭示吸附能与吸附物–催化剂体系性质之间的关联。借助 Open Catalyst Dataset(OC20)这样的大型数据集,我们将浅层机器学习技术与 XAI 方法结合使用。研究包括利用多种浅层机器学习技术预测吸附能,随后进行事后分析,以考察特征重要性、特征间相关性以及各种特征取值对吸附能预测的影响。事后分析表明,在我们的数据集中,吸附物性质比催化剂性质具有更大影响。按较高 Shapley 值排序的前五个特征为:吸附物电负性、吸附物原子数、催化剂电负性、有效配位数以及吸附物分子的原子序数之和。催化剂和吸附物电负性与吸附能预测之间呈正相关。此外,符号回归得到了与 SHAP 分析一致的结果。它推导出一个数学关系,表明催化剂电负性的平方与吸附能成正比。这些一致的相关性类似于以往研究中由基于物理的方程所得出的关系。我们的工作建立了一个将机器学习技术与 XAI 相结合的稳健框架,利用 OC20 等大型数据集,通过模型可解释性来改进催化剂设计。

英文摘要:

The increasing popularity of machine learning (ML) in catalysis has spurred interest in leveraging these techniques to enhance catalyst design. Our study aims to bridge the gap between physics-based studies and data-driven methodologies by integrating ML techniques with eXplainable AI (XAI). Specifically, we employ two XAI techniques: Post-hoc XAI analysis and Symbolic Regression. These techniques help us unravel the correlation between adsorption energy and the properties of the adsorbate-catalyst system. Leveraging a large dataset such as the Open Catalyst Dataset (OC20), we employ a combination of shallow ML techniques and XAI methodologies. Our investigation involves utilizing multiple shallow machine learning techniques to predict adsorption energy, followed by post-hoc analysis for feature importance, inter-feature correlations, and the influence of various feature values on the prediction of adsorption energy. The post-hoc analysis reveals that adsorbate properties exert a greater influence than catalyst properties in our dataset. The top five features based on higher Shapley values are adsorbate electronegativity, the number of adsorbate atoms, catalyst electronegativity, effective coordination number, and the sum of atomic numbers of the adsorbate molecule. There is a positive correlation between catalyst and adsorbate electronegativity with the prediction of adsorption energy. Additionally, symbolic regression yields results consistent with SHAP analysis. It deduces a mathematical relationship indicating that the square of the catalyst electronegativity is directly proportional to the adsorption energy. These consistent correlations resemble those derived from physics-based equations in previous research. Our work establishes a robust framework that integrates ML techniques with XAI, leveraging large datasets like OC20 to enhance catalyst design through model explainability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑