Active Learning for Adsorption Simulations: Evaluation, Criteria Analysis, and Recommendations for Metal–Organic Frameworks
Active Learning for Adsorption Simulations: Evaluation, Criteria Analysis, and Recommendations for Metal–Organic Frameworks
复制标题
DOI：
10.1021/acs.iecr.3c01589
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
Etinosa Osaro;K. Mukherjee;Yamil J. Colón
中科院分区：
文献类型：
--
作者：
Etinosa Osaro;K. Mukherjee;Yamil J. Colón
高通量分子模拟和机器学习（ML）已被实施，以充分筛选大量金属有机框架（MOF）用于涉及吸附的应用。事实证明，大正则蒙特卡罗 (GCMC) 模拟在计算给定压力和温度下的吸附能力方面是有效的，但它们可能需要昂贵的计算资源。虽然它们可以节省资源，但机器学习模型可能需要大量数据集，从而需要能够有效表征吸附的算法；主动学习（AL）在这方面可以发挥非常重要的作用。在这项工作中，我们利用高斯过程回归（GPR）来模拟 PCN-61、MgMOF-74 上 77 K、10-5 至 1 bar 的氮气、298 K 10-5 至 100 bar 的甲烷、298 K 10-5 至 100 bar 的二氧化碳以及 77 K 10-5 至 100 bar 的氢气的纯组分吸附。 DUT-32、DUT-49、MOF-177、NU-800、UiO-66、ZIF-8、IRMOF-1、IRMOF-10 和 IRMOF-16。 GPR 模型需要使用初始数据集（即先验数据集）对模型进行初始训练，并且在这项评估 AL 的研究中，我们使用了三种不同的先验选择方案。每个先前的方案都使用由 GP 模型不确定性产生的采样点进行更新。该协议一直持续到达到 2% 的最大 GPR 相对误差。我们主要利用平均绝对误差和模型收敛所需的总点数，对总共 44 个吸附物-吸附剂对的最佳先验选择方案提出建议。为了进一步评估 AL 框架，我们对模拟和 GP 氮等温线应用 BET 一致性标准，并比较所得表面积。
High-throughput molecular simulations and machine learning (ML) have been implemented to adequately screen a large number of metal–organic frameworks (MOFs) for applications involving adsorption. Grand canonical Monte Carlo (GCMC) simulations have proven effective in calculating the adsorption capacity at given pressures and temperatures, but they can require expensive computational resources. While they can be resource-efficient, ML models can require large datasets, creating a need for algorithms that can efficiently characterize adsorption; active learning (AL) can play a very important role in this regard. In this work, we make use of Gaussian process regression (GPR) to model pure component adsorption of nitrogen at 77 K from 10–5to 1 bar, methane at 298 K from 10–5to 100 bar, carbon dioxide at 298 K from 10–5to 100 bar, and hydrogen at 77 K from 10–5to 100 bar on PCN-61, MgMOF-74, DUT-32, DUT-49, MOF-177, NU-800, UiO-66, ZIF-8, IRMOF-1, IRMOF-10, and IRMOF-16. The GPR model requires an initial training of the model with an initial dataset, the prior one, and, in this study of evaluating AL, we make use of three different prior selection schemes. Each prior scheme is updated with a sampling point resulting from the GP model uncertainties. This protocol continues until a maximum GPR relative error of 2% is attained. We make a recommendation on the best prior selection scheme for the total 44 adsorbate–adsorbent pairs primarily making use of the mean absolute error and the total amount of points required for convergence of the model. To further evaluate the AL framework, we apply the BET consistency criteria on the simulated and GP nitrogen isotherms and compare the resulting surface areas.