A Bayesian framework for adsorption energy prediction on bimetallic alloy catalysts

Abstract

For high-throughput screening of materials for heterogeneous catalysis, scaling relations provides an efficient scheme to estimate the chemisorption energies of hydrogenated species. However, conditioning on a single descriptor ignores the model uncertainty and leads to suboptimal prediction of the chemisorption energy. In this article, we extend the single descriptor linear scaling relation to a multi-descriptor linear regression models to leverage the correlation between adsorption energy of any two pair of adsorbates. With a large dataset, we use Bayesian Information Criteria (BIC) as the model evidence to select the best linear regression model. Furthermore, Gaussian Process Regression (GPR) based on the meaningful convolution of physical properties of the metal-adsorbate complex can be used to predict the baseline residual of the selected model. This integrated Bayesian model selection and Gaussian process regression, dubbed as residual learning, can achieve performance comparable to standard DFT error (0.1 eV) for most adsorbate system. For sparse and small datasets, we propose an ad hoc Bayesian Model Averaging (BMA) approach to make a robust prediction. With this Bayesian framework, we significantly reduce the model uncertainty and improve the prediction accuracy. The possibilities of the framework for high-throughput catalytic materials exploration in a realistic setting is illustrated using large and small sets of both dense and sparse simulated dataset generated from a public database of bimetallic alloys available in Catalysis-Hub.org.

Machine learning augmented predictive and generative model for rupture life in ferritic and austenitic steels

“…To ameliorate these limitations, data analytics (DA), including statistical analysis and machine learning (ML) algorithms, have emerged as powerful tools for making reliable estimations with defined risk very quickly 13 . The DA tools can, therefore, be used to construct a reliable, predictive model for creep rupture life using a range of experimental data.…”

Infusing theory into deep learning for interpretable reactivity prediction

“…In recent years, machine learning (ML) has emerged as an alternative approach to predicting the chemical reactivity of catalytic sites with either hand-crafted [13][14][15][16][17][18][19][20] or algorithm-derived features [21][22][23][24][25] . By learning correlated interactions of atoms, ions, or molecules with a substrate from a sufficient amount of ab initio data, it is possible to compute adsorption properties orders of magnitude faster than traditional practices and narrow down candidate materials prior to experimental tests 13,14,[16][17][18]22,[25][26][27][28] .…”

Ab Initio Machine Learning in Chemical Compound Space

“… 346 In 2020, QML models of competing reaction barriers and transition state geometries corresponding to S N 2 and E2 reactions in the gas phase were successfully trained and applied throughout a CCS covering thousands of reactants, 347 relying on the QMrxn data set. 348 That same year, Bligaard and co-workers employed active learning to identify stable iridium oxide polymorphs and study their usefulness for the acidic oxygen evolution reaction, 349 introduced a Bayesian framework for adsorption energies of bimetallic alloy catalyst candidates, 350 and proposed a bond information based GPR as a means to speed up structural relaxation across different types of atomic systems. 351 In 2020, neural networks have been proposed for the prediction of overpotentials relevant for heterogeneous catalyst candidates, 352 as well as a higher-order correction scheme in alchemical perturbation density functional theory applications to catalytic activity.…”