Methods for comparing uncertainty quantifications for material property predictions

Tran, Kevin and Neiswanger, Willie and Yoon, Junwoong and Zhang, Qingyang and Xing, Eric and Ulissi, Zachary W (2020) Methods for comparing uncertainty quantifications for material property predictions. Machine Learning: Science and Technology, 1 (2). 025006. ISSN 2632-2153

[thumbnail of Tran_2020_Mach._Learn.__Sci._Technol._1_025006.pdf] Text
Tran_2020_Mach._Learn.__Sci._Technol._1_025006.pdf - Published Version

Download (1MB)

Abstract

Data science and informatics tools have been proliferating recently within the computational materials science and catalysis fields. This proliferation has spurned the creation of various frameworks for automated materials screening, discovery, and design. Underpinning these frameworks are surrogate models with uncertainty estimates on their predictions. These uncertainty estimates are instrumental for determining which materials to screen next, but the computational catalysis field does not yet have a standard procedure for judging the quality of such uncertainty estimates. Here we present a suite of figures and performance metrics derived from the machine learning community that can be used to judge the quality of such uncertainty estimates. This suite probes the accuracy, calibration, and sharpness of a model quantitatively. We then show a case study where we judge various methods for predicting density-functional-theory-calculated adsorption energies. Of the methods studied here, we find that the best performer is a model where a convolutional neural network is used to supply features to a Gaussian process regressor, which then makes predictions of adsorption energies along with corresponding uncertainty estimates.

Item Type: Article
Subjects: Article Archives > Multidisciplinary
Depositing User: Unnamed user with email support@articlearchives.org
Date Deposited: 29 Jun 2023 04:21
Last Modified: 19 Mar 2024 04:08
URI: http://archive.paparesearch.co.in/id/eprint/1743

Actions (login required)

View Item
View Item