Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia

Batra, Rohit; Pilania, Ghanshyam; Uberuaga, Blas P.; Ramprasad, Rampi

doi:10.1021/acsami.9b02174

Title: Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia

Full Record
Other Related Research

Abstract

Cost versus accuracy trade-offs are frequently encountered in materials science and engineering, where a particular property of interest can be measured/computed at different levels of accuracy or fidelity. Naturally, the most accurate measurement is also the most resource and time intensive, while the inexpensive quicker alternatives tend to be noisy. In such situations, a number of machine learning (ML) based multifidelity information fusion (MFIF) strategies can be employed to fuse information accessible from varying sources of fidelity and make predictions at the highest level of accuracy. In this work, we perform a comparative study on traditionally employed single-fidelity and three MFIF strategies, namely, (1) Δ-learning, (2) low-fidelity as a feature, and (3) multifidelity cokriging (CK) to compare their relative prediction accuracies and efficiencies for accelerated property predictions and high throughput chemical space explorations. We perform our analysis using a dopant formation energy data set for hafnia, which is a well-known high-k material and is being extensively studied for its promising ferroelectric, piezoelectric, and pyroelectric properties. We use a dopant formation energy data set of 42 dopants in hafnia—each studied in six different hafnia phases—computed at two levels of fidelities to find merits and limitations of these ML strategies. The findingsmore »« less

Authors:

^[1];

^[2];

^[3]

Georgia Inst. of Technology, Atlanta, GA (United States); Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Georgia Inst. of Technology, Atlanta, GA (United States)

Publication Date:: 2019-04-16

Research Org.:: Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Basic Energy Sciences (BES)

OSTI Identifier:: 1511635

Report Number(s):: LA-UR-19-23134
Journal ID: ISSN 1944-8244

Grant/Contract Number:: 89233218CNA000001

Resource Type:: Accepted Manuscript

Journal Name:: ACS Applied Materials and Interfaces

Additional Journal Information:: Journal Volume: 11; Journal Issue: 28; Journal ID: ISSN 1944-8244

Publisher:: American Chemical Society (ACS)

Country of Publication:: United States

Language:: English

Subject:: 36 MATERIALS SCIENCE; density functional theory; dopant formation energy; hafnia; machine learning; materials informatics; multifidelity learning

Citation Formats


                    Batra, Rohit, Pilania, Ghanshyam, Uberuaga, Blas P., and Ramprasad, Rampi. Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia.  United States: N. p., 2019. 
Web.  doi:10.1021/acsami.9b02174.

Copy to clipboard


                    Batra, Rohit, Pilania, Ghanshyam, Uberuaga, Blas P., & Ramprasad, Rampi. Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia.  United States.  https://doi.org/10.1021/acsami.9b02174

Copy to clipboard


                    Batra, Rohit, Pilania, Ghanshyam, Uberuaga, Blas P., and Ramprasad, Rampi. Tue .  
"Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia".  United States.  https://doi.org/10.1021/acsami.9b02174.  https://www.osti.gov/servlets/purl/1511635.

Copy to clipboard


                    
@article{osti_1511635,

  title        = {Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia},

  author       = {Batra, Rohit and Pilania, Ghanshyam and Uberuaga, Blas P. and Ramprasad, Rampi},

  abstractNote = {Cost versus accuracy trade-offs are frequently encountered in materials science and engineering, where a particular property of interest can be measured/computed at different levels of accuracy or fidelity. Naturally, the most accurate measurement is also the most resource and time intensive, while the inexpensive quicker alternatives tend to be noisy. In such situations, a number of machine learning (ML) based multifidelity information fusion (MFIF) strategies can be employed to fuse information accessible from varying sources of fidelity and make predictions at the highest level of accuracy. In this work, we perform a comparative study on traditionally employed single-fidelity and three MFIF strategies, namely, (1) Δ-learning, (2) low-fidelity as a feature, and (3) multifidelity cokriging (CK) to compare their relative prediction accuracies and efficiencies for accelerated property predictions and high throughput chemical space explorations. We perform our analysis using a dopant formation energy data set for hafnia, which is a well-known high-k material and is being extensively studied for its promising ferroelectric, piezoelectric, and pyroelectric properties. We use a dopant formation energy data set of 42 dopants in hafnia—each studied in six different hafnia phases—computed at two levels of fidelities to find merits and limitations of these ML strategies. The findings of this work indicate that the MFIF based learning schemes outperform the traditional SF machine learning methods, such as Gaussian process regression and CK provides an accurate, inexpensive and flexible alternative to other MFIF strategies. While the results presented here are for the case study of hafnia, they are expected to be general. Furthermore, materials discovery problems that involve huge chemical space explorations can be studied efficiently (or even made feasible in some situations) through a combination of a large number of low-fidelity and a few high-fidelity measurements/computations, in conjunction with the CK approach.},

  doi          = {10.1021/acsami.9b02174},

  journal      = {ACS Applied Materials and Interfaces},

  number       = 28,

  volume       = 11,

  place        = {United States},

  year         = {2019},

  month        = {4}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1021/acsami.9b02174

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 8 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence

Journal Article Yang, Xiu ; Barajas-Solano, David A. ; Tartakovsky, Guzel D. ; ... - Journal of Computational Physics

In this work, we propose a new Gaussian process regression (GPR)-based multifidelity method: physics-informed CoKriging (CoPhIK). In CoKriging-based multifidelity methods, the quantities of interest are modeled as linear combinations of multiple parameterized stationary Gaussian processes (GPs), and the hyperparameters of these GPs are estimated from data via optimization. In CoPhIK, we construct a GP representing low-fidelity data using physics-informed Kriging (PhIK), and model the discrepancy between low- and highfidelity data using a parameterized GP with hyperparameters identified via optimization. Our approach reduces the cost of optimization for inferring hyperparameters by incorporating partial physical knowledge. We prove that the physical constraintsmore »« less
https://doi.org/10.1016/j.jcp.2019.06.041
Multi-fidelity classification using Gaussian processes: Accelerating the prediction of large-scale computational models

Journal Article Costabal, Francisco Sahli ; Perdikaris, Paris ; Kuhl, Ellen ; ... - Computer Methods in Applied Mechanics and Engineering

We report that machine learning techniques typically rely on large datasets to create accurate classifiers. However, there are situations when data is scarce and expensive to acquire. This is the case of studies that rely on state-of-the-art computational models which typically take days to run, thus hindering the potential of machine learning tools. In this work, we present a novel classifier that takes advantage of lower fidelity models and inexpensive approximations to predict the binary output of expensive computer simulations. We postulate an autoregressive model between the different levels of fidelity with Gaussian process priors. We adopt a fully Bayesianmore »« less
Cited by 6
https://doi.org/10.1016/j.cma.2019.112602

Full Text Available
Multifidelity multiobjective optimization for wake-steering strategies

Journal Article Quick, Julian ; King, Ryan N. ; Barter, Garrett ; ... - Wind Energy Science (Online)

Abstract. Wake steering is an emerging wind power plant control strategy where upstream turbines are intentionally yawed out of perpendicular alignment with the incoming wind, thereby “steering” wakes away from downstream turbines. However, trade-offs between the gains in power production and fatigue loads induced by this control strategy are the subject of continuing investigation. In this study, we present a multifidelity multiobjective optimization approach for exploring the Pareto front of trade-offs between power and loading during wake steering. A large eddy simulation is used as the high-fidelity model, where an actuator line representation is used to model wind turbine bladesmore »« less
https://doi.org/10.5194/wes-7-1941-2022
Multifidelity computing for coupling full and reduced order models

Journal Article Ahmed, Shady E. ; San, Omer ; Kara, Kursat ; ... - PLoS ONE

Hybrid physics-machine learning models are increasingly being used in simulations of transport processes. Many complex multiphysics systems relevant to scientific and engineering applications include multiple spatiotemporal scales and comprise a multifidelity problem sharing an interface between various formulations or heterogeneous computational entities. To this end, we present a robust hybrid analysis and modeling approach combining a physics-based full order model (FOM) and a data-driven reduced order model (ROM) to form the building blocks of an integrated approach among mixed fidelity descriptions toward predictive digital twin technologies. At the interface, we introduce a long short-term memory network to bridge these highmore »« less
https://doi.org/10.1371/journal.pone.0246092

Full Text Available
Survey of Multifidelity Methods in Uncertainty Propagation, Inference, and Optimization

Journal Article Peherstorfer, Benjamin ; Willcox, Karen ; Gunzburger, Max - SIAM Review

In many situations across computational science and engineering, multiple computational models are available that describe a system of interest. These different models have varying evaluation costs and varying fidelities. Typically, a computationally expensive high-fidelity model describes the system with the accuracy required by the current application at hand, while lower-fidelity models are less accurate but computationally cheaper than the high-fidelity model. Outer-loop applications, such as optimization, inference, and uncertainty quantification, require multiple model evaluations at many different inputs, which often leads to computational demands that exceed available resources if only the high-fidelity model is used. This work surveys multifidelity methodsmore »« less
Cited by 59
https://doi.org/10.1137/16m1082469

Full Text Available

Similar Records