Methods for comparing uncertainty quantifications for material property predictions

Tran, Kevin; Neiswanger, Willie; Yoon, Junwoong; Zhang, Qingyang; Xing, Eric P.; Ulissi, Zachary W.

doi:10.1088/2632-2153/ab7e1a

Cited by 142 publications

(173 citation statements)

References 32 publications

Supporting

Mentioning

170

Contrasting

Order By: Relevance

“…A more general study (including GPR as well as other types of ML methods) of uncertainty quantification with relevance to physical sciences was reported in ref ( 201 ). This study also includes a didactic overview of uncertainty quantification methods.…”

Section: Validation and Accuracymentioning

confidence: 99%

Gaussian Process Regression for Materials and Molecules

et al. 2021

View full text Add to dashboard Cite

We provide an introduction to Gaussian process regression (GPR) machine-learning methods in computational materials science and chemistry. The focus of the present review is on the regression of atomistic properties: in particular, on the construction of interatomic potentials, or force fields, in the Gaussian Approximation Potential (GAP) framework; beyond this, we also discuss the fitting of arbitrary scalar, vectorial, and tensorial quantities. Methodological aspects of reference data generation, representation, and regression, as well as the question of how a data-driven model may be validated, are reviewed and critically discussed. A survey of applications to a variety of research questions in chemistry and materials science illustrates the rapid growth in the field. A vision is outlined for the development of the methodology in the years to come.

show abstract

Section: Validation and Accuracymentioning

confidence: 99%

Gaussian Process Regression for Materials and Molecules

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In some instances, prediction errors due to model inadequacy can be handled by statistical correction of predictions, which may provide a reliable uncertainty measure [20]. Various surrogate methods have been developed for the estimation of prediction uncertainty, such as bootstrap-based methods, Gaussian process regression, neural networks and deep learning ensembles [21][22][23]. Gaussian process regression has been employed to identify particular calculations within a given dataset for which the uncertainties exceed a given threshold [24,25].…”

Section: Introductionmentioning

confidence: 99%

Uncertainty quantification in classical molecular dynamics

Wan

Sinclair

Coveney

2021

Phil. Trans. R. Soc. A.

130

View full text Add to dashboard Cite

Molecular dynamics simulation is now a widespread approach for understanding complex systems on the atomistic scale. It finds applications from physics and chemistry to engineering, life and medical science. In the last decade, the approach has begun to advance from being a computer-based means of rationalizing experimental observations to producing apparently credible predictions for a number of real-world applications within industrial sectors such as advanced materials and drug discovery. However, key aspects concerning the reproducibility of the method have not kept pace with the speed of its uptake in the scientific community. Here, we present a discussion of uncertainty quantification for molecular dynamics simulation designed to endow the method with better error estimates that will enable it to be used to report actionable results. The approach adopted is a standard one in the field of uncertainty quantification, namely using ensemble methods, in which a sufficiently large number of replicas are run concurrently, from which reliable statistics can be extracted. Indeed, because molecular dynamics is intrinsically chaotic, the need to use ensemble methods is fundamental and holds regardless of the duration of the simulations performed. We discuss the approach and illustrate it in a range of applications from materials science to ligand–protein binding free energy estimation. This article is part of the theme issue ‘Reliability and reproducibility in computational science: implementing verification, validation and uncertainty quantification in silico ’.

show abstract

“…[135] Recently Tran et al comprehensively reviewed the various uncertainty quantification methods discussed above, and found that using the convolutional neural network feature in the Gaussian process provides the best uncertainty estimates. [136] Neural Network: Neural network models are typically the most flexible and the most accurate models. [101,103,104,[137][138][139][140] A neural network model can be thought of as a customized sequence of mathematical operations.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Progress in Computational and Machine‐Learning Methods for Heterogeneous Small‐Molecule Activation

Choi

Lee

et al. 2020

Advanced Materials

View full text Add to dashboard Cite

The chemical conversion of small molecules such as H2, H2O, O2, N2, CO2, and CH4 to energy and chemicals is critical for a sustainable energy future. However, the high chemical stability of these molecules poses grand challenges to the practical implementation of these processes. In this regard, computational approaches such as density functional theory, microkinetic modeling, data science, and machine learning have guided the rational design of catalysts by elucidating mechanistic insights, identifying active sites, and predicting catalytic activity. Here, the theory and methodologies for heterogeneous catalysis and their applications for small‐molecule activation are reviewed. An overview of fundamental theory and key computational methods for designing catalysts, including the emerging data science techniques in particular, is given. Applications of these methods for finding efficient heterogeneous catalysts for the activation of the aforementioned small molecules are then surveyed. Finally, promising directions of the computational catalysis field for further outlooks are discussed, focusing on the challenges and opportunities for new methods.

show abstract

Methods for comparing uncertainty quantifications for material property predictions

Cited by 142 publications

References 32 publications

Gaussian Process Regression for Materials and Molecules

Gaussian Process Regression for Materials and Molecules

Uncertainty quantification in classical molecular dynamics

Progress in Computational and Machine‐Learning Methods for Heterogeneous Small‐Molecule Activation

Contact Info

Product

Resources

About