Atomistic simulations play an important role in the material analysis and design by being rooted in the accurate first principles methods that free from empirical parameters and phenomenological models. However, successful applications of MD simulations largely depend on the availability of efficient and accurate force field potentials used for describing the interatomic interactions. As a powerful tool revolutionizing many areas in science and technology, machine learning techniques have gained growing attentions in the field of material science and engineering due to their potentials to accelerate the material discovery through their applications in surrogate model assisted material design. Despite tremendous advantages of employing machine learning techniques for the development of force field potentials as compared to conventional approaches, the uncertainty involved in the machine learning interpolated atomic potential energy surface has not drew much attention although it is an important issue. In this paper, the uncertainty quantification study is performed for the machine learning interpolated atomic potentials, and applied to the titanium dioxide (TiO2), an industrially relevant and well-studies material. The study results indicated that quantifying uncertainties is an indispensable task that must be performed along with the atomistic simulation process for a successful application of the machine learning based force field potentials.
Skip Nav Destination
ASME 2018 International Mechanical Engineering Congress and Exposition
November 9–15, 2018
Pittsburgh, Pennsylvania, USA
Conference Sponsors:
- ASME
ISBN:
978-0-7918-5217-0
PROCEEDINGS PAPER
Uncertainty Quantification of Artificial Neural Network Based Machine Learning Potentials
Yumeng Li,
Yumeng Li
University of Illinois at Urbana Champaign, Urbana, IL
Search for other works by this author on:
Weirong Xiao,
Weirong Xiao
University of Illinois at Urbana Champaign, Urbana, IL
Search for other works by this author on:
Pingfeng Wang
Pingfeng Wang
University of Illinois at Urbana Champaign, Urbana, IL
Search for other works by this author on:
Yumeng Li
University of Illinois at Urbana Champaign, Urbana, IL
Weirong Xiao
University of Illinois at Urbana Champaign, Urbana, IL
Pingfeng Wang
University of Illinois at Urbana Champaign, Urbana, IL
Paper No:
IMECE2018-88071, V012T11A030; 10 pages
Published Online:
January 15, 2019
Citation
Li, Y, Xiao, W, & Wang, P. "Uncertainty Quantification of Artificial Neural Network Based Machine Learning Potentials." Proceedings of the ASME 2018 International Mechanical Engineering Congress and Exposition. Volume 12: Materials: Genetics to Structures. Pittsburgh, Pennsylvania, USA. November 9–15, 2018. V012T11A030. ASME. https://doi.org/10.1115/IMECE2018-88071
Download citation file:
159
Views
Related Proceedings Papers
Related Articles
Machine Learning-Enabled Prediction of Transient Injection Map in Automotive Injectors With Uncertainty Quantification
J. Eng. Gas Turbines Power (April,2023)
Reducing Geometric Uncertainty in Computational Hemodynamics by Deep Learning-Assisted Parallel-Chain MCMC
J Biomech Eng (December,2022)
Quantifying Uncertainty in Multiscale Heat Conduction Calculations
J. Heat Transfer (November,2014)
Related Chapters
Advances in the Stochastic Modeling of Constitutive Laws at Small and Finite Strains
Advances in Computers and Information in Engineering Research, Volume 2
Expert Systems in Condition Monitoring
Tribology of Mechanical Systems: A Guide to Present and Future Technologies
Influence of Microstructure and Environment on the Fatigue Crack Growth Fracture Topography of Ti-6Al-2Sn-4Zr-2Mo-0.1Si
Fractography and Materials Science