Physics-based statistical learning approach to mesoscopic model selection
Abstract
In materials science and many other research areas, models are frequently inferred without considering their generalization to unseen data. Here, we apply statistical learning using cross-validation to obtain an optimally predictive coarse-grained description of a two-dimensional kinetic nearest-neighbor Ising model with Glauber dynamics (GD) based on the stochastic Ginzburg-Landau equation (sGLE). The latter is learned from GD “training” data using a log-likelihood analysis, and its predictive ability for various complexities of the model is tested on GD “test” data independent of the data used to train the model on. Using two different error metrics, we perform a detailed analysis of the error between magnetization time trajectories simulated using the learned sGLE coarse-grained description and those obtained using the GD model. We show that both for equilibrium and out-of-equilibrium GD training trajectories, the standard phenomenological description using a quartic free energy does not always yield the most predictive coarse-grained model. Moreover, increasing the amount of training data can shift the optimal model complexity to higher values. Our results are promising in that they pave the way for the use of statistical learning as a general tool for materials modeling and discovery.
- Authors:
-
- Univ. of California, San Diego, CA (United States). Dept. of Mechanical and Aerospace Engineering
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1457240
- Alternate Identifier(s):
- OSTI ID: 1225546
- Report Number(s):
- LA-UR-15-23538
Journal ID: ISSN 1539-3755; PLEEE8; TRN: US1901323
- Grant/Contract Number:
- AC52-06NA25396; 20140013DR
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics
- Additional Journal Information:
- Journal Volume: 92; Journal Issue: 5; Journal ID: ISSN 1539-3755
- Publisher:
- American Physical Society (APS)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 36 MATERIALS SCIENCE; stochastic partial differential equations; Ginzburg-Landau equation; Ising model; statistical learning
Citation Formats
Taverniers, Soren, Haut, Terry S., Barros, Kipton, Alexander, Francis J., and Lookman, Turab. Physics-based statistical learning approach to mesoscopic model selection. United States: N. p., 2015.
Web. doi:10.1103/PhysRevE.92.053301.
Taverniers, Soren, Haut, Terry S., Barros, Kipton, Alexander, Francis J., & Lookman, Turab. Physics-based statistical learning approach to mesoscopic model selection. United States. https://doi.org/10.1103/PhysRevE.92.053301
Taverniers, Soren, Haut, Terry S., Barros, Kipton, Alexander, Francis J., and Lookman, Turab. Mon .
"Physics-based statistical learning approach to mesoscopic model selection". United States. https://doi.org/10.1103/PhysRevE.92.053301. https://www.osti.gov/servlets/purl/1457240.
@article{osti_1457240,
title = {Physics-based statistical learning approach to mesoscopic model selection},
author = {Taverniers, Soren and Haut, Terry S. and Barros, Kipton and Alexander, Francis J. and Lookman, Turab},
abstractNote = {In materials science and many other research areas, models are frequently inferred without considering their generalization to unseen data. Here, we apply statistical learning using cross-validation to obtain an optimally predictive coarse-grained description of a two-dimensional kinetic nearest-neighbor Ising model with Glauber dynamics (GD) based on the stochastic Ginzburg-Landau equation (sGLE). The latter is learned from GD “training” data using a log-likelihood analysis, and its predictive ability for various complexities of the model is tested on GD “test” data independent of the data used to train the model on. Using two different error metrics, we perform a detailed analysis of the error between magnetization time trajectories simulated using the learned sGLE coarse-grained description and those obtained using the GD model. We show that both for equilibrium and out-of-equilibrium GD training trajectories, the standard phenomenological description using a quartic free energy does not always yield the most predictive coarse-grained model. Moreover, increasing the amount of training data can shift the optimal model complexity to higher values. Our results are promising in that they pave the way for the use of statistical learning as a general tool for materials modeling and discovery.},
doi = {10.1103/PhysRevE.92.053301},
journal = {Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics},
number = 5,
volume = 92,
place = {United States},
year = {Mon Nov 09 00:00:00 EST 2015},
month = {Mon Nov 09 00:00:00 EST 2015}
}
Web of Science
Works referenced in this record:
Automated adaptive inference of phenomenological dynamical models
journal, August 2015
- Daniels, Bryan C.; Nemenman, Ilya
- Nature Communications, Vol. 6, Issue 1
Theory of phase-ordering kinetics
journal, June 1994
- Bray, A. J.
- Advances in Physics, Vol. 43, Issue 3
Nonlinear generalized Langevin equations
journal, November 1973
- Zwanzig, Robert
- Journal of Statistical Physics, Vol. 9, Issue 3
Theory of dynamic critical phenomena
journal, July 1977
- Hohenberg, P. C.; Halperin, B. I.
- Reviews of Modern Physics, Vol. 49, Issue 3
Transport, Collective Motion, and Brownian Motion
journal, March 1965
- Mori, Hazime
- Progress of Theoretical Physics, Vol. 33, Issue 3
Optimal classifiers with minimum expected error within a Bayesian framework—Part I: Discrete and Gaussian models
journal, May 2013
- Dalton, Lori A.; Dougherty, Edward R.
- Pattern Recognition, Vol. 46, Issue 5
Time‐Dependent Statistics of the Ising Model
journal, February 1963
- Glauber, Roy J.
- Journal of Mathematical Physics, Vol. 4, Issue 2
A study of a coarse-grained free energy functional for the three-dimensional Ising model
journal, November 1983
- Kaski, K.; Binder, K.; Gunton, J. D.
- Journal of Physics A: Mathematical and General, Vol. 16, Issue 16
Algorithm refinement for the stochastic Burgers’ equation
journal, April 2007
- Bell, John B.; Foo, Jasmine; Garcia, Alejandro L.
- Journal of Computational Physics, Vol. 223, Issue 1
Optimal mean-square-error calibration of classifier error estimators under Bayesian models
journal, June 2012
- Dalton, Lori A.; Dougherty, Edward R.
- Pattern Recognition, Vol. 45, Issue 6
Crystal Statistics. I. A Two-Dimensional Model with an Order-Disorder Transition
journal, February 1944
- Onsager, Lars
- Physical Review, Vol. 65, Issue 3-4
Study of cell distribution functions of the three-dimensional Ising model
journal, April 1984
- Kaski, K.; Binder, K.; Gunton, J. D.
- Physical Review B, Vol. 29, Issue 7
Observation of Structural Anisotropy and the Onset of Liquidlike Motion During the Nonthermal Melting of InSb
journal, September 2005
- Gaffney, K. J.; Lindenberg, A. M.; Larsson, J.
- Physical Review Letters, Vol. 95, Issue 12
Coarse-grained Ginzburg–Landau free energy for Lennard-Jones systems
journal, September 2000
- Gracheva, M. E.; Rickman, J. M.; Gunton, J. D.
- The Journal of Chemical Physics, Vol. 113, Issue 9
Noise propagation in hybrid models of nonlinear systems: The Ginzburg–Landau equation
journal, April 2014
- Taverniers, Søren; Alexander, Francis J.; Tartakovsky, Daniel M.
- Journal of Computational Physics, Vol. 262
Beitrag zur Theorie des Ferromagnetismus
journal, February 1925
- Ising, Ernst
- Zeitschrift für Physik, Vol. 31, Issue 1
Works referencing / citing this record:
Modeling mesoscale energy localization in shocked HMX, part I: machine-learned surrogate models for the effects of loading and void sizes
journal, December 2018
- Nassar, A.; Rai, N. K.; Sen, O.
- Shock Waves, Vol. 29, Issue 4
Multi-scale shock-to-detonation simulation of pressed energetic material: A meso-informed ignition and growth model
journal, August 2018
- Sen, O.; Rai, N. K.; Diggs, A. S.
- Journal of Applied Physics, Vol. 124, Issue 8
Effects of parametric uncertainty on multi-scale model predictions of shock response of a pressed energetic material
journal, June 2019
- Lee, Sangyup; Sen, Oishik; Rai, Nirmal Kumar
- Journal of Applied Physics, Vol. 125, Issue 23
Modeling meso-scale energy localization in shocked HMX, Part I: machine- learned surrogate model for effect of loading and void size
text, January 2018
- Nassar, Anas; Rai, Nirmal K.; Sen, Oishik
- arXiv