Multi-reward reinforcement learning based development of inter-atomic potential models for silica

Koneru, Aditya; Chan, Henry; Manna, Sukriti; Loeffler, Troy D.; Dhabal, Debdas; Bertolazzo, Andressa A.; Molinero, Valeria; Sankaranarayanan, Subramanian K. R. S.

doi:10.1038/s41524-023-01074-9

Title: Multi-reward reinforcement learning based development of inter-atomic potential models for silica

Journal Article · 17 July 2023 · npj Computational Materials

DOI: https://doi.org/10.1038/s41524-023-01074-9 · OSTI ID:1991131

Koneru, Aditya;

; Manna, Sukriti; Loeffler, Troy D.;

;

; Molinero, Valeria;

Abstract Silica is an abundant and technologically attractive material. Due to the structural complexities of silica polymorphs coupled with subtle differences in Si–O bonding characteristics, the development of accurate models to predict the structure, energetics and properties of silica polymorphs remain challenging. Current models for silica range from computationally efficient Buckingham formalisms (BKS, CHIK, Soules) to reactive (ReaxFF) and more recent machine-learned potentials that are flexible but computationally costly. Here, we introduce an improved formalism and parameterization of BKS model via a multireward reinforcement learning (RL) using an experimental training dataset. Our model concurrently captures the structure, energetics, density, equation of state, and elastic constants of quartz (equilibrium) as well as 20 other metastable silica polymorphs. We also assess its ability in capturing amorphous properties and highlight the limitations of the BKS-type functional forms in simultaneously capturing crystal and amorphous properties. We demonstrate ways to improve model flexibility and introduce a flexible formalism, machine-learned ML-BKS, that outperforms existing empirical models and is on-par with the recently developed 50 to 100 times more expensive Gaussian approximation potential (GAP) in capturing the experimental structure and properties of silica polymorphs and amorphous silica.

View Journal Article

Cite

Export

Save

Research Organization:: Argonne National Laboratory (ANL), Argonne, IL (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)

Grant/Contract Number:: AC02-05CH11231; AC02-06CH11357; SC0020201; SC0023213

OSTI ID:: 1991131

Journal Information:: npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 9; ISSN 2057-3960

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (69)

Impact of Organic Templates on the Selective Formation of Zeolite Oligomers Ciantar, Marine; Trinh, Thuat T.; Michel, Carine Angewandte Chemie, Vol. 133, Issue 13 https://doi.org/10.1002/ange.202014027	journal	January 2021
Hierarchical Nanomanufacturing: From Shaped Zeolite Nanoparticles to High-Performance Separation Membranes Snyder, Mark A.; Tsapatsis, Michael Angewandte Chemie International Edition, Vol. 46, Issue 40, p. 7560-7573 https://doi.org/10.1002/anie.200604910	journal	October 2007
Gas Storage in Nanoporous Materials Morris, Russell E.; Wheatley, Paul S. Angewandte Chemie International Edition, Vol. 47, Issue 27 https://doi.org/10.1002/anie.200703934	journal	June 2008
Automatic parameterization of force field by systematic search and genetic algorithms Wang, Junmei; Kollman, Peter A. Journal of Computational Chemistry, Vol. 22, Issue 12 https://doi.org/10.1002/jcc.1079	journal	January 2001
Fast Parallel Algorithms for Short-Range Molecular Dynamics Plimpton, Steve Journal of Computational Physics, Vol. 117, Issue 1 https://doi.org/10.1006/jcph.1995.1039	journal	March 1995
Thermodynamic properties of quartz, cristobalite and amorphous SiO2: drop calorimetry measurements between 1000 and 1800 K and a review from 0 to 2000 K Richet, P.; Bottinga, Y.; Denielou, L. Geochimica et Cosmochimica Acta, Vol. 46, Issue 12 https://doi.org/10.1016/0016-7037(82)90383-0	journal	December 1982
Zeolite membranes – state of their development and perspective Caro, J.; Noack, M.; Kölsch, P. Microporous and Mesoporous Materials, Vol. 38, Issue 1 https://doi.org/10.1016/S1387-1811(99)00295-4	journal	July 2000
Photocatalytic activities of the nano-sized TiO2-supported Y-zeolites Anandan, Sambandam; Yoon, Minjoong Journal of Photochemistry and Photobiology C: Photochemistry Reviews, Vol. 4, Issue 1 https://doi.org/10.1016/S1389-5567(03)00002-9	journal	April 2003
A hybrid real-parameter genetic algorithm for function optimization Hwang, Shun-Fa; He, Rong-Song Advanced Engineering Informatics, Vol. 20, Issue 1 https://doi.org/10.1016/j.aei.2005.09.001	journal	January 2006
Machine learning for the design and discovery of zeolites and porous crystalline materials Gandhi, Akhilesh; Hasan, M. M. Faruque Current Opinion in Chemical Engineering, Vol. 35 https://doi.org/10.1016/j.coche.2021.100739	journal	March 2022
Interatomic potential for Si–O systems using Tersoff parameterization Munetoh, Shinji; Motooka, Teruaki; Moriguchi, Koji Computational Materials Science, Vol. 39, Issue 2 https://doi.org/10.1016/j.commatsci.2006.06.010	journal	April 2007
LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales Thompson, Aidan P.; Aktulga, H. Metin; Berger, Richard Computer Physics Communications, Vol. 271 https://doi.org/10.1016/j.cpc.2021.108171	journal	February 2022
Structural solution using molecular dynamics: Fundamentals and a case study of epoxy-silica interface Büyüköztürk, Oral; Buehler, Markus J.; Lau, Denvid International Journal of Solids and Structures, Vol. 48, Issue 14-15 https://doi.org/10.1016/j.ijsolstr.2011.03.018	journal	July 2011
An automated analysis workflow for optimization of force-field parameters using neutron scattering data Lynch, Vickie E.; Borreguero, Jose M.; Bhowmik, Debsindhu Journal of Computational Physics, Vol. 340 https://doi.org/10.1016/j.jcp.2017.03.045	journal	July 2017
Molecular dynamics simulations of vitreous silica structures Takada, A.; Richet, P.; Catlow, C. R. A. Journal of Non-Crystalline Solids, Vol. 345-346 https://doi.org/10.1016/j.jnoncrysol.2004.08.247	journal	October 2004
Silica molecular dynamic force fields—A practical assessment Soules, Thomas F.; Gilmer, George H.; Matthews, Manyalibo J. Journal of Non-Crystalline Solids, Vol. 357, Issue 6 https://doi.org/10.1016/j.jnoncrysol.2011.01.009	journal	March 2011
Zeolite membranes – Recent developments and progress Caro, Juergen; Noack, Manfred Microporous and Mesoporous Materials, Vol. 115, Issue 3, p. 215-233 https://doi.org/10.1016/j.micromeso.2008.03.008	journal	November 2008
First principles phonon calculations in materials science Togo, Atsushi; Tanaka, Isao Scripta Materialia, Vol. 108 https://doi.org/10.1016/j.scriptamat.2015.07.021	journal	November 2015
Pressure-induced phase transformation in β-eucryptite: An X-ray diffraction and density functional theory study Chen, Yachao; Manna, Sukriti; Narayanan, Badri Scripta Materialia, Vol. 122 https://doi.org/10.1016/j.scriptamat.2016.05.005	journal	September 2016
Enhanced Particle Swarm Optimization Algorithm: Efficient Training of ReaxFF Reactive Force Fields Furman, David; Carmeli, Benny; Zeiri, Yehuda Journal of Chemical Theory and Computation, Vol. 14, Issue 6 https://doi.org/10.1021/acs.jctc.7b01272	journal	May 2018
How Ion Condensation Occurs at a Charged Surface: A Molecular Dynamics Investigation of the Stern Layer for Water–Silica Interfaces Hocine, Sarah; Hartkamp, Remco; Siboulet, Bertrand The Journal of Physical Chemistry C, Vol. 120, Issue 2 https://doi.org/10.1021/acs.jpcc.5b08836	journal	January 2016
Development of a Modified Embedded Atom Force Field for Zirconium Nitride Using Multi-Objective Evolutionary Optimization Narayanan, Badri; Sasikumar, Kiran; Mei, Zhi-Gang The Journal of Physical Chemistry C, Vol. 120, Issue 31 https://doi.org/10.1021/acs.jpcc.6b05296	journal	July 2016
Machine Learning Classical Interatomic Potentials for Molecular Dynamics from First-Principles Training Data Chan, Henry; Narayanan, Badri; Cherukara, Mathew J. The Journal of Physical Chemistry C, Vol. 123, Issue 12 https://doi.org/10.1021/acs.jpcc.8b09917	journal	January 2019
Multi-reward Reinforcement Learning Based Bond-Order Potential to Study Strain-Assisted Phase Transitions in Phosphorene Koneru, Aditya; Batra, Rohit; Manna, Sukriti The Journal of Physical Chemistry Letters, Vol. 13, Issue 7 https://doi.org/10.1021/acs.jpclett.1c03551	journal	February 2022
Ab Initio -Based Bond Order Potential to Investigate Low Thermal Conductivity of Stanene Nanostructures Cherukara, Mathew J.; Narayanan, Badri; Kinaci, Alper The Journal of Physical Chemistry Letters, Vol. 7, Issue 19 https://doi.org/10.1021/acs.jpclett.6b01562	journal	September 2016
Methanol to Olefins (MTO): From Fundamentals to Commercialization Tian, Peng; Wei, Yingxu; Ye, Mao ACS Catalysis, Vol. 5, Issue 3 https://doi.org/10.1021/acscatal.5b00007	journal	February 2015
Thermochemistry of Microporous and Mesoporous Materials Navrotsky, Alexandra; Trofymluk, Olga; Levchenko, Andrey A. Chemical Reviews, Vol. 109, Issue 9 https://doi.org/10.1021/cr800495t	journal	September 2009
From Microporous to Mesoporous Molecular Sieve Materials and Their Use in Catalysis Corma, Avelino Chemical Reviews, Vol. 97, Issue 6, p. 2373-2420 https://doi.org/10.1021/cr960406n	journal	October 1997
General Multiobjective Force Field Optimization Framework, with Application to Reactive Force Fields for Silicon Carbide Jaramillo-Botero, Andres; Naserifar, Saber; Goddard, William A. Journal of Chemical Theory and Computation, Vol. 10, Issue 4 https://doi.org/10.1021/ct5001044	journal	March 2014
Pore-Size Engineering of Zeolite A for the Size/Shape Selective Molecular Separation Chudasama, Chintansinh D.; Sebastian, Jince; Jasra, Raksh V. Industrial & Engineering Chemistry Research, Vol. 44, Issue 6 https://doi.org/10.1021/ie049333l	journal	February 2005
Photocatalytic Reduction of CO ₂ with H ₂ O on Ti−β Zeolite Photocatalysts: Effect of the Hydrophobic and Hydrophilic Properties Ikeue, Keita; Yamashita, Hiromi; Anpo, Masakazu The Journal of Physical Chemistry B, Vol. 105, Issue 35 https://doi.org/10.1021/jp010885g	journal	September 2001
Thermodynamics of Pure-Silica Molecular Sieve Synthesis Piccione, Patrick M.; Yang, Sanyuan; Navrotsky, Alexandra The Journal of Physical Chemistry B, Vol. 106, Issue 14 https://doi.org/10.1021/jp014427j	journal	April 2002
Structures and Fragmentations of Small Silicon Oxide Clusters by ab Initio Calculations Lu, W. C.; Wang, C. Z.; Nguyen, V. The Journal of Physical Chemistry A, Vol. 107, Issue 36 https://doi.org/10.1021/jp027860h	journal	August 2003
Rings and Strain in Pure Silica Zeolites Sastre, German; Corma, Avelino The Journal of Physical Chemistry B, Vol. 110, Issue 36 https://doi.org/10.1021/jp060505x	journal	August 2006
Potential Functions for Silica and Zeolite Catalysts Based on ab Initio Calculations. 3. A Shell Model Ion Pair Potential for Silica and Aluminosilicates Schröder, Klaus-Peter; Sauer, Joachim The Journal of Physical Chemistry, Vol. 100, Issue 26 https://doi.org/10.1021/jp953405s	journal	January 1996
The active site of low-temperature methane hydroxylation in iron-containing zeolites Snyder, Benjamin E. R.; Vanelderen, Pieter; Bols, Max L. Nature, Vol. 536, Issue 7616 https://doi.org/10.1038/nature19059	journal	August 2016
Mild oxidation of methane to methanol or acetic acid on supported isolated rhodium catalysts Shan, Junjun; Li, Mengwei; Allard, Lawrence F. Nature, Vol. 551, Issue 7682 https://doi.org/10.1038/nature24640	journal	November 2017
Learning in continuous action space for developing high dimensional potential energy models Manna, Sukriti; Loeffler, Troy D.; Batra, Rohit Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-021-27849-6	journal	January 2022
Multi-objective parametrization of interatomic potentials for large deformation pathways and fracture of two-dimensional materials Zhang, Xu; Nguyen, Hoang; Paci, Jeffrey T. npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-021-00573-x	journal	July 2021
A machine-learned interatomic potential for silica and its relation to empirical models Erhard, Linus C.; Rohrer, Jochen; Albe, Karsten npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00768-w	journal	April 2022
Emerging materials intelligence ecosystems propelled by machine learning Batra, Rohit; Song, Le; Ramprasad, Rampi Nature Reviews Materials https://doi.org/10.1038/s41578-020-00255-y	journal	November 2020
A database of low-energy atomically precise nanoclusters Manna, Sukriti; Wang, Yunzhe; Hernandez, Alberto Scientific Data, Vol. 10, Issue 1 https://doi.org/10.1038/s41597-023-02200-4	journal	May 2023
Modeling and scale-bridging using machine learning: nanoconfinement effects in porous media Lubbers, Nicholas; Agarwal, Animesh; Chen, Yu Scientific Reports, Vol. 10, Issue 1 https://doi.org/10.1038/s41598-020-69661-0	journal	August 2020
Simulating the properties of small pore silicazeolites using interatomic potentials Combariza, Aldo F.; Gomez, Diego A.; Sastre, German Chem. Soc. Rev., Vol. 42, Issue 1 https://doi.org/10.1039/C2CS35243E	journal	January 2013
Machine learning a bond order potential model to study thermal transport in WSe ₂ nanostructures Chan, Henry; Sasikumar, Kiran; Srinivasan, Srilok Nanoscale, Vol. 11, Issue 21 https://doi.org/10.1039/C9NR02873K	journal	January 2019
Role of Repulsive Forces in Determining the Equilibrium Structure of Simple Liquids Weeks, John D.; Chandler, David; Andersen, Hans C. The Journal of Chemical Physics, Vol. 54, Issue 12 https://doi.org/10.1063/1.1674820	journal	June 1971
A reactive molecular dynamics simulation of the silica-water interface Fogarty, Joseph C.; Aktulga, Hasan Metin; Grama, Ananth Y. The Journal of Chemical Physics, Vol. 132, Issue 17 https://doi.org/10.1063/1.3407433	journal	May 2010
New optimization scheme to obtain interaction potentials for oxide glasses Sundararaman, Siddharth; Huang, Liping; Ispas, Simona The Journal of Chemical Physics, Vol. 148, Issue 19 https://doi.org/10.1063/1.5023707	journal	May 2018
Exploring the landscape of Buckingham potentials for silica by machine learning: Soft vs hard interatomic forcefields Liu, Han; Li, Yipeng; Fu, Zipeng The Journal of Chemical Physics, Vol. 152, Issue 5 https://doi.org/10.1063/1.5136041	journal	February 2020
Interatomic potential parameterization using particle swarm optimization: Case study of glassy silica Christensen, Rasmus; Sørensen, Søren S.; Liu, Han The Journal of Chemical Physics, Vol. 154, Issue 13 https://doi.org/10.1063/5.0041183	journal	April 2021
Machine learning meets chemical physics Ceriotti, Michele; Clementi, Cecilia; Anatole von Lilienfeld, O. The Journal of Chemical Physics, Vol. 154, Issue 16 https://doi.org/10.1063/5.0051418	journal	April 2021
Molecular dynamics simulations of liquid silica crystallization Niu, Haiyang; Piaggi, Pablo M.; Invernizzi, Michele Proceedings of the National Academy of Sciences, Vol. 115, Issue 21 https://doi.org/10.1073/pnas.1803919115	journal	May 2018
Machine-learning of piezoelectric coefficients for wurtzite crystals Manna, Sukriti; Wang, Mingyuan; Barbu, Adrian Materials and Manufacturing Processes https://doi.org/10.1080/10426914.2023.2219308	journal	May 2023
Phonon dispersion branches in α quartz Dorner, B.; Grimm, H.; Rzany, H. Journal of Physics C: Solid State Physics, Vol. 13, Issue 36 https://doi.org/10.1088/0022-3719/13/36/014	journal	December 1980
A Simplex Method for Function Minimization Nelder, J. A.; Mead, R. The Computer Journal, Vol. 7, Issue 4 https://doi.org/10.1093/comjnl/7.4.308	journal	January 1965
Silica glass structure generation for ab initio calculations using small samples of amorphous silica Van Ginhoven, Renée M.; Jónsson, Hannes; Corrales, L. René Physical Review B, Vol. 71, Issue 2 https://doi.org/10.1103/PhysRevB.71.024208	journal	January 2005
First-principles-based embedded atom method for PdAu nanoparticles Shan, Bin; Wang, Ligen; Yang, Sang Physical Review B, Vol. 80, Issue 3 https://doi.org/10.1103/PhysRevB.80.035404	journal	July 2009
Force fields for silicas and aluminophosphates based on ab initio calculations van Beest, B. W. H.; Kramer, G. J.; van Santen, R. A. Physical Review Letters, Vol. 64, Issue 16 https://doi.org/10.1103/PhysRevLett.64.1955	journal	April 1990
Morse Stretch Potential Charge Equilibrium Force Field for Ceramics: Application to the Quartz-Stishovite Phase Transition and to Silica Glass Demiralp, Ersan; Çağin, Tahir; Goddard, William A. Physical Review Letters, Vol. 82, Issue 8 https://doi.org/10.1103/PhysRevLett.82.1708	journal	February 1999
Structure of Liquid SiO 2 : A Measurement by High-Energy X-Ray Diffraction Mei, Q.; Benmore, C. J.; Weber, J. K. R. Physical Review Letters, Vol. 98, Issue 5 https://doi.org/10.1103/PhysRevLett.98.057802	journal	February 2007
The structure of vitreous silica Mozzi, R. L.; Warren, B. E. Journal of Applied Crystallography, Vol. 2, Issue 4 https://doi.org/10.1107/S0021889869006868	journal	October 1969
The merits of velocity clamping particle swarm optimisation in high dimensional spaces Oldewage, Elre T.; Engelbrecht, Andries P.; Cleghorn, Christopher W. 2017 IEEE Symposium Series on Computational Intelligence (SSCI) https://doi.org/10.1109/SSCI.2017.8280887	conference	November 2017
Thermal regimes of Li‐ion conductivity in β‐eucryptite Chen, Yachao; Manna, Sukriti; Ciobanu, Cristian V. Journal of the American Ceramic Society, Vol. 101, Issue 1 https://doi.org/10.1111/jace.15173	journal	September 2017
Application of zeolites in aquaculture industry: a review Ghasemi, Zahra; Sourinejad, Iman; Kazemian, Hossein Reviews in Aquaculture, Vol. 10, Issue 1 https://doi.org/10.1111/raq.12148	journal	February 2016
Ultrathin ZSM-5 zeolite nanosheet laminated membrane for high-flux desalination of concentrated brines Cao, Zishu; Zeng, Shixuan; Xu, Zhi Science Advances, Vol. 4, Issue 11 https://doi.org/10.1126/sciadv.aau8634	journal	November 2018
Merocyanine 540 as an optical probe of transmembrane electrical activity in the heart Salama, G.; Morad, M. Science, Vol. 191, Issue 4226, p. 485-487 https://doi.org/10.1126/science.1082169	journal	March 2003
“Ab initio” synthesis of zeolites for preestablished catalytic reactions Gallego, Eva María; Portilla, M. Teresa; Paris, Cecilia Science, Vol. 355, Issue 6329 https://doi.org/10.1126/science.aal0121	journal	March 2017
Machine Learning for Molecular Simulation Noé, Frank; Tkatchenko, Alexandre; Müller, Klaus-Robert Annual Review of Physical Chemistry, Vol. 71, Issue 1 https://doi.org/10.1146/annurev-physchem-042018-052331	journal	April 2020
New fitting scheme to obtain effective potential from Car-Parrinello molecular-dynamics simulations: Application to silica Carré, A.; Horbach, J.; Ispas, S. EPL (Europhysics Letters), Vol. 82, Issue 1 https://doi.org/10.1209/0295-5075/82/17001	journal	March 2008

Similar Records

Machine Learning a Simple Interpretable Short-Range Potential for Silica

Journal Article · 2024 · Journal of Chemical Theory and Computation · OSTI ID:2568018

Koneru, Aditya; Chan, Henry; Manna, Sukriti; +3 more

Multi-reward Reinforcement Learning Based Bond-Order Potential to Study Strain-Assisted Phase Transitions in Phosphorene

Journal Article · 2022 · Journal of Physical Chemistry Letters · OSTI ID:1894218

Koneru, Aditya; Batra, Rohit; Manna, Sukriti; +7 more

Hierarchical Reinforcement Learning of a Short-Range Bond-Order Potential for Silica: Analytic Embedding of Coordination with Classical Efficiency

Journal Article · 2026 · Journal of Chemical Theory and Computation · OSTI ID:3363025

Koneru, Aditya; Chan, Henry; Molinero, Valeria; +1 more

Related Subjects

36 MATERIALS SCIENCE
Atomistic models
Computational methods

Title: Multi-reward reinforcement learning based development of inter-atomic potential models for silica

Citation Formats

References (69)

Similar Records

Related Subjects