Predicting the dissolution kinetics of silicate glasses by topology-informed machine learning

Liu, Han; Zhang, Tony; Anoop Krishnan, N. M.; Smedskjaer, Morten M.; Ryan, Joseph V.; Gin, Stéṕhane; Bauchy, Mathieu

doi:10.1038/s41529-019-0094-1

Predicting the dissolution kinetics of silicate glasses by topology-informed machine learning

Journal Article · Thu Aug 29 00:00:00 EDT 2019 · npj Materials Degradation

DOI:https://doi.org/10.1038/s41529-019-0094-1· OSTI ID:1667366

Liu, Han ^[1]; Zhang, Tony ^[2]; ^[3]; ^[4]; Ryan, Joseph V. ^[5]; ^[6]; Bauchy, Mathieu ^[2]

Univ. of California, Los Angeles, CA (United States); CEA, France
Univ. of California, Los Angeles, CA (United States)
Univ. of California, Los Angeles, CA (United States); India Inst. of Technology Delhi (India)
Aalborg Univ. (Denmark)
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Alternative Energies and Atomic Energy Commission (CEA), Bagnols-sur-Ceze (France)

Machine learning (ML) regression methods are promising tools to develop models predicting the properties of materials by learning from existing databases. However, although ML models are usually good at interpolating data, they often do not offer reliable extrapolations and can violate the laws of physics. Here, to address the limitations of traditional ML, we introduce a “topology-informed ML” paradigm—wherein some features of the network topology (rather than traditional descriptors) are used as fingerprint for ML models—and apply this method to predict the forward (stage I) dissolution rate of a series of silicate glasses. We demonstrate that relying on a topological description of the atomic network (i) increases the accuracy of the predictions, (ii) enhances the simplicity and interpretability of the predictive models, (iii) reduces the need for large training sets, and (iv) improves the ability of the models to extrapolate predictions far from their training sets. As such, topology-informed ML can overcome the limitations facing traditional ML (e.g., accuracy vs. simplicity tradeoff) and offers a promising route to predict the properties of materials in a robust fashion.

View Accepted Manuscript (DOE)

Research Organization:: Energy Frontier Research Centers (EFRC) (United States). Center for Performance and Design of Nuclear Waste Forms and Containers (WastePD); Alternative Energies and Atomic Energy Commission (CEA), Cadarache (France)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES); National Science Foundation (NSF)

Grant/Contract Number:: SC0016584

OSTI ID:: 1667366

Alternate ID(s):: OSTI ID: 23138014

Journal Information:: npj Materials Degradation, Journal Name: npj Materials Degradation Journal Issue: 1 Vol. 3; ISSN 2397-2106

Publisher:: SpringerCopyright Statement

Country of Publication:: United States

Language:: English

References (49)

Information Science for Materials Discovery and Design Lookman, Turab; Alexander, Francis J.; Rajan, Krishna Springer Series in Materials Science https://doi.org/10.1007/978-3-319-23871-5	book	January 2016
Mechanical and Compositional Design of High-Strength Corning Gorilla® Glass Onbaşlı, Mehmet C.; Tandia, Adama; Mauro, John C. Handbook of Materials Modeling https://doi.org/10.1007/978-3-319-50257-1_100-1	book	January 2018
Thermodynamic and kinetic constraints on reaction rates among minerals and aqueous solutions. II. Rate constants, effective surface area, and the hydrolysis of feldspar Helgeson, Harold C.; Murphy, William M.; Aagaard, Per Geochimica et Cosmochimica Acta, Vol. 48, Issue 12 https://doi.org/10.1016/0016-7037(84)90294-1	journal	December 1984
Topology of covalent non-crystalline solids I: Short-range order in chalcogenide alloys Phillips, J. C. Journal of Non-Crystalline Solids, Vol. 34, Issue 2 https://doi.org/10.1016/0022-3093(79)90033-4	journal	October 1979
Topology of covalent non-crystalline solids II: Medium-range order in chalcogenide alloys and ASi(Ge) Phillips, J. C. Journal of Non-Crystalline Solids, Vol. 43, Issue 1 https://doi.org/10.1016/0022-3093(81)90172-1	journal	January 1981
Diffusion-controlled reaction of water with glass Doremus, R. H. Journal of Non-Crystalline Solids, Vol. 55, Issue 1 https://doi.org/10.1016/0022-3093(83)90014-5	journal	April 1983
Dissolution of albite glass and crystal Hamilton, James P.; Pantano, Carlo G.; Brantley, Susan L. Geochimica et Cosmochimica Acta, Vol. 64, Issue 15 https://doi.org/10.1016/S0016-7037(00)00388-4	journal	August 2000
Dissolution of nepheline, jadeite and albite glasses: toward better models for aluminosilicate dissolution Hamilton, James P.; Brantley, Susan L.; Pantano, Carlo G. Geochimica et Cosmochimica Acta, Vol. 65, Issue 21 https://doi.org/10.1016/S0016-7037(01)00724-4	journal	November 2001
Effects of glass structure on the corrosion behavior of sodium-aluminosilicate glasses Hamilton, J. Journal of Non-Crystalline Solids, Vol. 222, Issue 1-2 https://doi.org/10.1016/S0022-3093(97)00395-5	journal	December 1997
Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences Gardner, M. W.; Dorling, S. R. Atmospheric Environment, Vol. 32, Issue 14-15 https://doi.org/10.1016/S1352-2310(97)00447-0	journal	August 1998
Fracture toughness anomalies: Viewpoint of topological constraint theory Bauchy, Mathieu; Wang, Bu; Wang, Mengyi Acta Materialia, Vol. 121 https://doi.org/10.1016/j.actamat.2016.09.004	journal	December 2016
Predicting glass transition temperatures using neural networks Cassar, Daniel R.; de Carvalho, André C. P. L. F.; Zanotto, Edgar D. Acta Materialia, Vol. 159 https://doi.org/10.1016/j.actamat.2018.08.022	journal	October 2018
An experimental study of the dissolution rates of simulated aluminoborosilicate waste glasses as a function of pH and temperature under dilute conditions Pierce, Eric M.; Rodriguez, Elsa A.; Calligan, L. J. Applied Geochemistry, Vol. 23, Issue 9 https://doi.org/10.1016/j.apgeochem.2008.05.006	journal	September 2008
Deciphering the atomic genome of glasses by topological constraint theory and molecular dynamics: A review Bauchy, Mathieu Computational Materials Science, Vol. 159 https://doi.org/10.1016/j.commatsci.2018.12.004	journal	March 2019
Decoding the glass genome Mauro, John C. Current Opinion in Solid State and Materials Science, Vol. 22, Issue 2 https://doi.org/10.1016/j.cossms.2017.09.001	journal	April 2018
General models for estimating daily global solar radiation for different solar radiation zones in mainland China Li, Mao-Fen; Tang, Xiao-Ping; Wu, Wei Energy Conversion and Management, Vol. 70 https://doi.org/10.1016/j.enconman.2013.03.004	journal	June 2013
Solubility of glasses in the system P2O5–CaO–MgO–Na2O–TiO2: Experimental and modeling using artificial neural networks Brauer, Delia S.; Rüssel, Christian; Kraft, Jörg Journal of Non-Crystalline Solids, Vol. 353, Issue 3 https://doi.org/10.1016/j.jnoncrysol.2006.12.005	journal	March 2007
Investigating structural features which control the dissolution of bioactive phosphate glasses: Beyond the network connectivity Christie, Jamieson K.; Ainsworth, Richard I.; de Leeuw, Nora H. Journal of Non-Crystalline Solids, Vol. 432 https://doi.org/10.1016/j.jnoncrysol.2015.01.016	journal	January 2016
Predicting the dissolution kinetics of silicate glasses using machine learning Anoop Krishnan, N. M.; Mangalathu, Sujith; Smedskjaer, Morten M. Journal of Non-Crystalline Solids, Vol. 487 https://doi.org/10.1016/j.jnoncrysol.2018.02.023	journal	May 2018
The role of the network-modifier's field-strength in the chemical durability of aluminoborate glasses Oey, Tandré; Frederiksen, Kristine F.; Mascaraque, Nerea Journal of Non-Crystalline Solids, Vol. 505 https://doi.org/10.1016/j.jnoncrysol.2018.11.019	journal	February 2019
Prediction of the Young's modulus of silicate glasses by topological constraint theory Yang, Kai; Yang, Benjamin; Xu, Xinyi Journal of Non-Crystalline Solids, Vol. 514 https://doi.org/10.1016/j.jnoncrysol.2019.03.033	journal	June 2019
Accelerating the Design of Functional Glasses through Modeling Mauro, John C.; Tandia, Adama; Vargheese, K. Deenamma Chemistry of Materials, Vol. 28, Issue 12 https://doi.org/10.1021/acs.chemmater.6b01054	journal	June 2016
Effects of Irradiation on Albite’s Chemical Durability Hsiao, Yi-Hsuan; La Plante, Erika Callagon; Krishnan, N. M. Anoop The Journal of Physical Chemistry A, Vol. 121, Issue 41 https://doi.org/10.1021/acs.jpca.7b05098	journal	September 2017
Correlating the Network Topology of Oxide Glasses with their Chemical Durability Mascaraque, Nerea; Bauchy, Mathieu; Smedskjaer, Morten M. The Journal of Physical Chemistry B, Vol. 121, Issue 5 https://doi.org/10.1021/acs.jpcb.6b11371	journal	January 2017
Dissolution Kinetics of Hot Compressed Oxide Glasses Mascaraque, Nerea; Bauchy, Mathieu; Fierro, José Luis G. The Journal of Physical Chemistry B, Vol. 121, Issue 38 https://doi.org/10.1021/acs.jpcb.7b04535	journal	September 2017
Role of Electrochemical Surface Potential and Irradiation on Garnet-Type Almandine’s Dissolution Kinetics Hsiao, Yi-Hsuan; La Plante, Erika Callagon; Krishnan, N. M. Anoop The Journal of Physical Chemistry C, Vol. 122, Issue 30 https://doi.org/10.1021/acs.jpcc.8b04459	journal	March 2018
Topological Control on Silicates’ Dissolution Kinetics Pignatelli, Isabella; Kumar, Aditya; Bauchy, Mathieu Langmuir, Vol. 32, Issue 18 https://doi.org/10.1021/acs.langmuir.6b00359	journal	April 2016
Machine learning in materials informatics: recent applications and prospects Ramprasad, Rampi; Batra, Rohit; Pilania, Ghanshyam npj Computational Materials, Vol. 3, Issue 1 https://doi.org/10.1038/s41524-017-0056-5	journal	December 2017
Structure of International Simple Glass and properties of passivating layer formed in circumneutral pH conditions Collin, Marie; Fournier, Maxime; Frugier, Pierre npj Materials Degradation, Vol. 2, Issue 1 https://doi.org/10.1038/s41529-017-0025-y	journal	February 2018
Impacts of glass composition, pH, and temperature on glass forward dissolution rate Vienna, John D.; Neeway, James J.; Ryan, Joseph V. npj Materials Degradation, Vol. 2, Issue 1 https://doi.org/10.1038/s41529-018-0042-5	journal	August 2018
Predicting the Young’s Modulus of Silicate Glasses using High-Throughput Molecular Dynamics Simulations and Machine Learning Yang, Kai; Xu, Xinyi; Yang, Benjamin Scientific Reports, Vol. 9, Issue 1 https://doi.org/10.1038/s41598-019-45344-3	journal	June 2019
Direct Experimental Evidence for Differing Reactivity Alterations of Minerals following Irradiation: The Case of Calcite and Quartz Pignatelli, Isabella; Kumar, Aditya; Field, Kevin G. Scientific Reports, Vol. 6, Issue 1 https://doi.org/10.1038/srep20155	journal	January 2016
Composition dependence of glass transition temperature and fragility. I. A topological model incorporating temperature-dependent constraints Gupta, Prabhat K.; Mauro, John C. The Journal of Chemical Physics, Vol. 130, Issue 9 https://doi.org/10.1063/1.3077168	journal	March 2009
Composition dependence of glass transition temperature and fragility. II. A topological model of alkali borate liquids Mauro, John C.; Gupta, Prabhat K.; Loucks, Roger J. The Journal of Chemical Physics, Vol. 130, Issue 23 https://doi.org/10.1063/1.3152432	journal	June 2009
Structural, vibrational, and elastic properties of a calcium aluminosilicate glass from molecular dynamics simulations: The role of the potential Bauchy, M. The Journal of Chemical Physics, Vol. 141, Issue 2 https://doi.org/10.1063/1.4886421	journal	July 2014
Structure of boroaluminosilicate glasses: Impact of [Al 2 O 3 ]/[SiO 2 ] ratio on the structural role of sodium Zheng, Q. J.; Youngman, R. E.; Hogue, C. L. Physical Review B, Vol. 86, Issue 5 https://doi.org/10.1103/PhysRevB.86.054203	journal	August 2012
Prediction of Glass Hardness Using Temperature-Dependent Constraint Theory Smedskjaer, Morten M.; Mauro, John C.; Yue, Yuanzheng Physical Review Letters, Vol. 105, Issue 11 https://doi.org/10.1103/PhysRevLett.105.115503	journal	September 2010
Topological Control on the Structural Relaxation of Atomic Networks under Stress Bauchy, Mathieu; Wang, Mengyi; Yu, Yingtian Physical Review Letters, Vol. 119, Issue 3 https://doi.org/10.1103/PhysRevLett.119.035502	journal	July 2017
Current Understanding and Remaining Challenges in Modeling Long-Term Degradation of Borosilicate Nuclear Waste Glasses Vienna, John D.; Ryan, Joseph V.; Gin, Stéphane International Journal of Applied Glass Science, Vol. 4, Issue 4 https://doi.org/10.1111/ijag.12050	journal	November 2013
Durable Glass for Thousands of Years Jantzen, Carol M.; Brown, Kevin G.; Pickett, John B. International Journal of Applied Glass Science, Vol. 1, Issue 1 https://doi.org/10.1111/j.2041-1294.2010.00007.x	journal	March 2010
Topological controls on the dissolution kinetics of glassy aluminosilicates Oey, Tandré; Kumar, Aditya; Pignatelli, Isabella Journal of the American Ceramic Society, Vol. 100, Issue 12 https://doi.org/10.1111/jace.15122	journal	August 2017
Structure-property relationships from universal signatures of plasticity in disordered solids Cubuk, E. D.; Ivancic, R. J. S.; Schoenholz, S. S. Science, Vol. 358, Issue 6366 https://doi.org/10.1126/science.aai8830	journal	November 2017
Nuclear Waste Glasses - How Durable? Grambow, B. Elements, Vol. 2, Issue 6 https://doi.org/10.2113/gselements.2.6.357	journal	December 2006
Accuracy vs. Simplicity: A Complex Trade-Off Aragones, Enriqueta; Gilboa, Itzhak; Postlewaite, Andrew SSRN Electronic Journal https://doi.org/10.2139/ssrn.332382	journal	January 2002
Rate controls on silicate dissolution in cementitious environments Oey, Tandre; Hsiao, Yi-Hsuan; Callagon, Erika RILEM Technical Letters, Vol. 2 https://doi.org/10.21809/rilemtechlett.2017.35	journal	September 2017
Thermodynamic and kinetic constraints on reaction rates among minerals and aqueous solutions; I, Theoretical considerations Aagaard, P.; Helgeson, H. C. American Journal of Science, Vol. 282, Issue 3 https://doi.org/10.2475/ajs.282.3.237	journal	March 1982
Structural, vibrational, and elastic properties of a calcium aluminosilicate glass from molecular dynamics simulations: the role of the potential Bauchy, M. arXiv https://doi.org/10.48550/arxiv.1403.1640	text	January 2014
Direct Experimental Evidence for Differing Reactivity Alterations of Minerals following Irradiation: The Case of Calcite and Quartz Pignatelli, Isabella; Kumar, Aditya; Field, Kevin G. arXiv https://doi.org/10.48550/arxiv.1509.01728	preprint	January 2015
Predicting the dissolution kinetics of silicate glasses using machine learning Krishnan, N. M. Anoop; Mangalathu, Sujith; Smedskjaer, Morten M. arXiv https://doi.org/10.48550/arxiv.1712.06018	text	January 2017

Similar Records

Explainability and extrapolation of machine learning models for predicting the glass transition temperature of polymers

Journal Article · Sat Dec 09 23:00:00 EST 2023 · Journal of Polymer Science · OSTI ID:2580641

Can a simple topological-constraints-based model predict the initial dissolution rate of borosilicate and aluminosilicate glasses?

Journal Article · Mon Mar 16 00:00:00 EDT 2020 · npj Materials Degradation · OSTI ID:1667367

Reliable extrapolation of deep neural operators informed by physics or sparse observations

Journal Article · Tue May 02 00:00:00 EDT 2023 · Computer Methods in Applied Mechanics and Engineering · OSTI ID:1991293

Related Subjects

36 MATERIALS SCIENCE
condensed-matter physics
glasses

Predicting the dissolution kinetics of silicate glasses by topology-informed machine learning

Citation Formats

References (49)

Similar Records

Related Subjects