A deep learning-based potential developed for calcium silicate hydrates with both high accuracy and efficiency

References

• Monteiro PJM, Miller SA, Horvath A. Towards sustainable concrete. Nat Mater. 2017;16(7):698–699.
   PubMed Web of Science ®Google Scholar
• Scrivener KL, John VM, Gartner EM. Eco-efficient cements: potential economically viable solutions for a low-CO2 cement-based materials industry. Cem Concr Res. 2018;114:2–26.
   Web of Science ®Google Scholar
• Al-Ostaz A, Wu W, Cheng AHD, et al. A molecular dynamics and microporomechanics study on the mechanical properties of major constituents of hydrated cement. Compos B: Eng. 2010;41(7):543–549.
   Web of Science ®Google Scholar
• Miao CW. The influence of high performance concrete on low-carbon economy. AMR. 2011;374–377:1646–1656.
   Google Scholar
• Shi Y, Long G, Ma C, et al. Design and preparation of ultra-high performance concrete with low environmental impact. J Cleaner Prod. 2019;214:633–643.
   Web of Science ®Google Scholar
• Mehta PK, Monteiro PJM. Concrete: microstructure, properties, and material. 4th ed. New York: McGraw-Hill Education; 2014.
   Google Scholar
• Richardson IG. The calcium silicate hydrates. Cem Concr Res. 2008;38(2):137–158.
   Web of Science ®Google Scholar
• Pellenq RJ, Kushima A, Shahsavari R, et al. A realistic molecular model of cement hydrates. Proc Natl Acad Sci USA. 2009;106(38):16102–16107.
   PubMed Web of Science ®Google Scholar
• Puertas F, Palacios M, Manzano H, et al. A model for the C-A-S-H gel formed in alkali-activated slag cements. J Eur Ceram Soc. 2011;31(12):2043–2056.
   Web of Science ®Google Scholar
• Abdolhosseini Qomi MJ, Krakowiak KJ, Bauchy M, et al. Combinatorial molecular optimization of cement hydrates. Nat Commun. 2014;5(1):4960.
   PubMedGoogle Scholar
• Kovačević G, Persson B, Nicoleau L, et al. Atomistic modeling of crystal structure of Ca 1.67 SiH x. Cem Concr Res. 2015;67:197–203.
   Web of Science ®Google Scholar
• Kumar A, Walder BJ, Kunhi Mohamed A, et al. The atomic-level structure of cementitious calcium silicate hydrate. J Phys Chem C. 2017;121(32):17188–17196.
   Web of Science ®Google Scholar
• Kunhi Mohamed A, Parker SC, Bowen P, et al. An atomistic building block description of C-S-H – towards a realistic C-S-H model. Cem Concr Res. 2018;107:221–235.
   Web of Science ®Google Scholar
• Kunhi Mohamed A, Moutzouri P, Berruyer P, et al. The atomic-level structure of cementitious calcium aluminate silicate hydrate. J Am Chem Soc. 2020;142(25):11060–11071.
   PubMed Web of Science ®Google Scholar
• Valavi M, Casar Z, Kunhi Mohamed A, et al. Molecular dynamic simulations of cementitious systems using a newly developed force field suite ERICA FF. Cem Concr Res. 2022;154:106712.
   Web of Science ®Google Scholar
• Cygan RT, Liang J-J, Kalinichev AG. Molecular models of hydroxide, oxyhydroxide, and clay phases and the development of a general force field. J Phys Chem B. 2004;108(4):1255–1266.
   Web of Science ®Google Scholar
• Kalinichev AG, Wang J, Kirkpatrick RJ. Molecular dynamics modeling of the structure, dynamics and energetics of mineral–water interfaces: application to cement materials. Cem Concr Res. 2007;37(3):337–347.
   Web of Science ®Google Scholar
• Cygan RT, Greathouse JA, Heinz H, et al. Molecular models and simulations of layered materials. J Mater Chem. 2009;19(17):2470.
   Web of Science ®Google Scholar
• Zhou Y, Hou D, Jiang J, et al. Chloride ions transport and adsorption in the nano-pores of silicate calcium hydrate: experimental and molecular dynamics studies. Constr Build Mater. 2016;126:991–1001.
   Web of Science ®Google Scholar
• Shahsavari R, Pellenq RJ, Ulm FJ. Empirical force fields for complex hydrated calcio-silicate layered materials. Phys Chem Chem Phys. 2011;13(3):1002–1011.
   PubMed Web of Science ®Google Scholar
• Qomi MJ, Bauchy M, Ulm FJ, et al. Anomalous composition-dependent dynamics of nanoconfined water in the interlayer of disordered calcium-silicates. J Chem Phys. 2014;140(5):054515.
   PubMed Web of Science ®Google Scholar
• Morshedifard A, Masoumi S, Abdolhosseini Qomi MJ. Nanoscale origins of creep in calcium silicate hydrates. Nat Commun. 2018;9(1):1785.
   PubMedGoogle Scholar
• Manzano H, Pellenq RJ, Ulm FJ, et al. Hydration of calcium oxide surface predicted by reactive force field molecular dynamics. Langmuir. 2012;28(9):4187–4197.
   PubMed Web of Science ®Google Scholar
• Manzano H, Masoero E, Lopez-Arbeloa I, et al. 2013. Mechanical behaviour of ordered and disordered calcium silicate hydrates under shear strain studied by atomic scale simulations. Mechanics and Physics of Creep, Shrinkage, and Durability of Concrete.
   Google Scholar
• Bauchy M, Qomi MJ, Ulm FJ, et al. Order and disorder in calcium-silicate-hydrate. J Chem Phys. 2014;140(21):214503.
   PubMed Web of Science ®Google Scholar
• Hou D, Zhu Y, Lu Y, et al. Mechanical properties of calcium silicate hydrate (C–S–H) at nano-scale: a molecular dynamics study. Mater Chem Phys. 2014;146(3):503–511.
   Web of Science ®Google Scholar
• Mishra RK, Mohamed AK, Geissbühler D, et al. Cemff: a force field database for cementitious materials including validations, applications and opportunities. Cem Concr Res. 2017;102:68–89.
   Web of Science ®Google Scholar
• Schleder GR, Padilha ACM, Acosta CM, et al. From DFT to machine learning: recent approaches to materials science–a review. J. Phys. Mater. 2019;2(3):032001.
   Google Scholar
• Shahsavari R, Buehler MJ, Pellenq RJM, et al. First-principles study of elastic constants and interlayer interactions of complex hydrated oxides: case study of tobermorite and jennite. J Amer Ceram Soc. 2009;92(10):2323–2330.
   Web of Science ®Google Scholar
• Churakov SV, Labbez C, Pegado L, et al. Intrinsic acidity of surface sites in calcium silicate hydrates and its implication to their electrokinetic properties. J Phys Chem C. 2014;118(22):11752–11762.
   Web of Science ®Google Scholar
• Nguyen MT, Wang Z, Rod KA, et al. Atomic origins of the self-healing function in cement-polymer composites. ACS Appl Mater Interfaces. 2018;10(3):3011–3019.
   PubMed Web of Science ®Google Scholar
• Morawietz T, Singraber A, Dellago C, et al. How van der Waals interactions determine the unique properties of water. Proc Natl Acad Sci USA. 2016;113(30):8368–8373.
   PubMed Web of Science ®Google Scholar
• Behler J, Parrinello M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys Rev Lett. 2007;98(14):146401.
   PubMed Web of Science ®Google Scholar
• Kostiuchenko T, Körmann F, Neugebauer J, et al. Impact of lattice relaxations on phase transitions in a high-entropy alloy studied by machine-learning potentials. Npj Comput Mater. 2019;5(1):55.
   Google Scholar
• Lanzoni D, Rovaris F, Montalenti F. Machine learning potential for interacting dislocations in the presence of free surfaces. Sci Rep. 2022;12(1):3760.
   PubMed Web of Science ®Google Scholar
• Zong H, Pilania G, Ding X, et al. Developing an interatomic potential for martensitic phase transformations in zirconium by machine learning. Npj Comput Mater. 2018;4(1): 48.
   Google Scholar
• Li W, Ando Y. Dependence of a cooling rate on structural and vibrational properties of amorphous silicon: a neural network potential-based molecular dynamics study. J Chem Phys. 2019;151(11):114101.
   PubMed Web of Science ®Google Scholar
• Deringer VL, Bernstein N, Csanyi G, et al. Origins of structural and electronic transitions in disordered silicon. Nature. 2021;589(7840):59–64.
   PubMed Web of Science ®Google Scholar
• Kobayashi K, Nakamura H, Yamaguchi A, et al. Machine learning potentials for tobermorite minerals. Comput Mater Sci. 2021;188:110173.
   Web of Science ®Google Scholar
• Zhang L, Han J, Wang H, et al. Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics. Phys Rev Lett. 2018;120(14):143001.
   PubMed Web of Science ®Google Scholar
• Jinnouchi R, Lahnsteiner J, Karsai F, et al. Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on the fly with Bayesian inference. Phys Rev Lett. 2019;122(22):225701.
   PubMed Web of Science ®Google Scholar
• Wang H, Zhang L, Han J, et al. DeePMD-kit: a deep learning package for many-body potential energy representation and molecular dynamics. Comput Phys Commun. 2018;228:178–184.
   Web of Science ®Google Scholar
• Zhang L, Han J, Wang H, et al. End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems. Adv. Neural Inf. Process. Syst. 2018;31: 4441–4451.
   Google Scholar
• Jiang W, Zhang Y, Zhang L, et al. Accurate deep potential model for the Al–Cu–Mg alloy in the full concentration space. Chin Phys B. 2021;30(5):050706.
   Web of Science ®Google Scholar
• Jia W, Wang H, Chen M, et al. (2020). Pushing the limit of molecular dynamics with Ab initio accuracy to 100 million atoms with machine learning. Paper presented at: The SC20: International Conference for High Performance Computing, Networking, Storage and Analysis.
   Google Scholar
• Wen T, Wang R, Zhu L, et al. Specialising neural network potentials for accurate properties and application to the mechanical response of titanium. Npj Comput Mater. 2021;7(1): 206.
   Google Scholar
• Zhang C, Yue S, Panagiotopoulos AZ, et al. Dissolving salt is not equivalent to applying a pressure on water. Nat Commun. 2022;13(1):822.
   PubMed Web of Science ®Google Scholar
• Zhou Y, Zheng H, Li W, et al. A deep learning potential applied in tobermorite phases and extended to calcium silicate hydrates. Cem Concr Res. 2022;152:106685.
   Web of Science ®Google Scholar
• Cong X, Kirkpatrick RJ. 29Si MAS NMR study of the structure of calcium silicate hydrate. Adv Cem Based Mater. 1996;3(3–4):144–156.
   Google Scholar
• Hou D, Ma H, Zhu Y, et al. Calcium silicate hydrate from dry to saturated state: structure, dynamics and mechanical properties. Acta Mater. 2014;67:81–94.
   Web of Science ®Google Scholar
• Zhou Y, Hou D, Jiang J, et al. Reactive molecular simulation on the calcium silicate hydrates/polyethylene glycol composites. Chem Phys Lett. 2017;687:184–187.
   Web of Science ®Google Scholar
• Zhou Y, Hou D, Manzano H, et al. Interfacial connection mechanisms in calcium-silicate-hydrates/polymer nanocomposites: a molecular dynamics study. ACS Appl Mater Interf. 2017;9(46):41014–41025.
   PubMed Web of Science ®Google Scholar
• Kresse G, Furthmuller J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys Rev B Condens Matter. 1996;54(16):11169–11186.
   PubMed Web of Science ®Google Scholar
• Grimme S, Antony J, Ehrlich S, et al. A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu. J Chem Phys. 2010;132(15):154104.
   PubMed Web of Science ®Google Scholar
• VASP. 2022. Molecular dynamics calculations. Available from https://www.vasp.at/wiki/index.php/Molecular_dynamics_calculations.
   Google Scholar
• Lu D, Jiang W, Chen Y, et al. 2021. DP Train, then DP Compress: Model Compression in Deep Potential Molecular Dynamics. arXiv:2107.02103. https://ui.adsabs.harvard.edu/abs/2021arXiv210702103L.
   Google Scholar
• Wang J, Hou T. Application of molecular dynamics simulations in molecular property prediction II: diffusion coefficient. J Comput Chem. 2011;32(16):3505–3519.
   PubMed Web of Science ®Google Scholar
• Wang V, Xu N, Liu J-C, et al. VASPKIT: a user-friendly interface facilitating high-throughput computing and analysis using VASP code. Comput Phys Commun. 2021;267:108033.
   Web of Science ®Google Scholar
• Voigt W. Lehrbook, der kristallphysik. 2nd ed. Leipsig: Teubner; 1928.
   Google Scholar
• Reuss A. Berechnung der fließgrenze von mischkristallen auf grund der plastizitätsbedingung für einkristalle. Z Angew Math Mech. 1929;9(1):49–58.
   Google Scholar
• Hill R. The elastic behaviour of a crystalline aggregate. Proc Phys Soc A. 1952;65(5):349–354.
   Google Scholar
• Soyer-Uzun S, Chae SR, Benmore CJ, et al. Compositional evolution of calcium silicate hydrate (C-S-H) structures by total X-ray scattering. J Am Ceram Soc. 2012;95(2):793–798.
   Web of Science ®Google Scholar
• Zhou Y, Hou D, Geng G, et al. Insights on the interfacial strengthening mechanisms of calcium-silicate-hydrate/polymer nanocomposites. Phys Chem Chem Phys. 2018;20(12):8247–8266.
   PubMed Web of Science ®Google Scholar
• Manzano H, Dolado JS, Ayuela A. Elastic properties of the main species present in Portland cement pastes. Acta Mater. 2009;57(5):1666–1674.
   Web of Science ®Google Scholar
• Zhou Y, Orozco CA, Duque-Redondo E, et al. Modification of poly(ethylene glycol) on the microstructure and mechanical properties of calcium silicate hydrates. Cem Concr Res. 2019;115:20–30.
   Web of Science ®Google Scholar