Simulation techniques based on accurate and efficient representations of potential energy surfaces are urgently needed for the understanding of complex systems such as solid-liquid interfaces. Here we present a machine learning framework that enables the efficient development and validation of models for complex aqueous systems. Instead of trying to deliver a globally optimal machine learning potential, we propose to develop models applicable to specific thermodynamic state points in a simple and user-friendly process. After an initial ab initio simulation, a machine learning potential is constructed with minimum human effort through a data-driven active learning protocol. Such models can afterward be applied in exhaustive simulations to provide reliable answers for the scientific question at hand or to systematically explore the thermal performance of ab initio methods. We showcase this methodology on a diverse set of aqueous systems comprising bulk water with different ions in solution, water on a titanium dioxide surface, and water confined in nanotubes and between molybdenum disulfide sheets. Highlighting the accuracy of our approach with respect to the underlying ab initio reference, the resulting models are evaluated in detail with an automated validation protocol that includes structural and dynamical properties and the precision of the force prediction of the models. Finally, we demonstrate the capabilities of our approach for the description of water on the rutile titanium dioxide (110) surface to analyze the structure and mobility of water on this surface. Such machine learning models provide a straightforward and uncomplicated but accurate extension of simulation time and length scales for complex systems.

Charles University Faculty of Mathematics and Physics 121 16 Prague 2 Czech Republic

Department of Chemical Engineering Sargent Centre for Process Systems Engineering Imperial College London London SW7 2AZ United Kingdom

Department of Physics and Astronomy University College London London WC1E 6BT United Kingdom

London Centre for Nanotechnology University College London London WC1E 6BT United Kingdom

Thomas Young Centre University College London London WC1E 6BT United Kingdom

Yusuf Hamied Department of Chemistry University of Cambridge Cambridge CB2 1EW United Kingdom

Yusuf Hamied Department of Chemistry University of Cambridge Cambridge CB2 1EW United Kingdom;

Zobrazit více v PubMed

Zaera F., Probing liquid/solid interfaces at the molecular level. Chem. Rev. 112, 2920–2986 (2012). PubMed

Björneholm O., et al. ., Water at interfaces. Chem. Rev. 116, 7698–7726 (2016). PubMed

Behler J., Perspective: Machine learning potentials for atomistic simulations. J. Chem. Phys. 145, 170901 (2016). PubMed

Butler K. T., Davies D. W., Cartwright H., Isayev O., Walsh A., Machine learning for molecular and materials science. Nature 559, 547–555 (2018). PubMed

Deringer V. L., Caro M. A., Csányi G., Machine learning interatomic potentials as emerging tools for materials science. Adv. Mater. 31, e1902765 (2019). PubMed

Kang P. L., Shang C., Liu Z. P., Large-scale atomic simulation via machine learning potentials constructed by global potential energy surface exploration. Acc. Chem. Res. 53, 2119–2129 (2020). PubMed

Behler J., Four generations of high-dimensional neural network potentials. Chem. Rev., 10.1021/acs.chemrev.0c00868 (2021). PubMed

Morawietz T., Singraber A., Dellago C., Behler J., How van der Waals interactions determine the unique properties of water. Proc. Natl. Acad. Sci. U.S.A. 113, 8368–8373 (2016). PubMed PMC

Cheng B., Engel E. A., Behler J., Dellago C., Ceriotti M., Ab initio thermodynamics of liquid and solid water. Proc. Natl. Acad. Sci. U.S.A. 116, 1110–1115 (2019). PubMed PMC

Gartner T. E. 3rd, et al. ., Signatures of a liquid-liquid transition in an ab initio deep neural network model for water. Proc. Natl. Acad. Sci. U.S.A. 117, 26040–26046 (2020). PubMed PMC

Deringer V. L., et al. ., Origins of structural and electronic transitions in disordered silicon. Nature 589, 59–64 (2021). PubMed

Jinnouchi R., Lahnsteiner J., Karsai F., Kresse G., Bokdam M., Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on the fly with Bayesian inference. Phys. Rev. Lett. 122, 225701 (2019). PubMed

Behler J., Parrinello M., Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007). PubMed

Ghasemi S. A., Hofstetter A., Saha S., Goedecker S., Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network. Phys. Rev. B Condens. Matter Mater. Phys. 92, 045131 (2015).

Schütt K. T., Arbabzadah F., Chmiela S., Müller K. R., Tkatchenko A., Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8, 13890 (2017). PubMed PMC

Zhang L., Han J., Wang H., Car R., E W., Deep potential molecular dynamics: A scalable model with the accuracy of quantum mechanics. Phys. Rev. Lett. 120, 143001 (2018). PubMed

Unke O. T., Meuwly M., PhysNet: A neural network for predicting energies, forces, dipole moments, and partial charges. J. Chem. Theory Comput. 15, 3678–3693 (2019). PubMed

Bartók A. P., Payne M. C., Kondor R., Csányi G., Gaussian approximation potentials: The accuracy of quantum mechanics, without the electrons. Phys. Rev. Lett. 104, 136403 (2010). PubMed

Rupp M., Tkatchenko A., Müller K. R., von Lilienfeld O. A., Fast and accurate modeling of molecular atomization energies with machine learning. Phys. Rev. Lett. 108, 058301 (2012). PubMed

Thompson A. P., Swiler L. P., Trott C. R., Foiles S. M., Tucker G. J., Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials. J. Comput. Phys. 285, 316–330 (2015).

Shapeev A. V., Moment tensor potentials: A class of systematically improvable interatomic potentials. Multiscale Model. Simul. 14, 1153–1173 (2015).

Li Z., Kermode J. R., De Vita A., Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. Phys. Rev. Lett. 114, 096405 (2015). PubMed

Chmiela S., et al. ., Machine learning of accurate energy-conserving molecular force fields. Sci. Adv. 3, e1603015 (2017). PubMed PMC

Gastegger M., Behler J., Marquetand P., Machine learning molecular dynamics for the simulation of infrared spectra. Chem. Sci. (Camb.) 8, 6924–6935 (2017). PubMed PMC

Podryabinkin E. V., Shapeev A. V., Active learning of linearly parametrized interatomic potentials. Comput. Mater. Sci. 140, 171–180 (2017).

Zhang L., Lin D.-Y., Wang H., Car R., E W., Active learning of uniformly accurate interatomic potentials for materials simulation. Phys. Rev. Mater. 3, 023804 (2019).

Smith J. S., Nebgen B., Lubbers N., Isayev O., Roitberg A. E., Less is more: Sampling chemical space with active learning. J. Chem. Phys. 148, 241733 (2018). PubMed

Deringer V. L., Pickard C. J., Csányi G., Data-driven learning of total and local energies in elemental boron. Phys. Rev. Lett. 120, 156001 (2018). PubMed

Schütt K. T., Sauceda H. E., Kindermans P. J., Tkatchenko A., Müller K. R., SchNet - A deep learning architecture for molecules and materials. J. Chem. Phys. 148, 241722 (2018). PubMed

Musil F., et al. ., Machine learning for the structure-energy-property landscapes of molecular crystals. Chem. Sci. (Camb.) 9, 1289–1300 (2017). PubMed PMC

Schran C., Behler J., Marx D., Automated fitting of neural network potentials at coupled cluster accuracy: Protonated water clusters as testing ground. J. Chem. Theory Comput. 16, 88–99 (2020). PubMed

Bartók A. P., Kermode J., Bernstein N., Csányi G., Machine learning a general-purpose interatomic potential for silicon. Phys. Rev. X 8, 041048 (2018).

Rowe P., Deringer V. L., Gasparotto P., Csányi G., Michaelides A., An accurate and transferable machine learning potential for carbon. J. Chem. Phys. 153, 034702 (2020). PubMed

Deringer V. L., Caro M. A., Csányi G., A general-purpose machine-learning force field for bulk and nanostructured phosphorus. Nat. Commun. 11, 5461 (2020). PubMed PMC

Natarajan S. K., Behler J., Neural network molecular dynamics simulations of solid-liquid interfaces: Water at low-index copper surfaces. Phys. Chem. Chem. Phys. 18, 28704–28725 (2016). PubMed

Hellström M., Quaranta V., Behler J., One-dimensional vs. two-dimensional proton transport processes at solid-liquid zinc-oxide-water interfaces. Chem. Sci. (Camb.) 10, 1232–1243 (2018). PubMed PMC

Marcos F., et al. , Free energy of proton transfer at the water-TiO2 interface from: Ab initio deep potential molecular dynamics. Chem. Sci. (Camb.) 11, 2335–2341 (2020). PubMed PMC

Ghorbanfekr H., Behler J., Peeters F. M., Insights into water permeation through hBN nanocapillaries by ab initio machine learning molecular dynamics simulations. J. Phys. Chem. Lett. 11, 7363–7370 (2020). PubMed

Artrith N., Machine learning for the modeling of interfaces in energy storage and conversion materials. J. Phys. Energy 1, 032002 (2019).

Jinnouchi R., Miwa K., Karsai F., Kresse G., Asahi R., On-the-fly active learning of interatomic potentials for large-scale atomistic simulations. J. Phys. Chem. Lett. 11, 6946–6955 (2020). PubMed

Vandermause J., et al. ., On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events. npj Comput. Mater. 6, 1–11 (2020).

Bisbo M. K., Hammer B., Efficient global structure optimization with a machine-learned surrogate model. Phys. Rev. Lett. 124, 086102 (2020). PubMed

Schran C., Marsalek O., MarsalekGroup/aml: AML Python package. GitHub. https://github.com/MarsalekGroup/aml. Deposited 31 May 2021.

Schran C., Brezina K., Marsalek O., Committee neural network potentials control generalization errors and enable active learning. J. Chem. Phys. 153, 104105 (2020). PubMed

Behler J., First principles neural network potentials for reactive simulations of large molecular and condensed systems. Angew. Chem. Int. Ed. Engl. 56, 12828–12840 (2017). PubMed

Artrith N., Morawietz T., Behler J., High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxide. Phys. Rev. B Condens. Matter Mater. Phys. 83, 153101 (2011).

Grisafi A., Ceriotti M., Incorporating long-range physics in atomic-scale machine learning. J. Chem. Phys. 151, 204105 (2019). PubMed

Ko T. W., Finkler J. A., Goedecker S., Behler J., A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer. Nat. Commun. 12, 398 (2021). PubMed PMC

Yue S., et al. ., When do short-range atomistic machine-learning models fall short? J. Chem. Phys. 154, 034111 (2021). PubMed

Imbalzano G., et al. ., Uncertainty estimation for molecular dynamics and sampling. J. Chem. Phys. 154, 074102 (2021). PubMed

Behler J., Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J. Chem. Phys. 134, 074106 (2011). PubMed

Grossman J. C., Schwegler E., Draeger E. W., Gygi F., Galli G., Towards an assessment of the accuracy of density functional theory for first principles simulations of water. J. Chem. Phys. 120, 300–311 (2004). PubMed

R. A. DiStasio, Jr, Santra B., Li Z., Wu X., Car R., The individual and collective effects of exact exchange and dispersion interactions on the ab initio structure of liquid water. J. Chem. Phys. 141, 084502 (2014). PubMed

Forster-Tonigold K., Groß A., Dispersion corrected RPBE studies of liquid water. J. Chem. Phys. 141, 064501 (2014). PubMed

Gillan M. J., Alfè D., Michaelides A., Perspective: How good is DFT for water? J. Chem. Phys. 144, 130901 (2016). PubMed

Chen M., et al. ., Ab initio theory and modeling of water. Proc. Natl. Acad. Sci. U.S.A. 114, 10846–10851 (2017). PubMed PMC

Marsalek O., Markland T. E., Quantum dynamics and spectroscopy of ab initio liquid water: The interplay of nuclear and electronic quantum effects. J. Phys. Chem. Lett. 8, 1545–1551 (2017). PubMed

Brandenburg J. G., Zen A., Alfè D., Michaelides A., Interaction between water and carbon nanostructures: How good are current density functional approximations? J. Chem. Phys. 151, 164702 (2019). PubMed

Schienbein P., Marx D., Supercritical water is not hydrogen bonded. Angew. Chem. Int. Ed. Engl. 59, 18578–18585 (2020). PubMed PMC

Sharkas K., et al. ., Self-interaction error overbinds water clusters but cancels in structural energy differences. Proc. Natl. Acad. Sci. U.S.A. 117, 11283–11288 (2020). PubMed PMC

Wagle K., et al. ., Self-interaction correction in water-ion clusters. J. Chem. Phys. 154, 094302 (2021). PubMed

Duignan T. T., Kathmann S. M., Schenter G. K., Mundy C. J., Toward a first-principles framework for predicting collective properties of electrolytes. Acc. Chem. Res. 54, 2833–2843 (2021). PubMed

Pang C. L., Lindsay R., Thornton G., Structure of clean and adsorbate-covered single-crystal rutile TiO2 surfaces. Chem. Rev. 113, 3887–3948 (2013). PubMed

Diebold U., Perspective: A controversial benchmark system for water-oxide interfaces: H2O/TiO2(110). J. Chem. Phys. 147, 040901 (2017). PubMed

Předota M., Cummings P. T., Wesolowski D. J., Electric double layer at the rutile (110) surface. 3. Inhomogeneous viscosity and diffusivity measurement by computer simulations. J. Phys. Chem. C 111, 3071–3079 (2007).

Li M. L., Zhang C., Thornton G., Michaelides A., Structure and dynamics of liquid water on rutile TiO2(110). Phys. Rev. B Condens. Matter Mater. Phys. 82, 161415 (2010).

Spencer E. C., et al. ., Inelastic neutron scattering study of confined surface water on rutile nanoparticles. J. Phys. Chem. A 113, 2796–2800 (2009). PubMed

English N. J., Kavathekar R. S., MacElroy J. M. D., Hydrogen bond dynamical properties of adsorbed liquid water monolayers with various TiO2 interfaces. Mol. Phys. 110, 2919–2925 (2012).

Agosta L., Brandt E. G., Lyubartsev A. P., Diffusion and reaction pathways of water near fully hydrated TiO2 surfaces from ab initio molecular dynamics. J. Chem. Phys. 147, 024704 (2017). PubMed

Klimeš J., Bowler D. R., Michaelides A., Chemical accuracy for the van der Waals density functional. J. Phys. Condens. Matter 22, 022201 (2010). PubMed

Pluhařová E., Jungwirth P., Matubayasi N., Marsalek O., Structure and dynamics of the hydration shell: Spatially decomposed time correlation approach. J. Chem. Theory Comput. 15, 803–812 (2019). PubMed

Heard C. J., et al. ., Fast room temperature lability of aluminosilicate zeolites. Nat. Commun. 10, 4690 (2019). PubMed PMC

Singraber A., Morawietz T., Behler J., Dellago C., Parallel multistream training of high-dimensional neural network potentials. J. Chem. Theory Comput. 15, 3075–3092 (2019). PubMed

Schran C., water-ice-group/simple-MLP: Supporting data for published paper. Zenodo. 10.5281/zenodo.5235246. Deposited 23 August 2021. DOI

Kühne T. D., et al. ., CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations. J. Chem. Phys. 152, 194103 (2020). PubMed

Bussi G., Donadio D., Parrinello M., Canonical sampling through velocity rescaling. J. Chem. Phys. 126, 014101 (2007). PubMed

Reducing the Cost of Neural Network Potential Generation for Reactive Molecular Systems