Machine learning potentials for metal-organic frameworks using an incremental learning approach
Source abstract
Abstract
Abstract Computational modeling of physical processes in metal-organic frameworks (MOFs) is highly challenging due to the presence of spatial heterogeneities and complex operating conditions which affect their behavior. Density functional theory (DFT) may describe interatomic interactions at the quantum mechanical level, but is computationally too expensive for systems beyond the nanometer and picosecond range. Herein, we propose an incremental learning scheme to construct accurate and data-efficient machine learning potentials for MOFs. The scheme builds on the power of equivariant neural network potentials in combination with parallelized enhanced sampling and on-the-fly training to simultaneously explore and learn the phase space in an iterative manner. With only a few hundred single-point DFT evaluations per material, accurate and transferable potentials are obtained, even for flexible frameworks with multiple structurally different phases. The incremental learning scheme is universally applicable and may pave the way to model framework materials in larger spatiotemporal windows with higher accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Metal-Organic Frameworks: Synthesis and Applications · Machine Learning in Materials Science · Crystallography and molecular interactions
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (59)
Show source-provided references
1. Burtch, N. C., Jasuja, H. & Walton, K. S. Water stability and adsorption in metal-organic frameworks. Chem. Rev. 114, 10575 (2014).10.1021/cr5002589 ↗
2. Redfern, L. R. & Farha, O. K. Mechanical properties of metal-organic frameworks. Chem. Sci. 10, 10666 (2019).10.1039/C9SC04249K ↗
3. Horcajada, P. et al. Metal–organic frameworks in biomedicine. Chem. Rev. 112, 1232 (2012).10.1021/cr200256v ↗
4. Rogge, S. M. J. et al. Metal–organic and covalent organic frameworks as single-site catalysts. Chem. Soc. Rev. 46, 3134 (2017).10.1039/C7CS00033B ↗
5. Lee, J. et al. Metal–organic framework materials as catalysts. Chem. Soc. Rev. 38, 1450 (2009).10.1039/b807080f ↗
6. Freund, R. et al. The current status of mof and cof applications. Angew. Chem. Int. Ed. 60, 23975 (2021).10.1002/anie.202106259 ↗
7. Ma, N. & Horike, S. Metal–organic network-forming glasses. Chem. Rev. 122, 4163 (2022).10.1021/acs.chemrev.1c00826 ↗
8. Lin, J.-B. et al. A scalable metal-organic framework as a durable physisorbent for carbon dioxide capture. Science 374, 1464 (2021).10.1126/science.abi7281 ↗
9. Hanikel, N. et al. Evolution of water structures in metal-organic frameworks for improved atmospheric water harvesting. Science 374, 454 (2021).10.1126/science.abj0890 ↗
10. Furukawa, H., Müller, U. & Yaghi, O. M. "heterogeneity within order” in metal-organic frameworks. Angew. Chem. Int. Ed. 54, 3417 (2015).10.1002/anie.201410252 ↗
11. Cheetham, A. K., Bennett, T. D., Coudert, F.-X. & Goodwin, A. L. Defects and disorder in metal organic frameworks. Dalton Trans. 45, 4113 (2016).10.1039/C5DT04392A ↗
12. Krause, S. et al. The effect of crystallite size on pressure amplification in switchable porous solids. Nat. Commun. 9, 1573 (2018).10.1038/s41467-018-03979-2 ↗
13. Ehrling, S., Miura, H., Senkovska, I. & Kaskel, S. From macro- to nanoscale: finite size effects on metal–organic framework switchability. Trends Chem. 3, 291 (2021).10.1016/j.trechm.2020.12.012 ↗
14. Ehrling, S. et al. Crystal size versus paddle wheel deformability: selective gated adsorption transitions of the switchable metal–organic frameworks dut-8(co) and dut-8(ni). J. Mater. Chem. A 7, 21459 (2019).10.1039/C9TA06781G ↗
15. Van Speybroeck, V., Vandenhaute, S., Hoffman, A. E. & Rogge, S. M. Towards modeling spatiotemporal processes in metal-organic frameworks. Trends Chem. 3, 605–619 (2021).10.1016/j.trechm.2021.04.003 ↗
16. Evans, J. D., Bon, V., Senkovska, I., Lee, H.-C. & Kaskel, S. Four-dimensional metal-organic frameworks. Nat. Commun. 11, 2690 (2020).10.1038/s41467-020-16527-8 ↗
17. Vandenhaute, S., Rogge, S. M. J. & Van Speybroeck, V. Large-scale molecular dynamics simulations reveal new insights into the phase transition mechanisms in mil-53(al). Front. Chem. 9, 2296 (2021).10.3389/fchem.2021.718920 ↗
18. Keupp, J. & Schmid, R. Molecular dynamics simulations of the “breathing” phase transformation of mof nanocrystallites. Adv. Theory Simul. 2, 1900117 (2019).10.1002/adts.201900117 ↗
19. Friederich, P., Häse, F., Proppe, J. & Aspuru-Guzik, A. Machine-learned potentials for next-generation matter simulations. Nat. Mater. 20, 750 (2021).10.1038/s41563-020-0777-6 ↗
20. Unke, O. T. et al. Machine learning force fields. Chem. Rev. 121, 10142 (2021).10.1021/acs.chemrev.0c01111 ↗
21. Christensen, A. S., Bratholm, L. A., Faber, F. A. & Anatole von Lilienfeld, O. Fchl revisited: faster and more accurate quantum machine learning. J. Chem. Phys. 152, 044107 (2020).10.1063/1.5126701 ↗
22. Deringer, V. L. et al. Gaussian process regression for materials and molecules. Chem. Rev. 121, 10073 (2021).10.1021/acs.chemrev.1c00022 ↗
23. Behler, J. Four generations of high-dimensional neural network potentials. Chem. Rev. 121, 10037 (2021).10.1021/acs.chemrev.0c00868 ↗
24. Eckhoff, M. & Behler, J. From molecular fragments to the bulk: Development of a neural network potential for mof-5. J. Chem. Theory Comput. 15, 3793 (2019).10.1021/acs.jctc.8b01288 ↗
25. Achar, S. K., Wardzala, J. J., Bernasconi, L., Zhang, L. & Johnson, J. K. Combined deep learning and classical potential approach for modeling diffusion in uio-66. J. Chem. Theory Comput. 18, 3593 (2022).10.1021/acs.jctc.2c00010 ↗
26. Yu, Y., Zhang, W. & Mei, D. Artificial neural network potential for encapsulated platinum clusters in mof-808. J. Phys. Chem. C 126, 1204 (2022).10.1021/acs.jpcc.1c09178 ↗
27. Batzner, S. et al. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat. Commun. 13, 2453 (2022).10.1038/s41467-022-29939-5 ↗
28. Thomaset, N. et al. Tensor field networks: rotation- and translation-equivariant neural networks for 3d point clouds. Preprint at https://arxiv.org/abs/1802.08219 (2018).
29. Sivaraman, G. et al. Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide. NPJ Comput. Mater. 6, 104 (2020).10.1038/s41524-020-00367-7 ↗
30. Schran, C. et al. Machine learning potentials for complex aqueous systems made simple. Proc. Natl Acad. Sci. USA 118, e2110077118 (2021).10.1073/pnas.2110077118 ↗
31. Wang, W., Yang, T., Harris, W. H. & Gómez-Bombarelli, R. Active learning and neural network potentials accelerate molecular screening of ether-based solvate ionic liquids. Chem. Commun. 56, 8920 (2020).10.1039/D0CC03512B ↗
32. Vandermause, J. et al. On-the-fly active learning of interpretable bayesian force fields for atomistic rare events. NPJ Comput. Mater. 6, 20 (2020).10.1038/s41524-020-0283-z ↗
33. Cavka, J. H. et al. A new zirconium inorganic building brick forming metal organic frameworks with exceptional stability. J. Am. Chem. Soc. 130, 13850 (2008).10.1021/ja8057953 ↗
34. Loiseau, T. et al. A rationale for the large breathing of the porous aluminum terephthalate (mil-53) upon hydration. Chem. Eur. J. 10, 1373 (2004).10.1002/chem.200305413 ↗
35. Schütt, K. T., Unke, O. T. & Gastegger, M. Equivariant message passing for the prediction of tensorial properties and molecular spectra. Preprint at https://arxiv.org/abs/2102.03150 (2021).
36. Batatia, I., Kovács, D. P., Simm, G. N. C., Ortner, C. & Csányi, G. Mace: higher order equivariant message passing neural networks for fast and accurate force fields. Preprint at https://arxiv.org/abs/2206.07697 (2022).
37. 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).10.1063/1.5019779 ↗
38. Wang, H., Zhang, L., Han, J. & Weinan, E. Deepmd-kit: a deep learning package for many-body potential energy representation and molecular dynamics. Comput. Phys. Commun. 228, 178 (2018).10.1016/j.cpc.2018.03.016 ↗
39. Musil, F. et al. Physics-inspired structural representations for molecules and materials. Chem. Rev. 121, 9759 (2021).10.1021/acs.chemrev.1c00021 ↗
40. Nazarian, D., Ganesh, P. & Sholl, D. S. Benchmarking density functional theory predictions of framework structures and properties in a chemically diverse test set of metal-organic frameworks. J. Mater. Chem. A 3, 22432 (2015).10.1039/C5TA03864B ↗
41. Yot, P. G. et al. Metal-organic frameworks as potential shock absorbers: the case of the highly flexible mil-53(al). Chem. Commun. 50, 9462 (2014).10.1039/C4CC03853C ↗
42. Rogge, S. M. J. et al. A comparison of barostats for the mechanical characterization of metal–organic frameworks. J. Chem. Theory Comput. 11, 5583 (2015).10.1021/acs.jctc.5b00748 ↗
43. Rogge, S. M. J., Waroquier, M. & Van Speybroeck, V. Unraveling the thermodynamic criteria for size-dependent spontaneous phase separation in soft porous crystals. Nat. Commun. 10, 4842 (2019).10.1038/s41467-019-12754-w ↗
44. Coupry, D. E., Addicoat, M. A. & Heine, T. Extension of the universal force field for metal–organic frameworks. J. Chem. Theory Comput. 12, 5215 (2016).10.1021/acs.jctc.6b00664 ↗
45. Staacke, C. G. et al. On the role of long-range electrostatics in machine-learned interatomic potentials for complex battery materials. ACS Appl. Energy Mater. 4, 12562 (2021).10.1021/acsaem.1c02363 ↗
46. Grisafi, A. & Ceriotti, M. Incorporating long-range physics in atomic-scale machine learning. J. Chem. Phys. 151, 204105 (2019).10.1063/1.5128375 ↗
47. Lewis, A. M., Grisafi, A., Ceriotti, M. & Rossi, M. Learning electron densities in the condensed phase. J. Chem. Theory Comput. 17, 7203 (2021).10.1021/acs.jctc.1c00576 ↗
48. VandeVondele, J. et al. Quickstep: fast and accurate density functional calculations using a mixed Gaussian and plane waves approach. Comput. Phys. Commun. 167, 103 (2005).10.1016/j.cpc.2004.12.014 ↗
49. Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865 (1996).10.1103/PhysRevLett.77.3865 ↗
50. Grimme, S., Antony, J., Ehrlich, S. & Krieg, H. A consistent and accurate ab initio parametrization of density functional dispersion correction (dft-d) for the 94 elements h-pu. J. Chem. Phys. 132, 154104 (2010).10.1063/1.3382344 ↗
51. Lippert, B. G., Hutter, J. & Parrinello, M. A hybrid gaussian and plane wave density functional scheme. Mol. Phys. 92, 477 (1997).10.1080/00268979709482119 ↗
52. Verstraelen, T., Vanduyfhuys, L., Vandenbrande, S. & Rogge, S. Yaff, yet another force field. http://molmod.ugent.be/software/.
53. Bussi, G. & Parrinello, M. Accurate sampling using langevin dynamics. Phys. Rev. E 75, 056707 (2007).10.1103/PhysRevE.75.056707 ↗
54. Feller, S. E., Zhang, Y., Pastor, R. W. & Brooks, B. R. Constant pressure molecular dynamics simulation: the Langevin piston method. J. Chem. Phys. 103, 4613 (1995).10.1063/1.470648 ↗
55. Tribello, G. A., Bonomi, M., Branduardi, D., Camilloni, C. & Bussi, G. Plumed 2: new feathers for an old bird. Comp. Phys. Commun. 185, 604 (2014).10.1016/j.cpc.2013.09.018 ↗
56. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980 (2017).
57. Mölderet, F. et al. Sustainable data analysis with snakemake. F1000Research 10, 33 (2021).10.12688/f1000research.29032.1 ↗
58. Vandenhaute, S., Cools-Ceuppens, M., Verstraelen, T. & Van Speybroeck, V. Machine learning potentials for metal-organic frameworks with thermodynamic transferability: training data. https://doi.org/10.5281/zenodo.6359970 (2022).10.5281/zenodo.6359970 ↗
59. Vandenhaute, S., Cools-Ceuppens, M., DeKeyser, S., Verstraelen, T. & Van Speybroeck, V. Machine learning potentials for metal-organic frameworks using an incremental learning approach: workflow and data. https://doi.org/10.5281/zenodo.7539133 (2023).10.5281/zenodo.7539133 ↗