Open Access
Subscription or Fee Access
Prediction of Adsorption Energies using Machine Learning
Abstract
In this article, we have a much more comprehensive method that promotes the exploration of automated descriptors. Primary component analysis (PCA) with varimax rotation is used to find the strongest minimum range of adsorption energies that can be used as metal descriptors for a given data set. Our findings demonstrate that the mixture of descriptors produced by this method outperforms conventional descriptors such as nuclear carbon, hydrogen and oxygen adsorption energies. Prediction effects produced through conditional scaling of the identified descriptors were also correlated with observations from non-linear machine learning techniques such as kernel-based models and neural networks. We did not find either of these developed ML models to do better than regular scaling when forecasting through metals.
References
Greeley JP. Theoretical heterogeneous catalysis: scaling relationships and computational catalyst design. Annu Rev Chem Biomol Eng. 2016;7:605–35. doi: 10.1146/annurev-chembioeng-080615–034413, PMID 27088666.
Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW. A theory of learning from different domains. Mach Learn. May 2010;79(1–2):151–75. doi: 10.1007/s10994–009–5152–4.
Behler J. Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J Chem Phys. 2011;134(7):074106. doi: 10.1063/1.3553717, PMID 21341827.
Morawietz T, Behler J. A density-functional theory-based neural network potential for water clusters including van der Waals corrections. J Phys Chem A. 2013;117(32):7356–66. doi: 10.1021/jp401225b, pMID 23557541.
Behler J. Perspective: machine learning potentials for atomistic simulations. J Chem Phys. 2016;145(17):170901. doi: 10.1063/1.4966192, PMID 27825224.
Ulissi ZW, Tang MT, Xiao J, Liu X, Torelli DA, Karamad M, Cummins K, Hahn C, Lewis NS, Jaramillo TF, Chan K, JK. NÃÿrskov. Machine-learning methods enable exhaustive searches for active bimetallic facets and reveal active site motifs for CO2 reduction. ACS Catal. 2017;7(10):6600–8.
Rogers D, Hahn M. Extended-connectivity fingerprints. J Chem Inf Model. 2010;50(5):742–54. doi: 10.1021/ci100050t, pMID 20426451.
Lo YC, Rensi SE, Torng W, Altman RB. Machine learning in chemoinformatics and drug discovery. Drug Discov Today. 2018;23(8):1538–46, 08. doi: 10.1016/j.drudis.2018.05.010, PMID 29750902.
Sanchez-Lengeling B, Aspuru-Guzik A. Inverse molecular design using machine learning: generative models for matter engineering. Science. 2018;361(6400):360–5. doi: 10.1126/science.aat2663, PMID 30049875. 33]. Rasmussen CE. Gaussian processes in machine learning. Lecture Notes in Computer Science. 2004:63–71. doi: 10.1007/978–3–540–28650–9_4.
Hofmann T, Schölkopf B, Smola AJ. Kernel methods in machine learning. Ann Statist. 2008;36(3):1171–220. doi: 10.1214/009053607000000677.
Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on Artificial Intelligence. Vol. 2, ser. IJCAI’95. San Francisco: Morgan Kaufmann Publishers, Inc; 1995. p. 1137–43.
Rupp M. Machine learning for quantum mechanics in a nutshell. Int J Quantum Chem. 2015;115(16):1058–73. doi: 10.1002/qua.24954.
Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks in Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, ser. Proceedings of Machine Learning Research. Chia Laguna resort Teh YW, Titterington M, editors. Vol. 9. Sardinia, Italy: PMLR; May 13–15 2010. p. 249–56.
Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc B. 2005;67(2):301–20. doi: 10.1111/j.1467–9868.2005.00503.x.
Bo C, Maseras F, López N. The role of computational results databases in accelerating the discovery of catalysts. Nat Cat. 2018;1(11):809–10. doi: 10.1038/s41929–018–0176–4.
Jolliffe IT, Cadima J. Principal component analysis: a review and recent developments. Philos Trans R Soc Lond A. Apr 2016;374(2065):20150202. doi: 10.1098/rsta.2015.0202, PMID 26953178.
Melkumova LE, Shatskikh SY. Comparing ridge and lasso estimators for data analysis. Procedia Eng. 2017;201:746–55. doi: 10.1016/j.proeng.2017.09.615.
Housecroft CE, Sharpe AG. Inorganic chemistry. Inorg Chem. 2008:31, 1013, 1014.
Ramakrishnan R, von Lilienfeld OA. Machine learning, quantum chemistry, and chemical space. Reviews in Computational Chemistry. 2017:225–56. doi: 10.1002/9781119356059.ch5.
Verleysen M, François D. The curse of dimensionality in data mining and time series prediction. Lecture Notes in Computer Science. 2005:758–70. doi: 10.1007/11494669_93.
Rupp M, Tkatchenko A, Müller KR, von Lilienfeld OA. Fast and accurate modeling of molecular atomization energies with machine learning. Phys Rev Lett. Jan 2012;108(5):058301. doi: 10.1103/PhysRevLett.108.058301, PMID 22400967.
Hansen K, Biegler F, Ramakrishnan R, Pronobis W, von Lilienfeld OA, Müller KR, Tkatchenko A. Machine learning predictions of molecular properties: accurate many-body potentials and nonlocality in chemical space. J Phys Chem Lett. 2015;6(12):2326–31. doi: 10.1021/acs.jpclett.5b00831, PMID 26113956.
Seeger M. Gaussian processes for machine learning. Int J Neural Syst. 2004;14(2):69–106. doi: 10.1142/S0129065704001899, PMID 15112367.
Walker EA, Mitchell D, Terejanu GA, Heyden A. Identifying active sites of the water-gas shift reaction over titania supported platinum catalysts under uncertainty. ACS Catal. 2018;8(5):3990–8. doi: 10.1021/acscatal.7b03531.
Walker E, Ammal SC, Terejanu GA, Heyden A. Uncertainty quantification framework applied to the water-gas shift reaction over pt-based catalysts. J Phys Chem C. 2016;120(19):10328–39 339. doi: 10.1021/acs.jpcc.6b01348, P. 10.
Lu J, Behtash S, Heyden A. Theoretical investigation of the reaction mechanism of the decarboxylation and decarbonylation of propanoic acid on pd(111) model surfaces. J Phys Chem C. 2012;116(27):14328–41 341. doi: 10.1021/jp301926t, P. 14.
Lu J, Faheem M, Behtash S, Heyden A. Theoretical investigation of the decarboxylation and decarbonylation mechanism of propanoic acid over a ru(0001) model surface. J Cat. 2015;324:14–24. doi: 10.1016/j.jcat.2015.01.005.
Meredig B, Wolverton C. Dissolving the periodic table in cubic zirconia: data mining to discover chemical trends. Chem Mater. 2014;26(6):1985–91. doi: 10.1021/cm403727z.
Ghiringhelli LM, Vybiral J, Levchenko SV, Draxl C, Scheffler M. Big data of materials science: critical role of the descriptor. Phys Rev Lett. Mar 2015;114(10):105503. doi: 10.1103/PhysRevLett.114.105503, PMID 25815947.
Lopez-Paz D, Sra S, Smola AJ, Ghahramani Z, Schölkopf B. Randomized nonlinear component analysis. In: Proceedings of the 31st international conference on Machine Learning. JMLR.org. Vol. 32, ser. ICML’14; 2014. p. II–1359–67.
Abdi H. Factor rotations in factor analyses. In: Encyclopedia of social science research methods. Thousand Oaks, CA: SAGE; 2003.
Szaleniec M, Witko M, Tadeusiewicz R, Goclon J. Application of artificial neural networks and dft-based parameters for prediction of reaction kinetics of ethylbenzene dehydrogenase. J Comput Aid Mol Des. Mar 2006;20(3):145–57. doi: 10.1007/s10822–006–9042–6, PMID 16779618.
Behler J, Parrinello M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys Rev Lett. Apr 2007;98(14):146401. doi: 10.1103/PhysRevLett.98.146401, PMID 17501293.
Pereira F, Xiao K, Latino DARS, Wu C, Zhang Q, Aires-de-Sousa J. Machine learning methods to predict density functional theory b3lyp energies of homo and lumo orbitals. J Chem Inf Model. 2017;57(1):11–21. doi: 10.1021/acs.jcim.6b00340, pMID 28033004.
Rupp M, Ramakrishnan R, von Lilienfeld OA. Machine learning for quantum mechanical properties of atoms in molecules. J Phys Chem Lett. 2015;6(16):3309–13. doi: 10.1021/acs.jpclett.5b01456.
Refbacks
- There are currently no refbacks.