Machine learning-enabled fast exploration of stable and active single-atom catalysts for oxygen evolution reaction

Woonghyeon Park; Juhwan Noh; Geun Ho Gu; Gunwook Nam; Sang-Mun Jung; Yong-Tae Kim; Yousung Jung

doi:10.59717/j.xinn-mater.2024.100072

The Innovation Materials > 2024 Vol. 2 > No. 2 > 100072

Next Article Previous Article

ARTICLE Open Access

Cite PDF

Machine learning-enabled fast exploration of stable and active single-atom catalysts for oxygen evolution reaction

1.
Department of Chemical and Biomolecular Engineering (BK-21 Plus), Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, South Korea
2.
School of Chemical and Biological Engineering, and Institute of Chemical Processes, Seoul National University, Seoul 08826, South Korea
3.
Department of Materials Science and Engineering, Pohang University of Science and Technology (POSTECH), Pohang 37673, South Korea

More Information

Corresponding author: yousung.jung@snu.ac.kr
Received Date: 08 December 2023

Accepted Date: 11 May 2024

Published Online: 22 May 2024

The Innovation Materials 2(2), https://doi.org/10.59717/j.xinn-mater.2024.100072 | Cite this article

GRAPHICAL ABSTRACT

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

PUBLIC SUMMARY
1. Single-atom catalysts loaded with acid stable conductive metal oxides for enhanced oxygen evolution reaction.
  
  A high-throughput screening framework based on Density Functional Theory and Machine Learning is proposed.
  
  The computational cost was reduced to 1/10 of the traditional DFT method.
  
  14 promising SACs for OER were identified through the approach.

ABSTRACT

ABSTRACT

Oxygen evolution reaction (OER) can convert renewable energy into hydrogen through water electrolysis. Identifying stable and active single-atom catalysts (SACs) for OER under acidic conditions holds great promise for developing cost-effective and efficient energy storage solutions, but challenging due to the vast number of potential material compositions and diverse surface morphologies. Here, to accelerate new discoveries, we present a high-throughput screening (HTS) framework that leverages the power of machine learning (ML) and density functional theory (DFT). The proposed framework includes an assessment of both the thermodynamic and electrochemical stability of support surfaces. In addition, the integration of ML and uncertainty quantification for predicting the binding energies dramatically reduces the computational cost (by over a factor of 10), facilitating the identification of catalytically active SACs. Following the proposed scheme, we suggest 14 new promising SACs for OER across the 795 binary oxide supports and 21 transition metal atom combinations. These catalysts are found to break the scaling relation due to the enhanced *OOH binding with the support, which arises from favorable hydrogen bonding interactions.

FullText(HTML)

REFERENCES

[1]	Chu, S., and Majumdar, A. (2012). Opportunities and challenges for a sustainable energy future. Nature 488: 294−303. DOI: 10.1038/nature11475. View in Article CrossRef Google Scholar
[2]	Peng, L., and Wei, Z. (2020). Catalyst engineering for electrochemical energy conversion from water to water: water electrolysis and the hydrogen fuel cell. Engineering 6: 653−679. DOI: 10.1016/j.eng.2019.07.028. View in Article CrossRef Google Scholar
[3]	Holladay, J.D., Hu, J., King, D.L., et al. (2009). An overview of hydrogen production technologies. Catal. Today 139: 244−260. DOI: 10.1016/j.cattod.2008.08.039. View in Article CrossRef Google Scholar
[4]	Song, H.J., Yoon, H., Ju, B., et al. (2021). Highly efficient perovskite‐based electrocatalysts for water oxidation in acidic environments: A mini review. Adv. Energy Mater. 11: 2002428. DOI: 10.1002/aenm.202002428. View in Article CrossRef Google Scholar
[5]	Chorkendorff, I., Dickens, C.F., Seh, Z.W., et al. (2017). Combining theory and experiment in electrocatalysis: Insights into materials design. Science 355: eaad4998. DOI: 10.1126/science.aad4998. View in Article CrossRef Google Scholar
[6]	Randolph, K., Miller, E., Peterson, D., et al. (2017). Hydrogen production tech team roadmap. US Doe 55. https://www.energy.gov/sites/default/files/2014/03/f9/hptt_roadmap_june2013.pdf View in Article Google Scholar
[7]	DOE (2020). Department of energy hydrogen program plan. US Dep Energy 56. https://www.hydrogen.energy.gov/docs/hydrogenprogramlibraries/pdfs/hydrogen-program-plan-2020.pdf?Status=Master View in Article Google Scholar
[8]	Cao, L., Luo, Q., Chen, J., et al. (2019). Dynamic oxygen adsorption on single-atomic ruthenium catalyst with high performance for acidic oxygen evolution reaction. Nat. Commun. 10: 1−9. DOI: 10.1038/s41467-019-12886-z. View in Article CrossRef Google Scholar
[9]	McCrory, C.C.L., Jung, S., Peters, J.C., et al. (2013). Benchmarking heterogeneous electrocatalysts for the oxygen evolution reaction. J. Am. Chem. Soc. 135: 16977−16987. DOI: 10.1021/ja407115p. View in Article CrossRef Google Scholar
[10]	Qiao, B., Wang, A., Yang, X., et al. (2011). Single-atom catalysis of CO oxidation using Pt₁/FeO_x. Nat. Chem. 3: 634−641. DOI: 10.1038/nchem.1095. View in Article CrossRef Google Scholar
[11]	Yang, X., Wang, A., Qiao, B., et al. (2013). Single-atom catalysts: A new frontier in heterogeneous catalysis. Acc. Chem. Res. 46: 1740−1748. DOI: 10.1021/ar300361m. View in Article CrossRef Google Scholar
[12]	Zhang, H., Liu, G., Shi, L., et al. (2018). Single-atom catalysts: Emerging multifunctional materials in heterogeneous catalysis. Adv. Energy Mater. 8: 1−24. DOI: 10.1002/aenm.201701343. View in Article CrossRef Google Scholar
[13]	Wang, A., Li, J., and Zhang, T. (2018). Heterogeneous single-atom catalysis. Nat. Rev. Chem. 2: 65−81. DOI: 10.1038/s41570-018-0010-1. View in Article CrossRef Google Scholar
[14]	Liu, M., Wang, L., Zhao, K., et al. (2019). Atomically dispersed metal catalysts for the oxygen reduction reaction: Synthesis, characterization, reaction mechanisms and electrochemical energy applications. Energy Environ. Sci. 12: 2890−2923. DOI: 10.1039/c9ee01722d. View in Article CrossRef Google Scholar
[15]	Li, X., Liu, L., Ren, X., et al. (2020). Microenvironment modulation of single-atom catalysts and their roles in electrochemical energy conversion. Sci. Adv. 6: 1−20. DOI: 10.1126/sciadv.abb6833. View in Article CrossRef Google Scholar
[16]	Li, L., Chang, X., Lin, X., et al. (2020). Theoretical insights into single-atom catalysts. Chem. Soc. Rev. 49: 8156−8178. DOI: 10.1039/d0cs00795a. View in Article CrossRef Google Scholar
[17]	Kaiser, S.K., Chen, Z., Faust Akl, D., et al. (2020). Single-atom catalysts across the periodic table. Chem. Rev. 120: 11703−11809. DOI: 10.1021/acs.chemrev.0c00576. View in Article CrossRef Google Scholar
[18]	Zhang, F.-F., Cheng, C.-Q., Wang, J.-Q., et al. (2021). Iridium oxide modified with silver single atom for boosting oxygen evolution reaction in acidic media. ACS Energy Lett. 6: 1588−1595. DOI: 10.1021/acsenergylett.1c00283. View in Article CrossRef Google Scholar
[19]	Shan, J., Ye, C., Chen, S., et al. (2021). Short-range ordered iridium single atoms integrated into cobalt oxide spinel structure for highly efficient electrocatalytic water oxidation. J. Am. Chem. Soc. 143: 5201−5211. DOI: 10.1021/jacs.1c01525. View in Article CrossRef Google Scholar
[20]	Liu, Y., Chen, Y., Mu, X., et al. (2023). Spinel-anchored iridium single atoms enable efficient acidic water oxidation via intermediate stabilization effect. ACS Catal. 13: 3757−3767. DOI: 10.1021/acscatal.2c05940. View in Article CrossRef Google Scholar
[21]	Shi, X., Peng, H.-J., Hersbach, T.J.P., et al. (2022). Efficient and stable acidic water oxidation enabled by low-concentration, high-valence iridium sites. ACS Energy Lett. 7: 2228−2235. DOI: 10.1021/acsenergylett.2c00578. View in Article CrossRef Google Scholar
[22]	Kim, D.Y., Ha, M., and Kim, K.S. (2021). A universal screening strategy for the accelerated design of superior oxygen evolution/reduction electrocatalysts. J. Mater. Chem. A 9: 3511−3519. DOI: 10.1039/d0ta02425b. View in Article CrossRef Google Scholar
[23]	Xu, H., Cheng, D., Cao, D., et al. (2018). A universal principle for a rational design of single-atom electrocatalysts. Nat. Catal. 1: 339−348. DOI: 10.1038/s41929-018-0063-z. View in Article CrossRef Google Scholar
[24]	García-Mota, M., Vojvodic, A., Metiu, H., et al. (2011). Tailoring the activity for oxygen evolution electrocatalysis on rutile TiO₂(110) by transition-metal substitution. ChemCatChem 3: 1607−1611. DOI: 10.1002/cctc.201100160. View in Article CrossRef Google Scholar
[25]	Zhong, M., Tran, K., Min, Y., et al. (2020). Accelerated discovery of CO₂ electrocatalysts using active machine learning. Nature 581: 178−183. DOI: 10.1038/s41586-020-2242-8. View in Article CrossRef Google Scholar
[26]	Back, S., Yoon, J., Tian, N., et al. (2019). Convolutional neural network of atomic surface structures to predict binding energies for high-throughput screening of catalysts. J. Phys. Chem. Lett. 10: 4401−4408. DOI: 10.1021/acs.jpclett.9b01428. View in Article CrossRef Google Scholar
[27]	Tran, K., and Ulissi, Z.W. (2018). Active learning across intermetallics to guide discovery of electrocatalysts for CO₂ reduction and H₂ evolution. Nat. Catal. 1: 696−703. DOI: 10.1038/s41929-018-0142-1. View in Article CrossRef Google Scholar
[28]	Xu, W., Andersen, M., and Reuter, K. (2021). Data-driven descriptor engineering and refined scaling relations for predicting transition metal oxide reactivity. ACS Catal. 11: 734−742. DOI: 10.1021/acscatal.0c04170. View in Article CrossRef Google Scholar
[29]	Ha, M., Kim, D.Y., Umer, M., et al. (2021). Tuning metal single atoms embedded in N_xC_y moieties toward high-performance electrocatalysis. Energy Environ. Sci. 14: 3455−3468. DOI: 10.4135/9781412975704.n47. View in Article CrossRef Google Scholar
[30]	Guo, X., Lin, S., Gu, J., et al. (2019). Simultaneously achieving high activity and selectivity toward two-electron O₂ electroreduction: The power of single-atom catalysts. ACS Catal. 9: 11042−11054. DOI: 10.1021/acscatal.9b02778. View in Article CrossRef Google Scholar
[31]	Zafari, M., Kumar, D., Umer, M., et al. (2020). Machine learning-based high throughput screening for nitrogen fixation on boron-doped single atom catalysts. J. Mater. Chem. A 8: 5209−5216. DOI: 10.1039/c9ta12608b. View in Article CrossRef Google Scholar
[32]	Lin, S., Xu, H., Wang, Y., et al. (2020). Directly predicting limiting potentials from easily obtainable physical properties of graphene-supported single-atom electrocatalysts by machine learning. J. Mater. Chem. A 8: 5663−5670. DOI: 10.1039/c9ta13404b. View in Article CrossRef Google Scholar
[33]	Scalia, G., Grambow, C.A., Pernici, B., et al. (2020). Evaluating scalable uncertainty estimation methods for deep learning-based molecular property prediction. J. Chem. Inf. Model 60: 2697−2717. DOI: 10.1021/acs.jcim.9b00975. View in Article CrossRef Google Scholar
[34]	Lakshminarayanan, B., Pritzel, A., and Blundell, C. (2016). Simple and scalable predictive uncertainty estimation using deep ensembles. Guyon, I., Von Luxburg, U., and Bengio, S. et al. Advances in Neural Information Processing Systems 30 (NeurIPS Proceedings View in Article Google Scholar
[35]	Kresse, G., and Furthmüller, J. (1996). Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. Mater. Sci. 6: 15−50. DOI: 10.1016/0927-0256(96)00008-0. View in Article CrossRef Google Scholar
[36]	Kresse, G. (1999). From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. Rev. B 59: 1758−1775. DOI: 10.1103/PhysRevB.59.1758. View in Article CrossRef Google Scholar
[37]	Perdew, J.P., Burke, K., and Ernzerhof, M. (1996). Generalized gradient approximation made simple. Phys. Rev. Lett. 77: 3865−3868. DOI: 10.1103/PhysRevLett.77.3865. View in Article CrossRef Google Scholar
[38]	Blöchl, P.E. (1994). Projector augmented-wave method. Phys. Rev B 50: 17953−17979. DOI: 10.1103/PhysRevB.50.17953. View in Article CrossRef Google Scholar
[39]	Dudarev, S.L., Botton, G.A., Savrasov, S.Y., et al. (1998). Electron-energy-loss spectra and the structural stability of nickel oxide: An LSDA+U study. Phys. Rev. B 57: 1505−1509. DOI: 10.1103/PhysRevB.57.1505. View in Article CrossRef Google Scholar
[40]	Jain, A., Ong, S.P., Hautier, G., et al. (2013). Commentary: The materials project: A materials genome approach to accelerating materials innovation. APL Mater. 1: 11002. DOI: 10.1063/1.4812323. View in Article CrossRef Google Scholar
[41]	Back, S., Tran, K., and Ulissi, Z.W. (2019). Toward a design of active oxygen evolution catalysts: Insights from automated density functional theory calculations and machine learning. ACS Catal. 9: 7651−7659. DOI: 10.1021/acscatal.9b02416. View in Article CrossRef Google Scholar
[42]	Man, I.C., Su, H.Y., Calle-Vallejo, F., et al. (2011). Universality in oxygen evolution electrocatalysis on oxide surfaces. ChemCatChem 3: 1159−1165. DOI: 10.1002/cctc.201000397. View in Article CrossRef Google Scholar
[43]	Nørskov, J.K., Rossmeisl, J., Logadottir, A., et al. (2004). Origin of the overpotential for oxygen reduction at a fuel-cell cathode. J. Phys. Chem. B 108: 17886−17892. DOI: 10.1021/jp047349j. View in Article CrossRef Google Scholar
[44]	Gu, G.H., Noh, J., Kim, I., et al. (2019). Machine learning for renewable energy materials. J. Mater. Chem. A 7: 17096−17117. DOI: 10.1039/C9TA02356A. View in Article CrossRef Google Scholar
[45]	Dietterich, T.G. (2000). Ensemble methods in machine learning. Kittler, J. and Roli, F. (eds). Multiple classifier systems (Springer Berlin Heidelberg), pp: 1–15. DOI: 10.1007/3-540-45014-9_1. View in Article Google Scholar
[46]	Hirschfeld, L., Swanson, K., Yang, K., et al. (2020). Uncertainty quantification using neural networks for molecular property prediction. J. Chem. Inf. Model 60: 3770−3780. DOI: 10.1021/acs.jcim.0c00502. View in Article CrossRef Google Scholar
[47]	Van Der Maaten, L. (2014). Accelerating t-sne using tree-based algorithms. J. Mach. Learn Res. 15: 3221−3245. DOI: abs/10.5555/2627435.2697068. View in Article Google Scholar
[48]	Singh, A.K., Zhou, L., Shinde, A., et al. (2017). Electrochemical stability of metastable materials. Chem. Mater. 29: 10159−10167. DOI: 10.1021/acs.chemmater.7b03980. View in Article CrossRef Google Scholar
[49]	Chung, D.Y., Park, S., Lopes, P.P., et al. (2020). Electrokinetic analysis of poorly conductive electrocatalytic materials. ACS Catal. 10: 4990−4996. DOI: 10.1021/acscatal.0c00960. View in Article CrossRef Google Scholar
[50]	Fei, H., Dong, J., Chen, D., et al. (2019). Single atom electrocatalysts supported on graphene or graphene-like carbons. Chem. Soc. Rev. 48: 5207−5241. DOI: 10.1039/c9cs00422j. View in Article CrossRef Google Scholar
[51]	Sultan, S., Tiwari, J.N., Singh, A.N., et al. (2019). Single atoms and clusters based nanomaterials for hydrogen evolution, oxygen evolution reactions, and full water splitting. Adv. Energy Mater. 9: 1−48. DOI: 10.1002/aenm.201900624. View in Article CrossRef Google Scholar
[52]	Parrondo, J., George, M., Capuano, C., et al. (2015). Pyrochlore electrocatalysts for efficient alkaline water electrolysis. J. Mater. Chem. A 3: 10819−10828. DOI: 10.1039/c5ta01771h. View in Article CrossRef Google Scholar
[53]	Kim, M., Park, J., Kang, M., et al. (2020). Toward efficient electrocatalytic oxygen evolution: Emerging opportunities with metallic pyrochlore oxides for electrocatalysts and conductive supports. ACS Cent Sci 6: 880−891. DOI: 10.1021/acscentsci.0c00479. View in Article CrossRef Google Scholar
[54]	SNUMAT database. (2024). https://www.snumat.com. View in Article Google Scholar
[55]	Ong, S.P., Richards, W.D., Jain, A., et al. (2013). Python materials genomics (pymatgen): A robust, open-source python library for materials analysis. Comput. Mater. Sci. 68 : 314–319. DOI: https://doi.org/10.1016/j.commatsci.2012.10.028. View in Article Google Scholar
[56]	Xie, T. and Grossman, J.C. (2018). Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120: 145301. DOI: 10.1103/PhysRevLett.120.145301. View in Article CrossRef Google Scholar
[57]	Gu, G.H., Noh, J., Kim, S., et al. (2020). Practical deep-learning representation for fast heterogeneous catalyst screening. J. Phys. Chem. Lett. 11: 3185−3191. DOI: 10.1021/acs.jpclett.0c00634. View in Article CrossRef Google Scholar
[58]	Gunasooriya, G.T.K.K. and Nørskov, J.K. (2020). Analysis of acid-stable and active oxides for the oxygen evolution reaction. ACS Energy Lett. 5: 3778−3787. DOI: 10.1021/acsenergylett.0c02030. View in Article CrossRef Google Scholar
[59]	Craig, M.J., Coulter, G., Dolan, E., et al. (2019). Universal scaling relations for the rational design of molecular water oxidation catalysts with near-zero overpotential. Nat. Commun. 10: 1−9. DOI: 10.1038/s41467-019-12994-w. View in Article CrossRef Google Scholar
[60]	Li, N., Keane, T.P., Veroneau, S.S., et al. (2020). Template-stabilized oxidic nickel oxygen evolution catalysts. Proc. Natl. Acad. Sci. 117: 16187−16192. DOI: 10.1073/pnas.2001529117. View in Article CrossRef Google Scholar
[61]	Wu, W., Yao, J., Liu, S., et al. (2019). Nanostructured hexagonal ReO₃ with oxygen vacancies for efficient electrocatalytic hydrogen generation. Nanotechnology 30: 355701. DOI: 10.1088/1361-6528/ab214c. View in Article CrossRef Google Scholar
[62]	Chemicalbook.com. (2023). https://www.chemicalbook.com/. View in Article Google Scholar
[63]	Pourbaix, M. J. N., Van Muylder, J., and de Zoubov, N. (1959). Electrochemical properties of the palladium metals. Platin Met. Rev. 3: 47−53. DOI: 10.1595/003214059X324753. View in Article CrossRef Google Scholar

CITED BY

ABOUT THIS ARTICLE

Cite this article:

Park W., Noh J., Gu G., et al., (2024). Machine learning-enabled fast exploration of stable and active single-atom catalysts for oxygen evolution reaction. The Innovation Materials 2(2): 100072. https://doi.org/10.59717/j.xinn-mater.2024.100072

Park W., Noh J., Gu G., et al., (2024). Machine learning-enabled fast exploration of stable and active single-atom catalysts for oxygen evolution reaction. The Innovation Materials 2(2): 100072. https://doi.org/10.59717/j.xinn-mater.2024.100072

Standard PDF

Extended PDF

Figures(5) Tables(1)

Article Metrics

Article views(2354) PDF downloads(668) Cited by(0)

Relative Articles

Article Contents

ABOUT THIS ARTICLE

Machine learning-enabled fast exploration of stable and active single-atom catalysts for oxygen evolution reaction

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

ABSTRACT

REFERENCES

ABOUT THIS ARTICLE

Cite this article:

Share

Article Metrics

Relative Articles

Catalog

{{newsColumn.name}}

Journal links

{{newsColumn.name}}

Stay connected

Machine learning-enabled fast exploration of stable and active single-atom catalysts for oxygen evolution reaction

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

ABSTRACT

REFERENCES

ABOUT THIS ARTICLE

Cite this article:

Share

Article Metrics

Relative Articles

Catalog

Export File

Citation

Format

Content

{{newsColumn.name}}

Journal links

{{newsColumn.name}}

Stay connected