{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T11:27:40Z","timestamp":1753874860126,"version":"3.41.2"},"reference-count":53,"publisher":"AIP Publishing","issue":"13","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["22072064"],"award-info":[{"award-number":["22072064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,7]]},"abstract":"<jats:p>Metal-based catalysts are widely used in many kinds of reactions, including the hydrogenation of CO2 to alcohols. Adsorption energies of key intermediates have often been used as descriptors in high-throughput catalyst screening. However, establishing machine learning models to accurately predict adsorption energies of widely spanned species is still challenging. In the present article, we explored the predictive power of sure independence screening and sparsifying operator (SISSO), multilayer perceptron regression (MLPR), random forest regression (RFR), kernel ridge regression (KRR), support vector regression (SVR), eXtreme Gradient Boosting (XGBoost), and 20 ensemble machine learning (ML) methods for adsorption energies of 57 species involved in CO2 hydrogenation to ethanol using surface features, adsorbate features, and adsorption site features. The results show that SISSO and the five base ML methods cannot furnish models with the maximum absolute error (MAX) comparable to DFT errors. On the other hand, the MAX of most two-component and three-component ensemble ML methods is less than 0.3\u00a0eV, and the KRR+MLPR+XGBoost ensemble ML model performs the best, with the mean absolute error being 0.03\u00a0eV and MAX of only 0.17\u00a0eV. Feature importance analysis reveals that the condensed local softness is the most important feature, and there are linear relations between the condensed local softness and adsorption energies of 10 C1 species on all considered surfaces. The present work shows that ensemble ML methods outperform the base ML methods for predicting adsorption energies of widely ranged species with satisfactory accuracy and deserve further studies.<\/jats:p>","DOI":"10.1063\/5.0256411","type":"journal-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T10:00:24Z","timestamp":1743501624000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Prediction of adsorption energies of CmHnOp (m \u2264 2, n \u2264 6, p \u2264 2) on transition metals and alloys with machine learning methods"],"prefix":"10.1063","volume":"162","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1070-3028","authenticated-orcid":false,"given":"Hong","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of Theoretical and Computational Chemistry, Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University , Nanjing 210023,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Theoretical and Computational Chemistry, Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University , Nanjing 210023,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi-Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Theoretical and Computational Chemistry, Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University , Nanjing 210023,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5444-776X","authenticated-orcid":false,"given":"Zhao-Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Theoretical and Computational Chemistry, Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University , Nanjing 210023,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"317","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"2025040105484648800_c1","doi-asserted-by":"publisher","first-page":"121017","DOI":"10.1016\/j.fuel.2021.121017","article-title":"Greenhouse gases utilization: A review","volume":"301","year":"2021","journal-title":"Fuel"},{"issue":"6","key":"2025040105484648800_c2","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1016\/j.oneear.2020.05.011","article-title":"Attributing extreme events to climate change: A new frontier in a warming world","volume":"2","year":"2020","journal-title":"One Earth"},{"key":"2025040105484648800_c3","doi-asserted-by":"publisher","first-page":"100902","DOI":"10.1016\/j.coche.2023.100902","article-title":"CO2 as a building block: From capture to utilization","volume":"39","year":"2023","journal-title":"Curr. Opin. Chem. Eng."},{"issue":"5","key":"2025040105484648800_c4","doi-asserted-by":"publisher","first-page":"3570","DOI":"10.1021\/acs.energyfuels.2c04122","article-title":"Review and perspectives of emerging green technology for the sequestration of carbon dioxide into value-added products: An intensifying development","volume":"37","year":"2023","journal-title":"Energy Fuels"},{"issue":"3","key":"2025040105484648800_c5","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1021\/acs.accounts.6b00510","article-title":"Heterogeneous catalysis: A central science for a sustainable future","volume":"50","year":"2017","journal-title":"Acc. Chem. Res."},{"issue":"1","key":"2025040105484648800_c6","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.cattod.2012.04.003","article-title":"The past, present and future of heterogeneous catalysis","volume":"189","year":"2012","journal-title":"Catal. Today"},{"issue":"17","key":"2025040105484648800_c7","doi-asserted-by":"publisher","first-page":"4238","DOI":"10.1002\/cctc.201900401","article-title":"Methanol synthesis from CO2 hydrogenation","volume":"11","year":"2019","journal-title":"ChemCatChem"},{"issue":"4","key":"2025040105484648800_c8","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1016\/j.chempr.2020.10.019","article-title":"Advances in higher alcohol synthesis from CO2 hydrogenation","volume":"7","year":"2021","journal-title":"Chem"},{"issue":"2","key":"2025040105484648800_c9","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1039\/d2gc02900f","article-title":"Addressing the CO2 challenge through thermocatalytic hydrogenation to carbon monoxide, methanol and methane","volume":"25","year":"2023","journal-title":"Green Chem."},{"issue":"6083","key":"2025040105484648800_c10","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1126\/science.1219831","article-title":"The active site of methanol synthesis over Cu\/ZnO\/Al2O3 industrial catalysts","volume":"336","year":"2012","journal-title":"Science"},{"issue":"20","key":"2025040105484648800_c11","doi-asserted-by":"publisher","first-page":"6827","DOI":"10.1021\/jacs.7b03101","article-title":"Highly active and selective hydrogenation of CO2 to ethanol by ordered Pd\u2013Cu nanoparticles","volume":"139","year":"2017","journal-title":"J.\u00a0Am. Chem. Soc."},{"issue":"99","key":"2025040105484648800_c12","doi-asserted-by":"publisher","first-page":"14226","DOI":"10.1039\/c6cc08161d","article-title":"Direct synthesis of ethanol via CO2 hydrogenation using supported gold catalysts","volume":"52","year":"2016","journal-title":"Chem. Commun."},{"issue":"2","key":"2025040105484648800_c13","doi-asserted-by":"publisher","first-page":"e202109027","DOI":"10.1002\/ange.202109027","article-title":"Moderate surface segregation promotes selective ethanol production in CO2 hydrogenation reaction over CoCu catalysts","volume":"134","year":"2022","journal-title":"Angew. Chem."},{"issue":"12","key":"2025040105484648800_c14","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1038\/s41578-019-0152-x","article-title":"Theory-guided design of catalytic materials using scaling relationships and reactivity descriptors","volume":"4","year":"2019","journal-title":"Nat. Rev. Mater."},{"issue":"11","key":"2025040105484648800_c15","doi-asserted-by":"publisher","first-page":"3748","DOI":"10.1039\/c4cy00335g","article-title":"Scaling relations between adsorption energies for computational screening and design of catalysts","volume":"4","year":"2014","journal-title":"Catal. Sci. Technol."},{"key":"2025040105484648800_c16","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.cattod.2015.08.056","article-title":"Computational catalyst screening: Scaling, bond-order and catalysis","volume":"272","year":"2016","journal-title":"Catal. Today"},{"issue":"12","key":"2025040105484648800_c17","doi-asserted-by":"publisher","first-page":"2741","DOI":"10.1021\/acs.accounts.1c00153","article-title":"Adsorption enthalpies for catalysis modeling through machine-learned descriptors","volume":"54","year":"2021","journal-title":"Acc. Chem. Res."},{"issue":"4","key":"2025040105484648800_c18","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.trechm.2022.01.012","article-title":"Recent advances in the application of machine-learning algorithms to predict adsorption energies","volume":"4","year":"2022","journal-title":"Trends Chem."},{"issue":"2","key":"2025040105484648800_c19","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1021\/acs.jpcc.2c08343","article-title":"Machine learning assisted understanding and discovery of CO2 reduction reaction electrocatalyst","volume":"127","year":"2023","journal-title":"J.\u00a0Phys. Chem. C"},{"issue":"3","key":"2025040105484648800_c20","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/bf00994018","article-title":"Support-vector networks","volume":"20","year":"1995","journal-title":"Mach. Learn."},{"key":"2025040105484648800_c21","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Teh","year":"2010"},{"issue":"8","key":"2025040105484648800_c22","doi-asserted-by":"publisher","first-page":"083802","DOI":"10.1103\/physrevmaterials.2.083802","article-title":"SISSO: A compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates","volume":"2","year":"2018","journal-title":"Phys. Rev. Mater."},{"issue":"5","key":"2025040105484648800_c23","doi-asserted-by":"publisher","first-page":"2708","DOI":"10.1039\/d3ta06316j","article-title":"Local descriptors-based machine learning model refined by cluster analysis for accurately predicting adsorption energies on bimetallic alloys","volume":"12","year":"2024","journal-title":"J.\u00a0Mater. Chem. A"},{"key":"2025040105484648800_c24","doi-asserted-by":"publisher","first-page":"137772","DOI":"10.1016\/j.cplett.2020.137772","article-title":"Machine learning prediction of monatomic adsorption energies with non-first-principles calculated quantities","volume":"755","year":"2020","journal-title":"Chem. Phys. Lett."},{"issue":"32","key":"2025040105484648800_c25","doi-asserted-by":"publisher","first-page":"8316","DOI":"10.1002\/anie.201402958","article-title":"Fast prediction of adsorption properties for platinum nanocatalysts with generalized coordination numbers","volume":"53","year":"2014","journal-title":"Angew. Chem., Int. Ed."},{"issue":"1","key":"2025040105484648800_c26","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1038\/s41467-020-14969-8","article-title":"Determining the adsorption energies of small molecules with the intrinsic properties of adsorbates and substrates","volume":"11","year":"2020","journal-title":"Nat. Commun."},{"issue":"20","key":"2025040105484648800_c27","doi-asserted-by":"publisher","first-page":"9573","DOI":"10.1021\/acs.jpcc.2c09020","article-title":"Machine learning prediction of CO adsorption energies and properties of layered alloys using an improved feature selection algorithm","volume":"127","year":"2023","journal-title":"J.\u00a0Phys. Chem. C"},{"issue":"1","key":"2025040105484648800_c28","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1038\/s41467-020-20342-6","article-title":"Machine learned features from density of states for accurate adsorption energy prediction","volume":"12","year":"2021","journal-title":"Nat. Commun."},{"issue":"1","key":"2025040105484648800_c29","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/0927-0256(96)00008-0","article-title":"Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set","volume":"6","year":"1996","journal-title":"Comput. Mater. Sci."},{"issue":"16","key":"2025040105484648800_c30","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1103\/PhysRevB.54.11169","article-title":"Efficient iterative schemes for ab\u00a0initio total-energy calculations using a plane-wave basis set","volume":"54","year":"1996","journal-title":"Phys. Rev. B"},{"issue":"1","key":"2025040105484648800_c31","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1103\/physrevb.47.558","article-title":"Ab initio molecular dynamics for liquid metals","volume":"47","year":"1993","journal-title":"Phys. Rev. B"},{"issue":"18","key":"2025040105484648800_c32","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/physrevlett.77.3865","article-title":"Generalized gradient approximation made simple","volume":"77","year":"1996","journal-title":"Phys. Rev. Lett."},{"issue":"24","key":"2025040105484648800_c33","doi-asserted-by":"publisher","first-page":"17953","DOI":"10.1103\/physrevb.50.17953","article-title":"Projector augmented-wave method","volume":"50","year":"1994","journal-title":"Phys. Rev. B"},{"issue":"7","key":"2025040105484648800_c34","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1002\/jcc.21759","article-title":"Effect of the damping function in dispersion corrected density functional theory","volume":"32","year":"2011","journal-title":"J.\u00a0Comput. Chem."},{"volume-title":"Gaussian 16, Revision C.01","year":"2016","key":"2025040105484648800_c35"},{"issue":"7","key":"2025040105484648800_c36","doi-asserted-by":"publisher","first-page":"5648","DOI":"10.1063\/1.464913","article-title":"Density-functional thermochemistry. III. The role of exact exchange","volume":"98","year":"1993","journal-title":"J.\u00a0Chem. Phys."},{"issue":"18","key":"2025040105484648800_c37","doi-asserted-by":"publisher","first-page":"3297","DOI":"10.1039\/b508541a","article-title":"Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: Design and assessment of accuracy","volume":"7","year":"2005","journal-title":"Phys. Chem. Chem. Phys."},{"issue":"4","key":"2025040105484648800_c38","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1021\/acs.jctc.7b01252","article-title":"How accurate is density functional theory at predicting dipole moments? An assessment using a new database of 200 benchmark values","volume":"14","year":"2018","journal-title":"J.\u00a0Chem. Theory Comput."},{"issue":"30","key":"2025040105484648800_c39","doi-asserted-by":"publisher","first-page":"19800","DOI":"10.1039\/c8cp03569e","article-title":"How accurate are static polarizability predictions from density functional theory? An assessment over 132 species at equilibrium geometry","volume":"20","year":"2018","journal-title":"Phys. Chem. Chem. Phys."},{"issue":"9","key":"2025040105484648800_c40","doi-asserted-by":"publisher","first-page":"6796","DOI":"10.1063\/1.462569","article-title":"Electron affinities of the first-row atoms revisited. Systematic basis sets and wave functions","volume":"96","year":"1992","journal-title":"J.\u00a0Chem. Phys."},{"issue":"13","key":"2025040105484648800_c41","doi-asserted-by":"publisher","first-page":"6158","DOI":"10.1063\/1.478522","article-title":"Toward reliable density functional methods without adjustable parameters: The PBE0 model","volume":"110","year":"1999","journal-title":"J.\u00a0Chem. Phys."},{"key":"2025040105484648800_c42","doi-asserted-by":"crossref","DOI":"10.1201\/9781315380476","volume-title":"CRC Handbook of Chemistry and Physics: A Ready-Reference Book of Chemical and Physical Data 2014\u20132015","author":"Haynes","year":"2016","edition":"95"},{"key":"2025040105484648800_c43","first-page":"114","article-title":"The electronic factor in heterogeneous catalysis","volume-title":"Fundamental Concepts in Heterogeneous Catalysis","year":"2014"},{"issue":"21","key":"2025040105484648800_c44","doi-asserted-by":"publisher","first-page":"2832","DOI":"10.1039\/b801115j","article-title":"Covalent radii revisited","volume":"37","year":"2008","journal-title":"Dalton Trans."},{"issue":"5","key":"2025040105484648800_c45","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1039\/b919471a","article-title":"On the applicability of local softness and hardness","volume":"12","year":"2010","journal-title":"Phys. Chem. Chem. Phys."},{"issue":"21","key":"2025040105484648800_c46","doi-asserted-by":"publisher","first-page":"6347","DOI":"10.1002\/ange.201601824","article-title":"Spatially resolved quantification of the surface reactivity of solid catalysts","volume":"128","year":"2016","journal-title":"Angew. Chem."},{"issue":"5","key":"2025040105484648800_c47","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1002\/jcc.22885","article-title":"Multiwfn: A multifunctional wavefunction analyzer","volume":"33","year":"2012","journal-title":"J.\u00a0Comput. Chem."},{"issue":"1","key":"2025040105484648800_c48","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","year":"2001","journal-title":"Mach. Learn."},{"year":"2016","first-page":"785","article-title":"XGBoost: A scalable tree boosting system","key":"2025040105484648800_c49"},{"issue":"1","key":"2025040105484648800_c50","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","year":"2011","journal-title":"J.\u00a0Mach. Learn. Res."},{"issue":"4","key":"2025040105484648800_c51","doi-asserted-by":"publisher","first-page":"2752","DOI":"10.1021\/acscatal.8b04478","article-title":"Beyond scaling relations for the description of catalytic materials","volume":"9","year":"2019","journal-title":"ACS Catal."},{"issue":"4","key":"2025040105484648800_c52","doi-asserted-by":"publisher","first-page":"e1249","DOI":"10.1002\/widm.1249","article-title":"Ensemble learning: A survey","volume":"8","year":"2018","journal-title":"WIREs Data Min. Knowl. Discovery"},{"year":"2016","first-page":"1135","article-title":"\u2018Why should I trust you?\u2019: Explaining the predictions of any classifier","key":"2025040105484648800_c53"}],"container-title":["The Journal of Chemical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0256411\/20463272\/134705_1_5.0256411.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0256411\/20463272\/134705_1_5.0256411.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T10:00:42Z","timestamp":1743501642000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jcp\/article\/162\/13\/134705\/3341530\/Prediction-of-adsorption-energies-of-CmHnOp-m-2-n"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,1]]},"references-count":53,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2025,4,7]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0256411","relation":{},"ISSN":["0021-9606","1089-7690"],"issn-type":[{"type":"print","value":"0021-9606"},{"type":"electronic","value":"1089-7690"}],"subject":[],"published-other":{"date-parts":[[2025,4,7]]},"published":{"date-parts":[[2025,4,1]]},"article-number":"134705"}}