{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T16:46:08Z","timestamp":1771260368042,"version":"3.50.1"},"reference-count":87,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T00:00:00Z","timestamp":1630022400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T00:00:00Z","timestamp":1630022400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006133","name":"Advanced Research Projects Agency - Energy","doi-asserted-by":"crossref","award":["DE-AR0001221"],"award-info":[{"award-number":["DE-AR0001221"]}],"id":[{"id":"10.13039\/100006133","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The majority of computational catalyst design focuses on the screening of material components and alloy composition to optimize selectivity and activity for a given reaction. However, predicting the metastability of the alloy catalyst surface at realistic operating conditions requires an extensive sampling of possible surface reconstructions and their associated kinetic pathways. We present CatGym, a deep reinforcement learning (DRL) environment for predicting the thermal surface reconstruction pathways and their associated kinetic barriers in crystalline solids under reaction conditions. The DRL agent iteratively changes the positions of atoms in the near-surface region to generate kinetic pathways to accessible local minima involving changes in the surface compositions. We showcase our agent by predicting the surface reconstruction pathways of a ternary Ni<jats:sub>3<\/jats:sub>Pd<jats:sub>3<\/jats:sub>Au<jats:sub>2<\/jats:sub>(111) alloy catalyst. Our results show that the DRL agent can not only explore more diverse surface compositions than the conventional minima hopping method, but also generate the kinetic surface reconstruction pathways. We further demonstrate that the kinetic pathway to a global minimum energy surface composition and its associated transition state predicted by our agent is in good agreement with the minimum energy path predicted by nudged elastic band calculations.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac191c","type":"journal-article","created":{"date-parts":[[2021,7,29]],"date-time":"2021-07-29T22:43:45Z","timestamp":1627598625000},"page":"045018","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Deep reinforcement learning for predicting kinetic pathways to surface reconstruction in a ternary alloy"],"prefix":"10.1088","volume":"2","author":[{"given":"Junwoong","family":"Yoon","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2096-1178","authenticated-orcid":false,"given":"Zhonglin","family":"Cao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0030-3242","authenticated-orcid":false,"given":"Rajesh K","family":"Raju","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0723-6246","authenticated-orcid":false,"given":"Yuyang","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3346-6432","authenticated-orcid":false,"given":"Robert","family":"Burnley","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6618-7427","authenticated-orcid":false,"given":"Andrew J","family":"Gellman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2952-8576","authenticated-orcid":false,"given":"Amir","family":"Barati Farimani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9401-4918","authenticated-orcid":false,"given":"Zachary W","family":"Ulissi","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2021,8,27]]},"reference":[{"key":"mlstac191cbib1","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0926-860X(01)00828-6","article-title":"Alloy catalysts: the concepts","volume":"222","author":"Ponec","year":"2001","journal-title":"Appl. Catal.A"},{"key":"mlstac191cbib2","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1016\/0039-6028(95)00144-1","article-title":"On the reactivity of 2d Pd surface alloys obtained by surface segregation or deposition technique","volume":"331-333","author":"Bertolini","year":"1995","journal-title":"Surf. Sci."},{"key":"mlstac191cbib3","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.susc.2015.05.026","article-title":"Composition, structure and stability of surfaces formed by Ni deposition on Pd(111)","volume":"646","author":"Fu","year":"2016","journal-title":"Surf. Sci."},{"key":"mlstac191cbib4","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1021\/ar300245g","article-title":"In-situ studies of nanocatalysis","volume":"46","author":"Zhang","year":"2013","journal-title":"Acc. Chem. Res."},{"key":"mlstac191cbib5","doi-asserted-by":"publisher","first-page":"3487","DOI":"10.1021\/cr5002657","article-title":"Atomic-scale observations of catalyst structures under reaction conditions and during catalysis","volume":"116","author":"Tao","year":"2016","journal-title":"Chem. Rev."},{"key":"mlstac191cbib6","doi-asserted-by":"publisher","first-page":"10020","DOI":"10.1021\/acscatal.9b01831","article-title":"Operando insights into nanoparticle transformations during catalysis","volume":"9","author":"Bergmann","year":"2019","journal-title":"ACS Catal."},{"key":"mlstac191cbib7","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.surfrep.2008.01.001","article-title":"Ambient pressure photoelectron spectroscopy: a new tool for surface science and nanotechnology","volume":"63","author":"Salmeron","year":"2008","journal-title":"Surf. Sci. Rep."},{"key":"mlstac191cbib8","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1126\/science.1207272","article-title":"Spectroscopic observation of dual catalytic sites during oxidation of CO on a Au\/TiO2 catalyst","volume":"333","author":"Green","year":"2011","journal-title":"Science"},{"key":"mlstac191cbib9","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.jcat.2011.06.022","article-title":"In situ XPS study of the adsorption and reactions of NO and O2 on gold nanoparticles deposited on TiO2 and SiO2","volume":"283","author":"Herranz","year":"2011","journal-title":"J. Catal."},{"key":"mlstac191cbib10","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1038\/nature20795","article-title":"High-spatial-resolution mapping of catalytic reactions on single particles","volume":"541","author":"Wu","year":"2017","journal-title":"Nature"},{"key":"mlstac191cbib11","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1126\/science.1164170","article-title":"Reaction-driven restructuring of Rh-Pd and Pt-Pd core-shell nanoparticles","volume":"322","author":"Tao","year":"2008","journal-title":"Science"},{"key":"mlstac191cbib12","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1038\/nature23661","article-title":"Direct instrumental identification of catalytically active surface sites","volume":"549","author":"Pfisterer","year":"2017","journal-title":"Nature"},{"key":"mlstac191cbib13","doi-asserted-by":"publisher","DOI":"10.1063\/1.2960569","article-title":"A new scanning tunneling microscope reactor used for high-pressure and high-temperature catalysis studies","volume":"79","author":"Tao","year":"2008","journal-title":"Rev. Sci. Instrum."},{"key":"mlstac191cbib14","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1126\/science.1182122","article-title":"Break-up of stepped platinum catalyst surfaces by high co coverage","volume":"327","author":"Tao","year":"2010","journal-title":"Science"},{"key":"mlstac191cbib15","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.ultramic.2003.08.008","article-title":"Surface crystallography via electron microscopy","volume":"98","author":"Subramanian","year":"2004","journal-title":"Ultramicroscopy"},{"key":"mlstac191cbib16","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1021\/cr500084c","article-title":"Electron microscopy of solid catalysts\u2014transforming from a challenge to a toolbox","volume":"115","author":"Su","year":"2015","journal-title":"Chem. Rev."},{"key":"mlstac191cbib17","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1021\/acs.accounts.7b00076","article-title":"Atomic-resolution transmission electron microscopic movies for study of organic molecules, assemblies and reactions: the first 10 years of development","volume":"50","author":"Nakamura","year":"2017","journal-title":"Acc. Chem. Res."},{"key":"mlstac191cbib18","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1038\/nnano.2010.234","article-title":"Towards full-structure determination of bimetallic nanoparticles with an aberration-corrected electron microscope","volume":"5","author":"Ortalan","year":"2010","journal-title":"Nat. Nanotechnol."},{"key":"mlstac191cbib19","doi-asserted-by":"publisher","first-page":"1755","DOI":"10.1126\/science.1159846","article-title":"The role of interstitial sites in the Ti 3d defect state in the band gap of titania","volume":"320","author":"Wendt","year":"2008","journal-title":"Science"},{"key":"mlstac191cbib20","doi-asserted-by":"publisher","first-page":"14419","DOI":"10.1021\/acscatal.0c03335","article-title":"Recent progresses on structural reconstruction of nanosized metal catalysts via controlled-atmosphere transmission electron microscopy: a review","volume":"10","author":"Tang","year":"2020","journal-title":"ACS Catal."},{"key":"mlstac191cbib21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.145301","article-title":"Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties","volume":"120","author":"Xie","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstac191cbib22","doi-asserted-by":"publisher","first-page":"4401","DOI":"10.1021\/acs.jpclett.9b01428","article-title":"Convolutional neural network of atomic surface structures to predict binding energies for high-throughput screening of catalysts","volume":"10","author":"Back","year":"2019","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstac191cbib23","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1038\/s41929-018-0142-1","article-title":"Active learning across intermetallics to guide discovery of electrocatalysts for CO2 reduction and H2 evolution","volume":"1","author":"Tran","year":"2018","journal-title":"Nat. Catal."},{"key":"mlstac191cbib24","doi-asserted-by":"publisher","first-page":"24131","DOI":"10.1039\/C7TA01812F","article-title":"High-throughput screening of bimetallic catalysts enabled by machine learning","volume":"5","author":"Li","year":"2017","journal-title":"J. Mater. Chem. A"},{"key":"mlstac191cbib25","doi-asserted-by":"publisher","first-page":"3528","DOI":"10.1021\/acs.jpclett.5b01660","article-title":"Machine-learning-augmented chemisorption model for CO2 electroreduction catalyst screening","volume":"6","author":"Ma","year":"2015","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstac191cbib26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.125.173001","article-title":"Differentiable optimization for the prediction of ground state structures (DOGSS)","volume":"125","author":"Yoon","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstac191cbib27","doi-asserted-by":"publisher","first-page":"2873","DOI":"10.1007\/s11661-021-06279-5","article-title":"Prediction of mechanical properties of wrought aluminium alloys using feature engineering assisted machine learning approach","volume":"52","author":"Hu","year":"2021","journal-title":"Metallurgical Mater. Trans. A"},{"key":"mlstac191cbib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.mtcomm.2020.101871","article-title":"Yield strength prediction of high-entropy alloys using machine learning","volume":"26","author":"Bhandari","year":"2021","journal-title":"Mater. Today Commun."},{"key":"mlstac191cbib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.matdes.2019.108378","article-title":"A machine-learning approach to predicting and understanding the properties of amorphous metallic alloys","volume":"187","author":"Xiong","year":"2020","journal-title":"Mater. Des."},{"key":"mlstac191cbib30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.156001","article-title":"Data-driven learning of total and local energies in elemental boron","volume":"120","author":"Deringer","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstac191cbib31","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201902765","article-title":"Machine learning interatomic potentials as emerging tools for materials science","volume":"31","author":"Deringer","year":"2019","journal-title":"Adv. Mater."},{"key":"mlstac191cbib32","doi-asserted-by":"publisher","first-page":"1032","DOI":"10.1002\/qua.24890","article-title":"Constructing high-dimensional neural network potentials: a tutorial review","volume":"115","author":"Behler","year":"2015","journal-title":"Int. J. Quantum Chem."},{"key":"mlstac191cbib33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.99.064114","article-title":"Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning","volume":"99","author":"Podryabinkin","year":"2019","journal-title":"Phys. Rev. B"},{"key":"mlstac191cbib34","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1021\/acs.jctc.8b00908","article-title":"Schnetpack: a deep learning toolbox for atomistic systems","volume":"15","author":"Sch\u00fctt","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"mlstac191cbib35","article-title":"Schnet: a continuous-filter convolutional neural network for modeling quantum interactions","author":"Sch\u00fctt","year":"2017"},{"key":"mlstac191cbib36","doi-asserted-by":"publisher","DOI":"10.1063\/5.0015571","article-title":"Gaussian representation for image recognition and reinforcement learning of atomistic structure","volume":"153","author":"Christiansen","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstac191cbib37","first-page":"pp 8959","article-title":"Reinforcement learning for molecular design guided by quantum mechanics","volume":"vol 119","author":"Simm","year":"2020"},{"key":"mlstac191cbib38","article-title":"Structure prediction of surface reconstructions by deep reinforcement learning","volume":"32","author":"Meldgaard","year":"2020","journal-title":"J. Phys.: Condens. Matter."},{"key":"mlstac191cbib39","doi-asserted-by":"publisher","DOI":"10.1063\/1.5108871","article-title":"Atomistic structure learning","volume":"151","author":"J\u0142orgensen","year":"2019","journal-title":"J. Chem. Phys."},{"key":"mlstac191cbib40","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1021\/acscentsci.7b00492","article-title":"Optimizing chemical reactions with deep reinforcement learning","volume":"3","author":"Zhou","year":"2017","journal-title":"ACS Cent. Sci."},{"key":"mlstac191cbib41","doi-asserted-by":"publisher","first-page":"4850","DOI":"10.1016\/j.ijhydene.2013.12.148","article-title":"Hydrogen generation from formic acid decomposition at room temperature using a NiAuPd alloy nanocatalyst","volume":"39","author":"Wang","year":"2014","journal-title":"Int. J. Hydrog. Energy"},{"key":"mlstac191cbib42","doi-asserted-by":"publisher","first-page":"25677","DOI":"10.1021\/jp305323s","article-title":"Outstanding catalyst performance of PdAuNi nanoparticles for the anodic reaction in an alkaline direct ethanol (with anion-exchange membrane) fuel cell","volume":"116","author":"Dutta","year":"2012","journal-title":"J. Phys. Chem. C"},{"key":"mlstac191cbib43","doi-asserted-by":"publisher","first-page":"5297","DOI":"10.1021\/acs.jpcc.5b10711","article-title":"Hydrogen solubility of magnetron co-sputtered FCC and BCC PdCuAu thin films","volume":"120","author":"Honrado Guerreiro","year":"2016","journal-title":"J. Phys. Chem. C"},{"key":"mlstac191cbib44","doi-asserted-by":"publisher","DOI":"10.1002\/admi.201901784","article-title":"Surface segregation of ternary alloys: effect of the interaction between solute elements","volume":"7","author":"Zhao","year":"2020","journal-title":"Adv. Mater. Interfaces"},{"key":"mlstac191cbib45","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1002\/sia.5759","article-title":"Surface composition of PdCuAu ternary alloys: a combined LEIS and XPS study","volume":"47","author":"Tarditi","year":"2015","journal-title":"Surf. Interface Anal."},{"key":"mlstac191cbib46","doi-asserted-by":"publisher","first-page":"11659","DOI":"10.1039\/D0NR01358G","article-title":"Unexpectedly high stability and surface reconstruction of PdAuAg nanoparticles for formate oxidation electrocatalysis","volume":"12","author":"Pan","year":"2020","journal-title":"Nanoscale"},{"key":"mlstac191cbib47","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.susc.2010.10.001","article-title":"Novel PdAgCu ternary alloy as promising materials for hydrogen separation membranes: synthesis and characterization","volume":"605","author":"Tarditi","year":"2011","journal-title":"Surf. Sci."},{"key":"mlstac191cbib48","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.jpowsour.2018.11.044","article-title":"Ternary CoAuPd and binary AuPd electrocatalysts for methanol oxidation and oxygen reduction reaction: enhanced catalytic performance by surface reconstruction","volume":"412","author":"Luo","year":"2019","journal-title":"J. Power Sources"},{"key":"mlstac191cbib49","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.apcatb.2018.09.067","article-title":"Surface reconstruction engineering of twinned Pd2CoAg nanocrystals by atomic vacancy inducement for hydrogen evolution and oxygen reduction reactions","volume":"241","author":"Liu","year":"2019","journal-title":"Appl. Catal.B"},{"key":"mlstac191cbib50","author":"Sutton","year":"2018"},{"key":"mlstac191cbib51","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"mlstac191cbib52","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"mlstac191cbib53","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"mlstac191cbib54","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2016"},{"key":"mlstac191cbib55","first-page":"pp 1889","article-title":"Trust region policy optimization","author":"Schulman","year":"2015"},{"key":"mlstac191cbib56","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"mlstac191cbib57","doi-asserted-by":"publisher","first-page":"eaa7885","DOI":"10.1126\/sciadv.aap7885","article-title":"Deep reinforcement learning for de novo drug design","volume":"4","author":"Popova","year":"2018","journal-title":"Sci. Adv."},{"key":"mlstac191cbib58","first-page":"1","article-title":"Optimization of molecules via deep reinforcement learning","volume":"9","author":"Zhou","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstac191cbib59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41699-021-00246-9","article-title":"Efficient water desalination with graphene nanopores obtained using artificial intelligence","volume":"5","author":"Wang","year":"2021","journal-title":"npj 2D Mater. Appl."},{"key":"mlstac191cbib60","first-page":"pp 1057","volume":"vol 99","author":"Sutton","year":"1999"},{"key":"mlstac191cbib61","first-page":"pp 1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"mlstac191cbib62","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"mlstac191cbib63","first-page":"pp 735","article-title":"Continuous-discrete reinforcement learning for hybrid control in robotics","author":"Neunert","year":"2020"},{"key":"mlstac191cbib64","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2019\/316","article-title":"Hybrid actor-critic reinforcement learning in parameterized action space","author":"Fan","year":"2019"},{"key":"mlstac191cbib65","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.146401","article-title":"Generalized neural-network representation of high-dimensional potential-energy surfaces","volume":"98","author":"Behler","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"mlstac191cbib66","doi-asserted-by":"publisher","first-page":"6536","DOI":"10.1021\/acs.jctc.9b00869","article-title":"Accelerated saddle point refinement through full exploitation of partial Hessian diagonalization","volume":"15","author":"Hermes","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"mlstac191cbib67","article-title":"The atomic simulation environment\u2014a python library for working with atoms","volume":"29","author":"Larsen","year":"2017","journal-title":"J. Phys.: Condens. Matter."},{"key":"mlstac191cbib68","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s11837-011-0102-6","article-title":"The potential of atomistic simulations and the knowledgebase of interatomic models","volume":"63","author":"Tadmor","year":"2011","journal-title":"JOM"},{"key":"mlstac191cbib69","doi-asserted-by":"publisher","first-page":"7423","DOI":"10.1103\/PhysRevB.35.7423","article-title":"Interatomic interactions in the effective-medium theory","volume":"35","author":"Jacobsen","year":"1987","journal-title":"Phys. Rev. B"},{"key":"mlstac191cbib70","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1016\/0039-6028(96)00816-3","article-title":"A semi-empirical effective medium theory for metals and alloys","volume":"366","author":"Jacobsen","year":"1996","journal-title":"Surf. Sci."},{"key":"mlstac191cbib71","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"mlstac191cbib72","article-title":"Tensorforce: a tensorflow library for applied reinforcement learning","author":"Kuhnle","year":"2017"},{"key":"mlstac191cbib73","doi-asserted-by":"publisher","first-page":"9911","DOI":"10.1063\/1.1724816","article-title":"Minima hopping: an efficient search method for the global minimum of the potential energy surface of complex molecular systems","volume":"120","author":"Goedecker","year":"2004","journal-title":"J. Chem. Phys."},{"key":"mlstac191cbib74","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.susc.2017.11.003","article-title":"The structure of reconstructed chalcopyrite surfaces","volume":"669","author":"Thinius","year":"2018","journal-title":"Surf. Sci."},{"key":"mlstac191cbib75","doi-asserted-by":"publisher","first-page":"7618","DOI":"10.1038\/s41598-017-06877-7","article-title":"Metastable exohedrally decorated borospherene B40","volume":"7","author":"Saha","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstac191cbib76","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/S0039-6028(98)00363-X","article-title":"The surface energy of metals","volume":"411","author":"Vitos","year":"1998","journal-title":"Surf. Sci."},{"key":"mlstac191cbib77","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.susc.2015.04.017","article-title":"Surface segregation in AuPd alloys: ab initio analysis of the driving forces","volume":"639","author":"Creuze","year":"2015","journal-title":"Surf. Sci."},{"key":"mlstac191cbib78","doi-asserted-by":"publisher","first-page":"10605","DOI":"10.1021\/acs.jpcc.0c02058","article-title":"Surface segregation across ternary alloy composition space: Cu x Au y Pd 1\u2212x\u2212y","volume":"124","author":"Yin","year":"2020","journal-title":"J. Phys. Chem. C"},{"key":"mlstac191cbib79","doi-asserted-by":"publisher","first-page":"18535","DOI":"10.1021\/jp053515r","article-title":"The composition and structure of Pd\u2013Au surfaces","volume":"109","author":"Yi","year":"2005","journal-title":"J. Phys. Chem. B"},{"key":"mlstac191cbib80","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/0039-6028(75)90127-2","article-title":"Determination of the surface composition of palladium-nickel alloy film catalysts using Auger electron spectroscopy","volume":"53","author":"Stoddart","year":"1975","journal-title":"Surf. Sci."},{"key":"mlstac191cbib81","doi-asserted-by":"publisher","DOI":"10.1116\/1.3520434","article-title":"Segregation and interlayer relaxation at the NiPd(111) surface","volume":"29","author":"Derry","year":"2011","journal-title":"J. Vac. Sci. Technol. A"},{"key":"mlstac191cbib82","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0039-6028(00)00269-7","article-title":"STM comparative study of the Pd8Ni92(110) alloy surface and the Pd\/Ni(110) surface alloy","volume":"454-456","author":"Abel","year":"2000","journal-title":"Surf. Sci."},{"key":"mlstac191cbib83","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/0021-9517(73)90161-9","article-title":"Surface composition of nickel\u2013gold alloys","volume":"30","author":"Williams","year":"1973","journal-title":"J. Catal."},{"key":"mlstac191cbib84","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1063\/1.433171","article-title":"Surface segregation in alloys: LEED, Auger, and gas adsorption study of segregation of Au to the (111) surface of Ni","volume":"65","author":"Burton","year":"1976","journal-title":"J. Chem. Phys."},{"key":"mlstac191cbib85","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1016\/j.susc.2004.06.021","article-title":"IMFP measurements near Au\u2013Ni alloy surfaces by EPES: indirect evidence of submonolayer Au surface enrichment","volume":"566-568","author":"Krawczyk","year":"2004","journal-title":"Surf. Sci."},{"key":"mlstac191cbib86","doi-asserted-by":"publisher","first-page":"9978","DOI":"10.1063\/1.1323224","article-title":"Improved tangent estimate in the nudged elastic band method for finding minimum energy paths and saddle points","volume":"113","author":"Henkelman","year":"2000","journal-title":"J. Chem. Phys."},{"key":"mlstac191cbib87","doi-asserted-by":"publisher","first-page":"9901","DOI":"10.1063\/1.1329672","article-title":"A climbing image nudged elastic band method for finding saddle points and minimum energy paths","volume":"113","author":"Henkelman","year":"2000","journal-title":"J. Chem. Phys."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,12]],"date-time":"2021-12-12T17:55:38Z","timestamp":1639331738000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac191c"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,27]]},"references-count":87,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,8,27]]},"published-print":{"date-parts":[[2021,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac191c","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,27]]},"assertion":[{"value":"Deep reinforcement learning for predicting kinetic pathways to surface reconstruction in a ternary alloy","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2021-06-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-07-29","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-08-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}