{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:07:29Z","timestamp":1754154449246,"version":"3.41.2"},"reference-count":48,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["12074145"],"award-info":[{"award-number":["12074145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Jilin Provincial Research Foundation for Basic Research, China","award":["20220101003JC"],"award-info":[{"award-number":["20220101003JC"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>We have developed a deep convolutional neural network integrated with attention mechanisms to directly process two-dimensional stochastically constrained electrostatic potentials, and established an end-to-end mapping from electrostatic potentials to ground-state energy. Compared with existing methods, this model achieves superior median absolute error-with only 1\/10 of the required data volume-and adopts a lightweight architecture to reduce parameter redundancy. Furthermore, we proposed a transfer learning strategy that uses the pre-trained model as a \u2018large model\u2019 and fine-tunes it using three specific potential functions: simple harmonic oscillator (ho), infinite well (iw), and double inverted negative Gaussian (ng). Experimental results demonstrate that the adapted \u2018large model\u2019 accurately predicts these specific potential functions, effectively addressing the common generalization limitations in neural network-based partial differential equation solutions. This approach establishes a novel paradigm integrating efficiency and high precision for multi-electron system calculations.<\/jats:p>","DOI":"10.1088\/2632-2153\/adeef9","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T09:19:56Z","timestamp":1753348796000},"page":"035013","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient solving of Schr\u00f6dinger equation using deep convolutional neural network model with an attention mechanism and transfer learning"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1103-7807","authenticated-orcid":true,"given":"Ziyi","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Shishun","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1582-9682","authenticated-orcid":true,"given":"Mingjun","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9708-9897","authenticated-orcid":true,"given":"Yujun","family":"Yang","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"mlstadeef9bib1","doi-asserted-by":"publisher","first-page":"30334","DOI":"10.1039\/C6CP02553F","article-title":"The I-TTM model for ab initio-based ion\u2013water interaction potentials. II. Alkali metal ion\u2013water potential energy functions","volume":"18","author":"Riera","year":"2016","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstadeef9bib2","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.1021\/ct5001044","article-title":"General multiobjective force field optimization framework, with application to reactive force fields for silicon carbide","volume":"10","author":"Jaramillo-Botero","year":"2014","journal-title":"J. Chem. Theory Comput."},{"key":"mlstadeef9bib3","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1103\/PhysRevLett.64.1955","article-title":"Force fields for silicas and aluminophosphates based on ab initio calculations","volume":"64","author":"Van Beest","year":"1990","journal-title":"Phys. Rev. Lett."},{"key":"mlstadeef9bib4","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/S0065-3233(03)66002-X","article-title":"Force fields for protein simulations","volume":"66","author":"Ponder","year":"2003","journal-title":"Adv. Protein Chem."},{"key":"mlstadeef9bib5","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1002\/prot.21123","article-title":"Comparison of multiple amber force fields and development of improved protein backbone parameters","volume":"65","author":"Hornak","year":"2006","journal-title":"Proteins: Struct. Funct. Bioinf."},{"key":"mlstadeef9bib6","doi-asserted-by":"publisher","first-page":"3752","DOI":"10.1021\/acs.jpclett.6b01562","article-title":"Ab initio-based bond order potential to investigate low thermal conductivity of stanene nanostructures","volume":"7","author":"Cherukara","year":"2016","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstadeef9bib7","doi-asserted-by":"publisher","DOI":"10.1063\/1.2799196","article-title":"Development of a classical force field for the oxidized Si surface: application to hydrophilic wafer bonding","volume":"127","author":"Cole","year":"2007","journal-title":"J. Chem. Phys."},{"key":"mlstadeef9bib8","doi-asserted-by":"publisher","first-page":"10520","DOI":"10.1021\/acs.chemrev.8b00728","article-title":"Concepts of artificial intelligence for computer-assisted drug discovery","volume":"119","author":"Yang","year":"2019","journal-title":"Chem. Rev."},{"key":"mlstadeef9bib9","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1021\/acs.jcim.6b00740","article-title":"Protein\u2013ligand scoring with convolutional neural networks","volume":"57","author":"Ragoza","year":"2017","journal-title":"J. Chem. Inf. Modeling"},{"key":"mlstadeef9bib10","doi-asserted-by":"publisher","first-page":"2545","DOI":"10.1021\/acs.jcim.9b00266","article-title":"Deep learning in chemistry","volume":"59","author":"Mater","year":"2019","journal-title":"J. Chem. Inf. Modeling"},{"key":"mlstadeef9bib11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.033429","article-title":"Ab initio solution of the many-electron Schr\u00f6dinger equation with deep neural networks","volume":"2","author":"Pfau","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstadeef9bib12","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.1039\/C7SC04934J","article-title":"The tensormol-0.1 model chemistry: a neural network augmented with long-range physics","volume":"9","author":"Yao","year":"2018","journal-title":"Chem. Sci."},{"key":"mlstadeef9bib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.98.104426","article-title":"Solving frustrated quantum many-particle models with convolutional neural networks","volume":"98","author":"Liang","year":"2018","journal-title":"Phys. Rev. B"},{"key":"mlstadeef9bib14","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1007\/s00158-018-2101-5","article-title":"Deep learning for determining a near-optimal topological design without any iteration","volume":"59","author":"Yu","year":"2019","journal-title":"Struct. Multidiscip. Optim."},{"key":"mlstadeef9bib15","doi-asserted-by":"publisher","first-page":"433","DOI":"10.32604\/cmc.2019.06660","article-title":"A deep collocation method for the bending analysis of Kirchhoff plate","volume":"59","author":"Guo","year":"2019","journal-title":"Comput. Mater. Contin."},{"key":"mlstadeef9bib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.066401","article-title":"Machine learning topological invariants with neural networks","volume":"120","author":"Zhang","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstadeef9bib17","first-page":"pp 1","article-title":"Study on a 3D Possion\u2019s equation slover based on deep learning technique","author":"Shan","year":"2018"},{"key":"mlstadeef9bib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.97.205140","article-title":"Self-learning Monte Carlo with deep neural networks","volume":"97","author":"Shen","year":"2018","journal-title":"Phys. Rev. B"},{"article-title":"Lat-Net: compressing lattice Boltzmann flow simulations using deep neural networks","year":"2017","author":"Hennigh","key":"mlstadeef9bib19"},{"key":"mlstadeef9bib20","doi-asserted-by":"publisher","DOI":"10.1038\/srep40827","article-title":"Lifetime prediction for organic coating under alternating hydrostatic pressure by artificial neural network","volume":"7","author":"Tian","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstadeef9bib21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.058301","article-title":"Fast and accurate modeling of molecular atomization energies with machine learning","volume":"108","author":"Rupp","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstadeef9bib22","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/15\/9\/095003","article-title":"Machine learning of molecular electronic properties in chemical compound space","volume":"15","author":"Montavon","year":"2013","journal-title":"New J. Phys."},{"article-title":"Machine learning prediction errors better than DFT accuracy","year":"2017","author":"Faber","key":"mlstadeef9bib23"},{"key":"mlstadeef9bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.89.235411","article-title":"Modeling electronic quantum transport with machine learning","volume":"89","author":"Lopez-Bezanilla","year":"2014","journal-title":"Phys. Rev. B"},{"key":"mlstadeef9bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.253002","article-title":"Finding density functionals with machine learning","volume":"108","author":"Snyder","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstadeef9bib26","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1038\/s41467-017-00839-3","article-title":"Bypassing the Kohn\u2013Sham equations with machine learning","volume":"8","author":"Brockherde","year":"2017","journal-title":"Nat. Commun."},{"key":"mlstadeef9bib27","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1021\/acs.jctc.5b01011","article-title":"Kinetic energy of hydrocarbons as a function of electron density and convolutional neural networks","volume":"12","author":"Yao","year":"2016","journal-title":"J. Chem. Theory Comput."},{"key":"mlstadeef9bib28","doi-asserted-by":"publisher","first-page":"3041","DOI":"10.1007\/s11071-018-04739-z","article-title":"Bilinear neural network method to obtain the exact analytical solutions of nonlinear partial differential equations and its application to p-gBKP equation","volume":"95","author":"Zhang","year":"2019","journal-title":"Nonlinear Dyn."},{"key":"mlstadeef9bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.padiff.2024.100682","article-title":"The bilinear neural network method for solving Benney\u2013Luke equation","volume":"10","author":"Tuan","year":"2024","journal-title":"Part. Differ. Equ. Appl. Math."},{"key":"mlstadeef9bib30","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/s11071-022-07207-x","article-title":"Bilinear residual network method for solving the exactly explicit solutions of nonlinear evolution equations","volume":"108","author":"Zhang","year":"2022","journal-title":"Nonlinear Dyn."},{"key":"mlstadeef9bib31","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1126\/science.1165893","article-title":"Distilling free-form natural laws from experimental data","volume":"324","author":"Schmidt","year":"2009","journal-title":"Science"},{"key":"mlstadeef9bib32","doi-asserted-by":"publisher","DOI":"10.1063\/5.0037319","article-title":"Artificial neural networks for the kinetic energy functional of non-interacting fermions","volume":"154","author":"Ghasemi","year":"2021","journal-title":"J. Chem. Phys."},{"key":"mlstadeef9bib33","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/0893-6080(89)90003-8","article-title":"On the approximate realization of continuous mappings by neural networks","volume":"2","author":"Funahashi","year":"1989","journal-title":"Neural Netw."},{"key":"mlstadeef9bib34","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/S0893-6080(00)00031-9","article-title":"Neural networks with a continuous squashing function in the output are universal approximators","volume":"13","author":"Castro","year":"2000","journal-title":"Neural Netw."},{"key":"mlstadeef9bib35","first-page":"pp 675","article-title":"Caffe: convolutional architecture for fast feature embedding","author":"Jia","year":"2014"},{"key":"mlstadeef9bib36","article-title":"Best practices for convolutional neural networks applied to visual document analysis","volume":"vol 3","author":"Simard","year":"2003"},{"key":"mlstadeef9bib37","first-page":"p 1237","article-title":"Flexible, high performance convolutional neural networks for image classification","volume":"vol 22","author":"Ciresan","year":"2011"},{"key":"mlstadeef9bib38","first-page":"pp 1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"mlstadeef9bib39","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"mlstadeef9bib40","first-page":"pp 770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"mlstadeef9bib41","doi-asserted-by":"publisher","first-page":"88","DOI":"10.3390\/opt5010007","article-title":"Electronic population reconstruction from strong-field-modified absorption spectra with a convolutional neural network","volume":"5","author":"Richter","year":"2024","journal-title":"Optics"},{"key":"mlstadeef9bib42","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3390\/e23010095","article-title":"Deep neural network model for approximating eigenmodes localized by a confining potential","volume":"23","author":"Grubi\u0161i\u0107","year":"2021","journal-title":"Entropy"},{"key":"mlstadeef9bib43","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.96.042113","article-title":"Deep learning and the Schr\u00f6dinger equation","volume":"96","author":"Mills","year":"2017","journal-title":"Phys. Rev. A"},{"key":"mlstadeef9bib44","first-page":"p 27","article-title":"Recurrent models of visual attention","author":"Mnih","year":"2014"},{"key":"mlstadeef9bib45","first-page":"pp 4438","article-title":"Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition","author":"Fu","year":"2017"},{"key":"mlstadeef9bib46","first-page":"pp 3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"mlstadeef9bib47","first-page":"pp 3146","article-title":"Dual attention network for scene segmentation","author":"Fu","year":"2019"},{"key":"mlstadeef9bib48","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/BF01321860","article-title":"Numerical recipes: the art of scientific computing","volume":"19","author":"Frolkovi\u010d","year":"1990","journal-title":"Acta Appl. Math."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adeef9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adeef9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adeef9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adeef9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T09:19:57Z","timestamp":1753348797000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adeef9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":48,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,7,24]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adeef9","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,7,24]]},"assertion":[{"value":"Efficient solving of Schr\u00f6dinger equation using deep convolutional neural network model with an attention mechanism and transfer learning","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 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-05-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-11","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-24","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}