{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:06:08Z","timestamp":1784203568873,"version":"3.55.0"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010083","name":"Hunan Provincial Innovation Foundation for Postgraduate","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010083","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.109040","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:07:33Z","timestamp":1777129653000},"page":"109040","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-particle neural operator transformer for solving partial differential equations"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3222-5656","authenticated-orcid":false,"given":"Shengjun","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxiang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6556-6222","authenticated-orcid":false,"given":"Hanchao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinru","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109040_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.cpc.2025.109702","article-title":"Pinto: Physics-informed transformer neural operator for learning generalized solutions of partial differential equations for any initial and boundary condition","volume":"315","author":"Boya","year":"2025","journal-title":"Computer Physics Communications"},{"issue":"15","key":"10.1016\/j.neunet.2026.109040_bib0002","doi-asserted-by":"crossref","first-page":"3932","DOI":"10.1073\/pnas.1517384113","article-title":"Discovering governing equations from data by sparse identification of nonlinear dynamical systems","volume":"113","author":"Brunton","year":"2016","journal-title":"Proceedings of the national academy of sciences"},{"issue":"4","key":"10.1016\/j.neunet.2026.109040_bib0003","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1090\/S0894-0347-2012-00740-1","article-title":"Image restoration: Total variation, wavelet frames, and beyond","volume":"25","author":"Cai","year":"2012","journal-title":"Journal of the American Mathematical Society"},{"key":"10.1016\/j.neunet.2026.109040_bib0004","series-title":"Proceedings of the 35th neural information processing systems, NeurIPS, December 6\u201314, virtual","first-page":"24924","article-title":"Choose a transformer: Fourier or galerkin","author":"Cao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109040_bib0005","series-title":"Proceedings of the 32th neural information processing systems, neurIPS, December 3\u20138, Canada","first-page":"6572","article-title":"Neural ordinary differential equations","author":"Chen","year":"2018"},{"issue":"4","key":"10.1016\/j.neunet.2026.109040_bib0006","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1109\/72.392253","article-title":"Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems","volume":"6","author":"Chen","year":"1995","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"1","key":"10.1016\/j.neunet.2026.109040_bib0007","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1137\/15M1037457","article-title":"Image restoration: Wavelet frame shrinkage, nonlinear evolution pdes, and beyond","volume":"15","author":"Dong","year":"2017","journal-title":"Multiscale Modeling & Simulation"},{"key":"10.1016\/j.neunet.2026.109040_bib0008","series-title":"Proceedings of the 34th neural information processing systems, neurIPS, December 6\u201314, virtual","first-page":"5531","article-title":"Redesigning the transformer architecture with insights from multi-particle dynamical systems","author":"Dutta","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2026.109040_bib0009","first-page":"12","article-title":"A mathematical framework for transformer circuits","volume":"1","author":"Elhage","year":"2021","journal-title":"Transformer Circuits Thread"},{"key":"10.1016\/j.neunet.2026.109040_bib0010","series-title":"Proceedings of 37th neural information processing systems, NeurIPS, USA, December 10\u201316","first-page":"57026","article-title":"The emergence of clusters in self-attention dynamics","author":"Geshkovski","year":"2023"},{"key":"10.1016\/j.neunet.2026.109040_bib0011","unstructured":"Geshkovski, B., Letrouit, C., Polyanskiy, Y., & Rigollet, P. (2023b). A mathematical perspective on transformers. arXiv preprint arXiv: 2312.10794."},{"key":"10.1016\/j.neunet.2026.109040_bib0012","series-title":"Chemical oscillations and instabilities: Non-linear chemical kinetics","author":"Gray","year":"1990"},{"issue":"1","key":"10.1016\/j.neunet.2026.109040_bib0013","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6420\/aa9a90","article-title":"Stable architectures for deep neural networks","volume":"34","author":"Haber","year":"2017","journal-title":"Inverse Problems"},{"key":"10.1016\/j.neunet.2026.109040_bib0014","series-title":"Proceedings of the 35th international conference on machine learning, ICML, 23\u201329 July, USA","first-page":"12556","article-title":"GNOT: A general neural operator transformer for operator learning","author":"Hao","year":"2023"},{"issue":"5","key":"10.1016\/j.neunet.2026.109040_bib0015","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural networks"},{"key":"10.1016\/j.neunet.2026.109040_bib0016","series-title":"Differential equations and mathematical biology","author":"Jones","year":"2009"},{"key":"10.1016\/j.neunet.2026.109040_bib0017","series-title":"Proceedings of the 9th international conference on learning representations, ICLR, Austria, May 3\u20137","first-page":"1","article-title":"Fourier neural operator for parametric partial differential equations","author":"Li","year":"2021"},{"key":"10.1016\/j.neunet.2026.109040_bib0018","first-page":"1","article-title":"Transformer for partial differential equations\u2019 operator learning","volume":"2023","author":"Li","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"issue":"3","key":"10.1016\/j.neunet.2026.109040_bib0019","first-page":"1","article-title":"Physics-informed neural operator for learning partial differential equations","volume":"1","author":"Li","year":"2024","journal-title":"ACM\/IMS Journal of Data Science"},{"key":"10.1016\/j.neunet.2026.109040_bib0020","series-title":"Proceedings of the 35th international conference on machine learning, ICML, Sweden, July 10\u201315","first-page":"3214","article-title":"Pde-net: Learning pdes from data","author":"Long","year":"2018"},{"issue":"3","key":"10.1016\/j.neunet.2026.109040_bib0021","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1038\/s42256-021-00302-5","article-title":"Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators","volume":"3","author":"Lu","year":"2021","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109040_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2022.114778","article-title":"A comprehensive and fair comparison of two neural operators (with practical extensions) based on fair data","volume":"393","author":"Lu","year":"2022","journal-title":"Computer Methods in Applied Mechanics and Engineering"},{"key":"10.1016\/j.neunet.2026.109040_bib0023","unstructured":"Lu, Y., Li, Z., He, D., Sun, Z., Dong, B., Qin, T., Wang, L., & Liu, T.-Y. (2019). Understanding and improving transformer from a multi-particle dynamic system point of view. arXiv preprint arXiv: 1906.02762."},{"key":"10.1016\/j.neunet.2026.109040_bib0024","series-title":"Proceedings of the 35th international conference on machine learning, ICML, Sweden, July 10\u201315","first-page":"3282","article-title":"Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations","author":"Lu","year":"2018"},{"key":"10.1016\/j.neunet.2026.109040_bib0025","series-title":"An introduction to celestial mechanics","author":"Moulton","year":"1970"},{"issue":"3","key":"10.1016\/j.neunet.2026.109040_bib0026","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1007\/s10851-019-00903-1","article-title":"Deep neural networks motivated by partial differential equations","volume":"62","author":"Ruthotto","year":"2020","journal-title":"Journal of Mathematical Imaging and Vision"},{"key":"10.1016\/j.neunet.2026.109040_bib0027","series-title":"Proceedings of the IEEE winter conference on applications of computer vision, WACV, USA, January 3\u20138","first-page":"3530","article-title":"Efficient attention: Attention with linear complexities","author":"Shen","year":"2021"},{"key":"10.1016\/j.neunet.2026.109040_bib0028","series-title":"Partial differential equations in physics","author":"Sommerfeld","year":"1949"},{"key":"10.1016\/j.neunet.2026.109040_bib0029","series-title":"Nuclear reactor physics","author":"Stacey","year":"2018"},{"key":"10.1016\/j.neunet.2026.109040_bib0030","series-title":"Proceedings of the 36th neural information processing systems, NeurIPS, USA, November 28,\u2013December 9","first-page":"1596","article-title":"PDEbench: An extensive benchmark for scientific machine learning","author":"Takamoto","year":"2022"},{"key":"10.1016\/j.neunet.2026.109040_bib0031","series-title":"Proceedings of the 11th international conference on learning representations, ICLR, Rwanda, May 1\u20135","first-page":"1","article-title":"Factorized fourier neural operators","author":"Tran","year":"2023"},{"key":"10.1016\/j.neunet.2026.109040_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2023.107436","article-title":"A wavelet neural operator based elastography for localization and quantification of tumors","volume":"232","author":"Tripura","year":"2023","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"10.1016\/j.neunet.2026.109040_bib0033","series-title":"Proceedings of the 31th neural information processing systems, NeurIps, USA, December 4\u20139","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2026.109040_bib0034","unstructured":"Vuckovic, J., Baratin, A., & Combes, R. T. d. (2020). A mathematical theory of attention. arXiv preprint arXiv: 2007.02876."},{"issue":"40","key":"10.1016\/j.neunet.2026.109040_bib0035","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.abi8605","article-title":"Learning the solution operator of parametric partial differential equations with physics-informed deepONets","volume":"7","author":"Wang","year":"2021","journal-title":"Science Advances"},{"key":"10.1016\/j.neunet.2026.109040_bib0036","series-title":"Proceedings of the 41th international conference on machine learning, ICML, Austria, July 21\u201327","first-page":"54288","article-title":"Improved operator learning by orthogonal attention","author":"Xiao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109040_bib0037","series-title":"Introduction to partial differential equations with applications","author":"Zachmanoglou","year":"1986"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005009?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005009?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:21:28Z","timestamp":1784200888000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026005009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":37,"alternative-id":["S0893608026005009"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109040","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-particle neural operator transformer for solving partial differential equations","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109040","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109040"}}