{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:57:36Z","timestamp":1785484656865,"version":"3.56.0"},"reference-count":35,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"4","funder":[{"name":"Maths4DL","award":["EP\/V026259\/1"],"award-info":[{"award-number":["EP\/V026259\/1"]}]},{"name":"Philip Leverhulme Prize"},{"name":"Royal Society Wolfson Fellowship"},{"name":"Wellcome Innovator Awards","award":["215733\/Z\/19\/Z"],"award-info":[{"award-number":["215733\/Z\/19\/Z"]}]},{"name":"Wellcome Innovator Awards","award":["221633\/Z\/20\/Z"],"award-info":[{"award-number":["221633\/Z\/20\/Z"]}]},{"name":"Cantab Capital Institute for the Mathematics of Information"},{"DOI":"10.13039\/100012338","name":"Alan Turing Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["777826"],"award-info":[{"award-number":["777826"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V029428\/1"],"award-info":[{"award-number":["EP\/V029428\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S026045\/1"],"award-info":[{"award-number":["EP\/S026045\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T003553\/1"],"award-info":[{"award-number":["EP\/T003553\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N014588\/1"],"award-info":[{"award-number":["EP\/N014588\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T017961\/1"],"award-info":[{"award-number":["EP\/T017961\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Sci. Comput."],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>Partial differential equation (PDE) problems often exhibit strong local spatial structures, and accurately capturing these features is essential for high-quality solution approximation. The Fourier neural operator (FNO) has recently emerged as a powerful method for solving PDEs by leveraging frequency-domain parameterization to efficiently model global patterns. In addition to its high predictive accuracy, FNO is valued for its resolution-invariant property. However, this global emphasis comes at the expense of local spatial fidelity, as frequency-based convolutions inherently lack the ability to effectively encode fine-grained local dependencies. Although several studies have attempted to address this limitation without compromising the resolution invariance, their methods often fall short in capturing sufficient local spatial features (LSFs) and tend to significantly increase computational cost. To overcome this challenge, we propose a simple yet effective hybrid framework, termed Conv-FNO, which incorporates a convolutional neural network\u2013based feature preextractor to capture LSFs directly from the input data. This architecture enhances the local representational capacity of FNO while maintaining its desirable global properties. To preserve resolution invariance, we introduce two resizing schemes for inputs with different resolutions. Theoretical analysis is provided to justify the effectiveness of our resizing schemes across varying resolutions. We conducted experiments on a wide range of representative PDEs to verify the effectiveness of Conv-FNO. Experimental results show that Conv-FNO not only significantly outperforms the standard FNO but also consistently surpasses other baseline methods.<\/jats:p>\n                  <jats:p>Reproducibility of computational results. This paper has been awarded the \u201cSIAM Reproducibility Badge: Code and data available\u201d as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https:\/\/github.com\/cyliu111\/Conv-FNO and in the supplementary materials ( Conv-FNO-main.zip [342KB]). [Formula: see text]<\/jats:p>","DOI":"10.1137\/25m1766723","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:02:04Z","timestamp":1785481324000},"page":"C991-C1010","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Fourier Neural Operators with Local Spatial Features"],"prefix":"10.1137","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2432-3758","authenticated-orcid":true,"given":"Chaoyu","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge, Cambridge, CB3 0WA, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Murari","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge, Cambridge, CB3 0WA, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihao","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge, Cambridge, CB3 0WA, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangming","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge, Cambridge, CB3 0WA, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Budd","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, University of Bath, Bath, BA2 7AY, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carola-Bibiane","family":"Sch\u00f6nlieb","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge, Cambridge, CB3 0WA, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"ref1","unstructured":"B. Bonev, T. Kurth, C. Hundt, J. Pathak, M. Baust, K. Kashinath, and A. Anandkumar, Spherical fourier neural operators: Learning stable dynamics on the sphere, in Proceedings of the International Conference on Machine Learning, PMLR, 2023, pp. 2806\u20132823."},{"key":"ref2","first-page":"83","volume-title":"Numerical Analysis Meets Machine Learning, Handb. Numer. Analy. 25","author":"Boull\u00e9 N.","year":"2024"},{"key":"ref3","unstructured":"J. Brandstetter, D. E. Worrall, and M. Welling, Message passing neural PDE solvers, in Proceedings of the International Conference on Learning Representations, 2022, https:\/\/openreview.net\/forum?id=vSix3HPYKSU."},{"key":"ref4","first-page":"24924","volume":"34","author":"Cao S.","year":"2021","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"W. T. Cochran, J. W. Cooley, D. L. Favin, H. D. Helms, R. A. Kaenel, W. W. Lang, G. C. Maling, D. E. Nelson, C. M. Rader, and P. D. Welch, What is the fast Fourier transform? Proc. IEEE, 55 (1967), pp. 1664\u20131674.","DOI":"10.1109\/PROC.1967.5957"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1134\/S1064562423701107"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.01.029"},{"key":"ref8","author":"George R. J.","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1088\/1741-4326\/ad313a"},{"key":"ref10","unstructured":"J. Helwig, X. Zhang, C. Fu, J. Kurtin, S. Wojtowytsch, and S. Ji, Group equivariant Fourier neural operators for partial differential equations, in Proceedings of the 40th International Conference on Machine Learning, JMLR.org, 2023."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2311"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00466-023-02331-w"},{"key":"ref13","author":"Kossaifi J.","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref14","first-page":"1","volume":"22","author":"Kovachki N.","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","first-page":"1","volume":"24","author":"Kovachki N.","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","series-title":"Handb. Numer. Anal. 25","first-page":"419","volume-title":"Numerical Analysis Meets Machine Learning","author":"Kovachki N. B.","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01136-8"},{"key":"ref18","unstructured":"Z. Li, N. Kovachki, K. Azizzadenesheli, B. Liu, K. Bhattacharya, A. Stuart, and A. Anandkumar, Fourier neural operator for parametric partial differential equations, in Proceedings of the International Conference on Learning Representations, 2021."},{"key":"ref19","first-page":"9","volume":"1","author":"Li Z.","year":"2024","journal-title":"ACM\/JMS J. Data Sci."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2024.0242"},{"key":"ref21","unstructured":"C. Liu, Y. Li, Z. Deng, C. Budd, and C.B. Sch\u00f6nlieb, Conservation-Preserved Fourier Neural Operator Through Adaptive Correction, preprint, arXiv:2505.24579, 2025."},{"key":"ref22","volume":"36","author":"Liu N.","year":"2024","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref23","unstructured":"M. Liu-Schiaffini, J. Berner, B. Bonev, T. Kurth, K. Azizzadenesheli, and A. Anandkumar,\n                      Neural operators with localized integral and differential kernels\n                      , in Proceedings of the ICLR 2024 Workshop on DifferentialEquations In Science, 2024, https:\/\/openreview.net\/forum?id=fTOeB5L4PP."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00302-5"},{"key":"ref25","first-page":"1","volume":"6","author":"McGreivy N.","year":"2024","journal-title":"Nature Mach. Intell."},{"key":"ref26","unstructured":"R. Molinaro, S. Lanthaler, B. Raoni\u0107, T. Rohner, V. Armegioiu, S. Simonis, D. Grund, Y. Ramic, Z. Y. Wan, F. Sha, et\u00a0al., Generative AI for Fast and Accurate Statistical Computation of Fluids, preprint, arXiv:2409.18359, 2024."},{"key":"ref27","unstructured":"J. Pathak, S. Subramanian, P. Harrington, S. Raja, A. Chattopadhyay, M. Mardani, T. Kurth, D. Hall, Z. Li, K. Azizzadenesheli, et\u00a0al., Fourcastnet: A Global Data-Driven High-Resolution Weather Model Using Adaptive Fourier Neural Operators, preprint, arXiv:2202.11214, 2022."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2024.106239"},{"key":"ref29","author":"Rahman M. A.","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref30","volume":"36","author":"Raonic B.","year":"2024","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, and T. Brox, U-Net: Convolutional networks for biomedical image segmentation, in Medical Image Computing and Computer-assisted Intervention\u2013MICCAI 2015: 18th International Conference, Part III, Springer, Cham, 2015, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0117"},{"key":"ref33","unstructured":"A. Tran, A. Mathews, L. Xie, and C. S. Ong, Factorized Fourier neural operators, in Proceedings of the 11th International Conference on Learning Representations, 2023, https:\/\/openreview.net\/forum?id=tmIiMPl4IPa."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abi8605"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.advwatres.2022.104180"}],"container-title":["SIAM Journal on Scientific Computing"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:02:09Z","timestamp":1785481329000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/25M1766723"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,8,31]]}},"alternative-id":["10.1137\/25M1766723"],"URL":"https:\/\/doi.org\/10.1137\/25m1766723","relation":{},"ISSN":["1064-8275","1095-7197"],"issn-type":[{"value":"1064-8275","type":"print"},{"value":"1095-7197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]}}}