{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:21:17Z","timestamp":1778001677898,"version":"3.51.4"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-023-00761-y","type":"journal-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T17:02:42Z","timestamp":1701709362000},"page":"1458-1465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Physics-enhanced deep surrogates for partial differential equations"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6267-8771","authenticated-orcid":false,"given":"Rapha\u00ebl","family":"Pestourie","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8798-1267","authenticated-orcid":false,"given":"Youssef","family":"Mroueh","sequence":"additional","affiliation":[]},{"given":"Chris","family":"Rackauckas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7288-0516","authenticated-orcid":false,"given":"Payel","family":"Das","sequence":"additional","affiliation":[]},{"given":"Steven G.","family":"Johnson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,4]]},"reference":[{"key":"761_CR1","doi-asserted-by":"crossref","unstructured":"Baker, N. et al. Workshop Report on Basic Research Needs for Scientific Machine Learning: Core Technologies for Artificial Intelligence. Technical Report (USDOE Office of Science, 2019).","DOI":"10.2172\/1478744"},{"key":"761_CR2","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1137\/130932715","volume":"57","author":"P Benner","year":"2015","unstructured":"Benner, P., Gugercin, S. & Willcox, K. A survey of projection-based model reduction methods for parametric dynamical systems. SIAM Rev. 57, 483\u2013531 (2015).","journal-title":"SIAM Rev."},{"key":"761_CR3","doi-asserted-by":"crossref","unstructured":"Willard, J., Jia, X., Xu, S., Steinbach, M. & Kumar, V. Integrating scientific knowledge with machine learning for engineering and environmental systems. ACM Comput. Surv. 55, 1\u201337 (2022).","DOI":"10.1145\/3514228"},{"key":"761_CR4","doi-asserted-by":"publisher","first-page":"eaau6792","DOI":"10.1126\/sciadv.aau6792","volume":"5","author":"J Hoffmann","year":"2019","unstructured":"Hoffmann, J. et al. Machine learning in a data-limited regime: augmenting experiments with synthetic data uncovers order in crumpled sheets. Sci. Adv. 5, eaau6792 (2019).","journal-title":"Sci. Adv."},{"key":"761_CR5","doi-asserted-by":"publisher","first-page":"107101","DOI":"10.1063\/5.0062546","volume":"33","author":"P Pant","year":"2021","unstructured":"Pant, P., Doshi, R., Bahl, P. & Barati Farimani, A. Deep learning for reduced order modelling and efficient temporal evolution of fluid simulations. Phys. Fluids 33, 107101 (2021).","journal-title":"Phys. Fluids"},{"key":"761_CR6","doi-asserted-by":"publisher","first-page":"33732","DOI":"10.1364\/OE.26.033732","volume":"26","author":"R Pestourie","year":"2018","unstructured":"Pestourie, R. et al. Inverse design of large-area metasurfaces. Opt. Expr. 26, 33732\u201333747 (2018).","journal-title":"Opt. Expr."},{"key":"761_CR7","unstructured":"Boyd, J. P. Chebyshev and Fourier Spectral Methods 2nd edn (Dover Publications, Inc., 2001)."},{"key":"761_CR8","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1038\/s41524-020-00431-2","volume":"6","author":"R Pestourie","year":"2020","unstructured":"Pestourie, R., Mroueh, Y., Nguyen, T. V., Das, P. & Johnson, S. G. Active learning of deep surrogates for PDEs: application to metasurface design. npj Comput. Mat. 6, 164 (2020).","journal-title":"npj Comput. Mat."},{"key":"761_CR9","doi-asserted-by":"crossref","unstructured":"Lu, L., Pestourie, R., Johnson, S. G. & Romano, G. Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport. Phys. Rev. Research 4, 023210 (2022).","DOI":"10.1103\/PhysRevResearch.4.023210"},{"key":"761_CR10","unstructured":"Pestourie, R. Assume Your Neighbor Is Your Equal: Inverse Design in Nanophotonics. PhD thesis, Harvard Univ. (2020)."},{"key":"761_CR11","doi-asserted-by":"crossref","unstructured":"Bayati, E. et al. Inverse designed extended depth of focus meta-optics for broadband imaging in the visible. Nanophotonics 11, 2531\u20132540 (2021).","DOI":"10.1515\/nanoph-2021-0431"},{"key":"761_CR12","doi-asserted-by":"crossref","unstructured":"Li, Z. et al. Inverse design enables large-scale high-performance meta-optics reshaping virtual reality. Nat. Commun. 13, 2409 (2022).","DOI":"10.1038\/s41467-022-29973-3"},{"key":"761_CR13","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1088\/0034-4885\/67\/5\/R03","volume":"67","author":"RJ Potton","year":"2004","unstructured":"Potton, R. J. Reciprocity in optics. Rep. Progr. Phys. 67, 717 (2004).","journal-title":"Rep. Progr. Phys."},{"key":"761_CR14","doi-asserted-by":"crossref","unstructured":"Li, B. et al. Trustworthy AI: from principles to practices. ACM Comput. Surv. 55, 1\u201346 (2023).","DOI":"10.1145\/3555803"},{"key":"761_CR15","doi-asserted-by":"publisher","first-page":"2778","DOI":"10.1364\/OL.34.002778","volume":"34","author":"AF Oskooi","year":"2009","unstructured":"Oskooi, A. F., Kottke, C. & Johnson, S. G. Accurate finite-difference time-domain simulation of anisotropic media by subpixel smoothing. Optics Lett. 34, 2778\u20132780 (2009).","journal-title":"Optics Lett."},{"key":"761_CR16","doi-asserted-by":"crossref","unstructured":"Ferziger, J. H., Peri\u0107, M. & Street, R. L. Computational Methods for Fluid Dynamics Vol. 3 (Springer, 2002).","DOI":"10.1007\/978-3-642-56026-2"},{"key":"761_CR17","unstructured":"Romano, G. OpenBTE: a solver for ab-initio phonon transport in multidimensional structures. Preprint at https:\/\/arxiv.org\/abs\/2106.02764 (2021)."},{"key":"761_CR18","first-page":"17429","volume":"33","author":"M Cranmer","year":"2020","unstructured":"Cranmer, M. et al. Discovering symbolic models from deep learning with inductive biases. Adv. Neural Info. Proc. Syst. 33, 17429\u201317442 (2020).","journal-title":"Adv. Neural Info. Proc. Syst."},{"key":"761_CR19","doi-asserted-by":"crossref","unstructured":"Rackauckas, C. et al. Universal differential equations for scientific machine learning. Preprint at https:\/\/arxiv.org\/abs\/2001.04385 (2020).","DOI":"10.21203\/rs.3.rs-55125\/v1"},{"key":"761_CR20","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","volume":"12","author":"AE Hoerl","year":"1970","unstructured":"Hoerl, A. E. & Kennard, R. W. Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12, 55\u201367 (1970).","journal-title":"Technometrics"},{"key":"761_CR21","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","volume":"3","author":"GE Karniadakis","year":"2021","unstructured":"Karniadakis, G. E. et al. Physics-informed machine learning. Nat. Rev. Phys. 3, 422\u2013440 (2021).","journal-title":"Nat. Rev. Phys."},{"key":"761_CR22","doi-asserted-by":"crossref","unstructured":"Lu, L. et al. Physics-informed neural networks with hard constraints for inverse design. SIAM J. Sci. Comput. 43, B1105\u2013B1132 (2021).","DOI":"10.1137\/21M1397908"},{"key":"761_CR23","doi-asserted-by":"crossref","unstructured":"Shin, Y., Darbon, J. & Karniadakis, G. E. On the convergence of physics informed neural networks for linear second-order elliptic and parabolic type PDEs. Commun. Comput. Phys. 28, 2042\u20132074 (2020).","DOI":"10.4208\/cicp.OA-2020-0193"},{"key":"761_CR24","doi-asserted-by":"publisher","first-page":"e2101784118","DOI":"10.1073\/pnas.2101784118","volume":"118","author":"D Kochkov","year":"2021","unstructured":"Kochkov, D. et al. Machine learning\u2013accelerated computational fluid dynamics. Proc. Natl Acad. Sci. USA 118, e2101784118 (2021).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"761_CR25","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1038\/s42256-021-00302-5","volume":"3","author":"L Lu","year":"2021","unstructured":"Lu, L., Jin, P., Pang, G., Zhang, Z. & Karniadakis, G. E. Learning nonlinear operators via deeponet based on the universal approximation theorem of operators. Nat. Mach. Intell. 3, 218\u2013229 (2021).","journal-title":"Nat. Mach. Intell."},{"key":"761_CR26","unstructured":"Li, Z. et al. Fourier neural operator for parametric partial differential equations. Preprint at https:\/\/arxiv.org\/abs\/2010.08895 (2020)."},{"key":"761_CR27","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1109\/MMM.2008.929554","volume":"9","author":"S Koziel","year":"2008","unstructured":"Koziel, S., Cheng, Q. S. & Bandler, J. W. Space mapping. IEEE Microw. Mag. 9, 105\u2013122 (2008).","journal-title":"IEEE Microw. Mag."},{"key":"761_CR28","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1109\/22.898979","volume":"48","author":"MH Bakr","year":"2000","unstructured":"Bakr, M. H., Bandler, J. W., Ismail, M. A., Rayas-S\u00e1nchez, J. E. & Zhang, Q.-J. Neural space-mapping optimization for em-based design. IEEE Trans. Microw. Theory Tech. 48, 2307\u20132315 (2000).","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"761_CR29","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1109\/LMWC.2019.2927113","volume":"29","author":"F Feng","year":"2019","unstructured":"Feng, F. et al. Coarse-and fine-mesh space mapping for em optimization incorporating mesh deformation. IEEE Microw. Wirel. Compon. Lett. 29, 510\u2013512 (2019).","journal-title":"IEEE Microw. Wirel. Compon. Lett."},{"key":"761_CR30","doi-asserted-by":"publisher","first-page":"7052","DOI":"10.1073\/pnas.1922210117","volume":"117","author":"L Lu","year":"2020","unstructured":"Lu, L. et al. Extraction of mechanical properties of materials through deep learning from instrumented indentation. Proc. Natl Acad. Sci. USA 117, 7052\u20137062 (2020).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"761_CR31","doi-asserted-by":"publisher","first-page":"3721","DOI":"10.1109\/TMTT.2006.882894","volume":"54","author":"S Koziel","year":"2006","unstructured":"Koziel, S., Bandler, J. W. & Madsen, K. A space-mapping framework for engineering optimization-theory and implementation. IEEE Trans. Microw. Theory Tech. 54, 3721\u20133730 (2006).","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"761_CR32","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1090\/cams\/10","volume":"2","author":"M Levine","year":"2022","unstructured":"Levine, M. & Stuart, A. A framework for machine learning of model error in dynamical systems. Commun. Am. Math. Soc. 2, 283\u2013344 (2022).","journal-title":"Commun. Am. Math. Soc."},{"key":"761_CR33","unstructured":"Ren, P. et al. Physics-informed deep super-resolution for spatiotemporal data. Preprint at https:\/\/arxiv.org\/abs\/2208.01462 (2022)."},{"key":"761_CR34","doi-asserted-by":"publisher","first-page":"035114","DOI":"10.1063\/5.0082562","volume":"34","author":"C Drygala","year":"2022","unstructured":"Drygala, C., Winhart, B., di Mare, F. & Gottschalk, H. Generative modeling of turbulence. Phys. Fluids 34, 035114 (2022).","journal-title":"Phys. Fluids"},{"key":"761_CR35","doi-asserted-by":"crossref","unstructured":"Geneva, N. & Zabaras, N. Multi-fidelity generative deep learning turbulent flows. Found. Data Sci. 2, 391\u2013428 (2020).","DOI":"10.3934\/fods.2020019"},{"key":"761_CR36","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1017\/S0962492922000058","volume":"31","author":"JS Hesthaven","year":"2022","unstructured":"Hesthaven, J. S., Pagliantini, C. & Rozza, G. Reduced basis methods for time-dependent problems. Acta Numerica 31, 265\u2013345 (2022).","journal-title":"Acta Numerica"},{"key":"761_CR37","doi-asserted-by":"crossref","unstructured":"Weinberg, S. The Quantum Theory of Fields Vol. 2 (Cambridge Univ. Press, 1995).","DOI":"10.1017\/CBO9781139644167"},{"key":"761_CR38","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.jcp.2017.02.002","volume":"336","author":"TY Hou","year":"2017","unstructured":"Hou, T. Y., Hwang, F.-N., Liu, P. & Yao, C.-C. An iteratively adaptive multi-scale finite element method for elliptic PDEs with rough coefficients. J. Comput. Phys. 336, 375\u2013400 (2017).","journal-title":"J. Comput. Phys."},{"key":"761_CR39","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1038\/s41566-018-0246-9","volume":"12","author":"S Molesky","year":"2018","unstructured":"Molesky, S. et al. Inverse design in nanophotonics. Nat. Photon. 12, 659\u2013670 (2018).","journal-title":"Nat. Photon."},{"key":"761_CR40","doi-asserted-by":"publisher","first-page":"30202","DOI":"10.1364\/OE.26.030202","volume":"26","author":"C P\u00e9rez-Arancibia","year":"2018","unstructured":"P\u00e9rez-Arancibia, C., Pestourie, R. & Johnson, S. G. Sideways adiabaticity: beyond ray optics for slowly varying metasurfaces. Optics Expr. 26, 30202\u201330230 (2018).","journal-title":"Optics Expr."},{"key":"761_CR41","unstructured":"Jin, J.-M. The Finite Element Method in Electromagnetics (John Wiley & Sons, 2015)."},{"key":"761_CR42","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1137\/S1052623499362822","volume":"12","author":"K Svanberg","year":"2002","unstructured":"Svanberg, K. A class of globally convergent optimization methods based on conservative convex separable approximations. SIAM J. Optim.12, 555\u2013573 (2002).","journal-title":"SIAM J. Optim."},{"key":"761_CR43","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/BF01589116","volume":"45","author":"DC Liu","year":"1989","unstructured":"Liu, D. C. & Nocedal, J. On the limited memory BFGS method for large scale optimization. Math. Program. 45, 503\u2013528 (1989).","journal-title":"Math. Program."},{"key":"761_CR44","doi-asserted-by":"crossref","unstructured":"Huber, P. J. in Breakthroughs in Statistics: Methodology and Distribution (eds Kotz, S. & Johnson, N. L.) 492\u2013518 (Springer, 1992).","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"761_CR45","unstructured":"Lakshminarayanan, B., Pritzel, A. & Blundell, C. Simple and scalable predictive uncertainty estimation using deep ensembles. In Proc. 31st International Conference on Neural Information Processing Systems (eds von Luxburg, U. et al.) 6405\u20136416 (Curran Associates Inc., 2017)."},{"key":"761_CR46","unstructured":"Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, 2016)."},{"key":"761_CR47","unstructured":"Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https:\/\/arxiv.org\/abs\/1412.6980 (2014)."},{"key":"761_CR48","doi-asserted-by":"crossref","unstructured":"Innes, M. Flux: elegant machine learning with Julia. J. Open Source Softw. 3, 602 (2018).","DOI":"10.21105\/joss.00602"},{"key":"761_CR49","unstructured":"Innes, M. Don\u2019t unroll adjoint: differentiating SSA-form programs. Preprint at https:\/\/arxiv.org\/abs\/1810.07951 (2018)."},{"key":"761_CR50","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1006\/jcph.2001.6765","volume":"170","author":"NJ Champagne II","year":"2001","unstructured":"Champagne II, N. J., Berryman, J. G. & Buettner, H. M. FDFD: a 3D finite-difference frequency-domain code for electromagnetic induction tomography. J. Comput. Phys. 170, 830\u2013848 (2001).","journal-title":"J. Comput. Phys."},{"key":"761_CR51","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1109\/8.477075","volume":"43","author":"ZS Sacks","year":"1995","unstructured":"Sacks, Z. S., Kingsland, D. M., Lee, R. & Lee, J.-F. A perfectly matched anisotropic absorber for use as an absorbing boundary condition. IEEE Trans. Antennas Propag. 43, 1460\u20131463 (1995).","journal-title":"IEEE Trans. Antennas Propag."},{"key":"761_CR52","doi-asserted-by":"publisher","unstructured":"Pestourie, R. & Das, P. payel79\/peds: publish. Zenodo https:\/\/doi.org\/10.5281\/zenodo.8342595 (2023).","DOI":"10.5281\/zenodo.8342595"},{"key":"761_CR53","doi-asserted-by":"publisher","unstructured":"Pestourie, R. & Das, P. PEDS datasets and figure data. Zenodo https:\/\/doi.org\/10.5281\/zenodo.10011958 (2023).","DOI":"10.5281\/zenodo.10011958"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00761-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00761-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00761-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:08:38Z","timestamp":1702930118000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00761-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":53,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["761"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00761-y","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,4]]},"assertion":[{"value":"12 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}