{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:31:33Z","timestamp":1786980693920,"version":"build-2736575974"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T00:00:00Z","timestamp":1739232000000},"content-version":"vor","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100005376","name":"American Mathematical Society","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005376","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Adv Comput Math"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Recently, deep neural networks (DNNs) have become powerful tools for solving inverse scattering problems. However, the approximation and generalization rates of DNNs for solving these problems remain largely under-explored. In this work, we introduce two types of combined DNNs (uncompressed and compressed) to reconstruct two function-valued coefficients in the Helmholtz equation for inverse scattering problems from the scattering data at two different frequencies. An analysis of the approximation and generalization capabilities of the proposed neural networks for simulating the regularized pseudo-inverses of the linearized forward operators in direct scattering problems is provided. The results show that, with sufficient training data and parameters, the proposed neural networks can effectively approximate the inverse process with desirable generalization. Preliminary numerical results show the feasibility of the proposed neural networks for recovering two types of isotropic inhomogeneous media. Furthermore, the trained neural network is capable of reconstructing the isotropic representation of certain types of anisotropic media.<\/jats:p>","DOI":"10.1007\/s10444-025-10225-z","type":"journal-article","created":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T05:22:13Z","timestamp":1739251333000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["On the recovery of two function-valued coefficients in the Helmholtz equation for inverse scattering problems via neural networks"],"prefix":"10.1007","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1671-4721","authenticated-orcid":false,"given":"Zehui","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,11]]},"reference":[{"issue":"1","key":"10225_CR1","doi-asserted-by":"publisher","first-page":"265","DOI":"10.4007\/annals.2006.163.265","volume":"163","author":"K Astala","year":"2006","unstructured":"Astala, K., P\u00e4iv\u00e4rinta, L.: Calder\u00f3n\u2019s inverse conductivity problem in the plane. Ann. of Math. (2) 163(1), 265\u2013299 (2006)","journal-title":"Ann. of Math. (2)"},{"issue":"1\u20133","key":"10225_CR2","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1081\/PDE-200044485","volume":"30","author":"K Astala","year":"2005","unstructured":"Astala, K., P\u00e4iv\u00e4rinta, L., Lassas, M.: Calder\u00f3n\u2019s inverse problem for anisotropic conductivity in the plane. Comm. Partial Differential Equations 30(1\u20133), 207\u2013224 (2005)","journal-title":"Comm. Partial Differential Equations"},{"issue":"1","key":"10225_CR3","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1515\/jiip.2008.002","volume":"16","author":"AL Bukhgeim","year":"2008","unstructured":"Bukhgeim, A.L.: Recovering a potential from Cauchy data in the two-dimensional case. J. Inverse Ill-Posed Probl. 16(1), 19\u201333 (2008)","journal-title":"J. Inverse Ill-Posed Probl."},{"key":"10225_CR4","volume-title":"Qualitative methods in inverse scattering theory","author":"F Cakoni","year":"2005","unstructured":"Cakoni, F., Colton, D.: Qualitative methods in inverse scattering theory. The MIT Press, Cambridge, Massachusetts, London, England (2005)"},{"issue":"4","key":"10225_CR5","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1137\/080734339","volume":"7","author":"E Cand\u00e8s","year":"2009","unstructured":"Cand\u00e8s, E., Demanet, L., Ying, L.: A fast butterfly algorithm for the computation of Fourier integral operators. Multiscale Model. Sim. 7(4), 1727\u20131750 (2009)","journal-title":"Multiscale Model. Sim."},{"key":"10225_CR6","doi-asserted-by":"crossref","unstructured":"Colton, D., Kress, R.: Inverse acoustic and electromagnetic scattering theory, 4th edn. Applied Mathematical Sciences, vol. 93. Springer, Cham (2019)","DOI":"10.1007\/978-3-030-30351-8"},{"key":"10225_CR7","doi-asserted-by":"crossref","unstructured":"Costabel, M.: On the spectrum of volume integral operators in acoustic scattering. In: Constanda, C., Kirsch, A. (eds.) Integral Methods in Science and Engineering, pp. 119\u2013127 (2015)","DOI":"10.1007\/978-3-319-16727-5_11"},{"key":"10225_CR8","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1017\/S0962492921000052","volume":"30","author":"R DeVore","year":"2021","unstructured":"DeVore, R., Hanin, B., Petrova, G.: Neural network approximation. Acta Numer. 30, 327\u2013444 (2021)","journal-title":"Acta Numer."},{"key":"10225_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-1740-8","volume-title":"Regularization of inverse problems","author":"HW Engl","year":"1996","unstructured":"Engl, H.W., Hanke, M., Neubauer, A.: Regularization of inverse problems. Kluwer, Dordrecht (1996)"},{"key":"10225_CR10","doi-asserted-by":"crossref","unstructured":"Fan, Y., Feliu-Fab\u00e0, J., Lin, L., Ying, L., Zepeda-N\u00fa\u00f1ez, L.: A multiscale neural network based on hierarchical nested bases. Res. Math. Sci. 6(21) (2019)","DOI":"10.1007\/s40687-019-0183-3"},{"key":"10225_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4948-7","volume-title":"A mathematical introduction to compressive sensing","author":"S Foucart","year":"2013","unstructured":"Foucart, S., Rauhut, H.: A mathematical introduction to compressive sensing. Applied and Numerical Harmonic Analysis, Birkh\u00e4user (2013)"},{"issue":"2","key":"10225_CR12","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1088\/0266-5611\/12\/2\/003","volume":"12","author":"F Gylys-Colwell","year":"1996","unstructured":"Gylys-Colwell, F.: An inverse problem for the Helmholtz equation. Inverse Prob. 12(2), 139\u2013156 (1996)","journal-title":"Inverse Prob."},{"key":"10225_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10225_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference for Learning Representations, San Diego (2015)"},{"issue":"6","key":"10225_CR15","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1002\/cpa.3160400605","volume":"40","author":"RV Kohn","year":"1987","unstructured":"Kohn, R.V., Vogelius, M.: Relaxation of a variational method for impedance computed tomography. Comm. Pure Appl. Math. 40(6), 745\u2013777 (1987)","journal-title":"Comm. Pure Appl. Math."},{"issue":"4","key":"10225_CR16","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1137\/20M1383276","volume":"20","author":"M Li","year":"2022","unstructured":"Li, M., Demanet, L., Zepeda-N\u00fa\u00f1ez, L.: Wide-band butterfly network: stable and efficient inversion via multi-frequency neural networks. Multiscale Model. Sim. 20(4), 1191\u20131227 (2022)","journal-title":"Multiscale Model. Sim."},{"issue":"2","key":"10225_CR17","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1137\/15M1007173","volume":"13","author":"Y Li","year":"2015","unstructured":"Li, Y., Yang, H., Martin, E.R., Ho, K.L., Ying, L.: Butterfly factorization. Multiscale Mod. Sim. 13(2), 714\u2013732 (2015)","journal-title":"Multiscale Mod. Sim."},{"key":"10225_CR18","doi-asserted-by":"crossref","unstructured":"Maurer, A.: A vector-contraction inequality for Rademacher complexities. In: Ortner, R., Simon, H.U., Zilles, S. (eds.) Algorithmic Learning Theory, pp. 3\u201317. Springer International Publishing (2016)","DOI":"10.1007\/978-3-319-46379-7_1"},{"issue":"3","key":"10225_CR19","doi-asserted-by":"publisher","first-page":"2267","DOI":"10.1093\/imaiai\/iaad023","volume":"12","author":"E Schnoor","year":"2023","unstructured":"Schnoor, E., Behboodi, A., Rauhut, H.: Generalization error bounds for iterative recovery algorithms unfolded as neural networks. Inf. Inference: A J. IMA 12(3), 2267\u20132299 (2023)","journal-title":"Inf. Inference: A J. IMA"},{"key":"10225_CR20","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019","volume-title":"Understanding machine learning: from theory to algorithms","author":"S Shalev-Shwartz","year":"2014","unstructured":"Shalev-Shwartz, S., Ben-David, S.: Understanding machine learning: from theory to algorithms. Cambridge University Press, USA (2014)"},{"issue":"2","key":"10225_CR21","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1002\/cpa.3160430203","volume":"43","author":"J Sylvester","year":"1990","unstructured":"Sylvester, J.: An anisotropic inverse boundary value problem. Comm. Pure Appl. Math. 43(2), 201\u2013232 (1990)","journal-title":"Comm. Pure Appl. Math."},{"key":"10225_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2024.116050","volume":"451","author":"B Zhang","year":"2024","unstructured":"Zhang, B., Zepeda-Nunez, L., Li, Q.: Solving the wide-band inverse scattering problem via equivariant neural networks. J. Comput. Appl. Math. 451, 116050 (2024)","journal-title":"J. Comput. Appl. Math."}],"container-title":["Advances in Computational Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10444-025-10225-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10444-025-10225-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10444-025-10225-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T16:52:27Z","timestamp":1740415947000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10444-025-10225-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10225"],"URL":"https:\/\/doi.org\/10.1007\/s10444-025-10225-z","relation":{},"ISSN":["1019-7168","1572-9044"],"issn-type":[{"value":"1019-7168","type":"print"},{"value":"1572-9044","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"28 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author declares no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"12"}}