{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:04:22Z","timestamp":1763139862019,"version":"3.45.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U22A2068"],"award-info":[{"award-number":["U22A2068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["202042008"],"award-info":[{"award-number":["202042008"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62422608"],"award-info":[{"award-number":["62422608"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"the China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2024M763101, GZB20240694"],"award-info":[{"award-number":["2024M763101, GZB20240694"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>For partial differential equations (PDE), neural operators can learn the mapping of input and output functions in infinite dimensional Spaces by introducing kernel functions into linear transformations. latent Spectral Model (LSM) is an advanced neural operator, that does not solve PDE directly in coordinate space, but first simplifies complex high-dimensional data into a compact Latent space through hierarchical projection networks, then approximates the solution mapping through neural spectral blocks. However, LSM does not deeply extract the Latent features of PDE, nor does it fuse the different coordinate space features of PDE. To extract more effective features of PDE to improve the solution accuracy further, we propose MU-LSM: Latent spectral model based on multi-scale fusion and UNet. Unlike LSM, MU-LSM introduces UNet and multi-scale fusion in PDE solution procedure. First, when PDE is converted from coordinate space to latent space, MU-LSM extracts the smooth global features and sharp local features of PDE by UNet. Then, MU-LSM concatenates the latent features extracted by UNet with latent tokens. Finally, after the processing of all neural spectrum blocks, MU-LSM fuses the new coordinate space features and the original coordinate space features by jumping connections. The experimental results show that on three solid PDE and four fluid PDE, compared with 15 advanced PDE solvers such as DeepONet, FNO, and LSM, MU-LSM has the highest overall accuracy, with an average accuracy improvement of 7.7%.<\/jats:p>","DOI":"10.1007\/s40747-025-01994-7","type":"journal-article","created":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T03:49:21Z","timestamp":1761968961000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MU-LSM: latent spectral model based on multi-scale fusion and UNet"],"prefix":"10.1007","volume":"11","author":[{"given":"Jingjian","family":"Chen","sequence":"first","affiliation":[]},{"given":"Jie","family":"Nie","sequence":"additional","affiliation":[]},{"given":"Ning","family":"Song","sequence":"additional","affiliation":[]},{"given":"Min","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Zhiqiang","family":"Wei","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"1994_CR1","unstructured":"Ashiqur\u00a0Rahman M, Ross ZE, Azizzadenesheli K (2022) U-no: U-shaped neural operators. arXiv e-prints pp. arXiv\u20132204"},{"key":"1994_CR2","doi-asserted-by":"crossref","unstructured":"Bhattacharya K, Hosseini B, Kovachki NB, Stuart AM (2020) Model reduction and neural networks for parametric pdes","DOI":"10.5802\/smai-jcm.74"},{"key":"1994_CR3","first-page":"24924","volume":"34","author":"S Cao","year":"2021","unstructured":"Cao S (2021) Choose a transformer: Fourier or galerkin. Adv Neural Inf Process Syst 34:24924\u201324940","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"1994_CR4","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1080\/19942060.2020.1720820","volume":"14","author":"XH Chen","year":"2020","unstructured":"Chen XH, Liu J, Pang YF, Chen J, Gong CY (2020) Developing a new mesh quality evaluation method based on convolutional neural network. Engineering Applications of Computational Fluid Mechanics 14(1):391\u2013400","journal-title":"Engineering Applications of Computational Fluid Mechanics"},{"key":"1994_CR5","doi-asserted-by":"crossref","unstructured":"Fanaskov V, Oseledets IV (2023) Spectral neural operators. In: Doklady Mathematics, vol. 108, pp. S226\u2013S232. Springer","DOI":"10.1134\/S1064562423701107"},{"key":"1994_CR6","first-page":"24048","volume":"34","author":"G Gupta","year":"2021","unstructured":"Gupta G, Xiao X, Bogdan P (2021) Multiwavelet-based operator learning for differential equations. Adv Neural Inf Process Syst 34:24048\u201324062","journal-title":"Adv Neural Inf Process Syst"},{"key":"1994_CR7","doi-asserted-by":"crossref","unstructured":"Han J, Arnulf J, Weinan E (2018) Solving high-dimensional partial differential equations using deep learning. Proceedings of the National Academy of Sciences pp. 201718942","DOI":"10.1073\/pnas.1718942115"},{"key":"1994_CR8","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"1994_CR9","unstructured":"Le C (2022) Ai for science: Innovate the future together - 2022 zhongguancun forum series activities \"science intelligence summit\" held. Zhongguancun (9), 2"},{"issue":"388","key":"1994_CR10","first-page":"1","volume":"24","author":"Z Li","year":"2023","unstructured":"Li Z, Huang DZ, Liu B, Anandkumar A (2023) Fourier neural operator with learned deformations for pdes on general geometries. J Mach Learn Res 24(388):1\u201326","journal-title":"J Mach Learn Res"},{"key":"1994_CR11","unstructured":"Li Z, Kovachki N, Azizzadenesheli K, Liu B, Anandkumar A (2020) Neural operator: Graph kernel network for partial differential equations"},{"key":"1994_CR12","unstructured":"Li Z, Kovachki NB, Azizzadenesheli K, Liu B, Bhattacharya K, Stuart A, Anandkumar A (2021) Fourier neural operator for parametric partial differential equations. In: International Conference on Learning Representations"},{"key":"1994_CR13","unstructured":"Liu X, Xu B, Zhang L (2022) Ht-net: Hierarchical transformer based operator learning model for multiscale pdes"},{"key":"1994_CR14","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1994_CR15","unstructured":"Lu, L., Jin, P., Karniadakis, G.E.: Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators (2019)"},{"key":"1994_CR16","unstructured":"Lu L, Jin P, Karniadakis GE (2019) Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators"},{"key":"1994_CR17","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.probengmech.2019.05.001","volume":"57","author":"A Mohammad","year":"2019","unstructured":"Mohammad A (2019) Nabian, Hadi, Meidani: A deep learning solution approach for high-dimensional random differential equations - sciencedirect. Probab Eng Mech 57:14\u201325","journal-title":"Probab Eng Mech"},{"key":"1994_CR18","doi-asserted-by":"crossref","unstructured":"Nelsen NH, Stuart AM (2020) The random feature model for input-output maps between banach spaces","DOI":"10.1137\/20M133957X"},{"key":"1994_CR19","doi-asserted-by":"crossref","unstructured":"Patel RG, Trask NA, Wood MA, Cyr EC (2021) A physics-informed operator regression framework for extracting data-driven continuum models. Computer Methods in Applied Mechanics and Engineering 373","DOI":"10.1016\/j.cma.2020.113500"},{"key":"1994_CR20","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.jcp.2017.11.039","volume":"357","author":"M Raissi","year":"2018","unstructured":"Raissi M, Karniadakis GE (2018) Hidden physics models: machine learning of nonlinear partial differential equations. J Comput Phys 357:125\u2013141","journal-title":"J Comput Phys"},{"issue":"1","key":"1994_CR21","doi-asserted-by":"publisher","first-page":"A172","DOI":"10.1137\/17M1120762","volume":"40","author":"M Raissi","year":"2017","unstructured":"Raissi M, Perdikaris P, Karniadakis GE (2017) Numerical gaussian processes for time-dependent and non-linear partial differential equations. SIAM J Sci Comput 40(1):A172\u2013A198","journal-title":"SIAM J Sci Comput"},{"key":"1994_CR22","unstructured":"Raissi M, Perdikaris P, Karniadakis GE (2017) Physics informed deep learning (part ii): Data-driven discovery of nonlinear partial differential equations"},{"key":"1994_CR23","unstructured":"Raissi M, Perdikaris P, Karniadakis GE (2017) Physics informed deep learning (part ii): Data-driven discovery of nonlinear partial differential equations"},{"key":"1994_CR24","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pp. 234\u2013241. Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1994_CR25","unstructured":"Science: Science publishes 125 cutting-edge questions in science. Field of Vision (20), 2 (2016)"},{"key":"1994_CR26","unstructured":"Tran A, Mathews A, Xie L, Ong CS (2021) Factorized fourier neural operators. arXiv preprint arXiv:2111.13802"},{"key":"1994_CR27","doi-asserted-by":"crossref","unstructured":"Wang N, Chang H, Zhang D (2021) Deep?learning?based inverse modeling approaches: A subsurface flow example. John Wiley and Sons Ltd. (2)","DOI":"10.1029\/2020JB020549"},{"key":"1994_CR28","doi-asserted-by":"crossref","unstructured":"Wang R, Kashinath K, Mustafa M, Albert A, Yu R (2020) Towards physics-informed deep learning for turbulent flow prediction. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 1457\u20131466","DOI":"10.1145\/3394486.3403198"},{"key":"1994_CR29","doi-asserted-by":"crossref","unstructured":"Weinan E, Han J, Jentzen A (2017) Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations. arXiv e-prints","DOI":"10.1007\/s40304-017-0117-6"},{"key":"1994_CR30","doi-asserted-by":"crossref","unstructured":"Wen G, Li Z, Azizzadenesheli K, Anandkumar A, Benson SM (2022) U-fno-an enhanced fourier neural operator-based deep-learning model for multiphase flow. Advances in water resources (May), 163","DOI":"10.1016\/j.advwatres.2022.104180"},{"key":"1994_CR31","unstructured":"Wu H, Hu T, Luo H, Wang J, Long M (2023) Solving high-dimensional pdes with latent spectral models. arXiv preprint arXiv:2301.12664"},{"key":"1994_CR32","doi-asserted-by":"crossref","unstructured":"Xiong W, Huang X, Zhang Z, Deng R, Sun P, Tian Y (2023) Koopman neural operator as a mesh-free solver of non-linear partial differential equations. arXiv preprint arXiv:2301.10022","DOI":"10.2139\/ssrn.4479919"},{"key":"1994_CR33","doi-asserted-by":"crossref","unstructured":"Xu H (2021) Dl-pde: Deep-learning based data-driven discovery of partial differential equations from discrete and noisy data. Communications in Computational Physics 29","DOI":"10.4208\/cicp.OA-2020-0142"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01994-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-01994-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01994-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:01:26Z","timestamp":1763139686000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-01994-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"references-count":33,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["1994"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-01994-7","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"12 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"490"}}