{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T05:45:31Z","timestamp":1792129531365,"version":"4.4.0"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,9,8]],"date-time":"2027-09-08T00:00:00Z","timestamp":1820361600000},"content-version":"am","delay-in-days":281,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1R01HL177814"],"award-info":[{"award-number":["1R01HL177814"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-23-1-2071"],"award-info":[{"award-number":["N00014-23-1-2071"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC-2047127"],"award-info":[{"award-number":["OAC-2047127"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational Physics"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.jcp.2026.115359","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T15:59:26Z","timestamp":1788537566000},"page":"115359","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["D-Flow SGLD: Source-space posterior sampling for scientific inverse problems with flow matching"],"prefix":"10.1016","volume":"567","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1284-6368","authenticated-orcid":false,"given":"Meet Hemant","family":"Parikh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9030-1733","authenticated-orcid":false,"given":"Jian-Xun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jcp.2026.115359_bib0001","series-title":"Large-Scale Inverse Problems and Quantification Of Uncertainty","volume":"712","author":"Biegler","year":"2010"},{"issue":"1","key":"10.1016\/j.jcp.2026.115359_bib0002","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-024-54712-1","article-title":"Conditional neural field latent diffusion model for generating spatiotemporal turbulence","volume":"15","author":"Du","year":"2024","journal-title":"Nat. Commun."},{"issue":"3","key":"10.1016\/j.jcp.2026.115359_bib0003","doi-asserted-by":"crossref","DOI":"10.1063\/5.0082562","article-title":"Generative modeling of turbulence","volume":"34","author":"Drygala","year":"2022","journal-title":"Phys. Fluids"},{"key":"10.1016\/j.jcp.2026.115359_bib0004","doi-asserted-by":"crossref","DOI":"10.1017\/jfm.2026.11193","article-title":"Conditional flow matching for generative modelling of near-wall turbulence with quantified uncertainty","volume":"1029","author":"Parikh","year":"2026","journal-title":"J. Fluid Mech."},{"key":"10.1016\/j.jcp.2026.115359_bib0005","unstructured":"H. Chung, J. Kim, M.T. McCann, M.L. Klasky, J.C. Ye, Diffusion posterior sampling for general noisy inverse problems (2022). arXiv preprint arXiv: 2209.14687."},{"key":"10.1016\/j.jcp.2026.115359_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2025.118431","article-title":"Unifying and extending diffusion models through pdes for solving inverse problems","volume":"448","author":"Dasgupta","year":"2026","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.jcp.2026.115359_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2023.111972","article-title":"A physics-informed diffusion model for high-fidelity flow field reconstruction","volume":"478","author":"Shu","year":"2023","journal-title":"J. Comput. Phys."},{"issue":"2","key":"10.1016\/j.jcp.2026.115359_bib0008","doi-asserted-by":"crossref","first-page":"C399","DOI":"10.1137\/24M1636071","article-title":"Cocogen: physically consistent and conditioned score-based generative models for forward and inverse problems","volume":"47","author":"Jacobsen","year":"2025","journal-title":"SIAM J. Sci. Comput."},{"key":"10.1016\/j.jcp.2026.115359_bib0009","doi-asserted-by":"crossref","unstructured":"S. Shan, M. Zhu, Y. Lin, L. Lu, Red-diffeq: regularization by denoising diffusion models for solving inverse pde problems with application to full waveform inversion (2025). arXiv preprint arXiv: 2509.21659.","DOI":"10.1038\/s42005-026-02677-6"},{"key":"10.1016\/j.jcp.2026.115359_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2025.114005","article-title":"Data-driven stochastic closure modeling via conditional diffusion model and neural operator","volume":"534","author":"Dong","year":"2025","journal-title":"J. Comput. Phys."},{"issue":"5","key":"10.1016\/j.jcp.2026.115359_bib0011","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevFluids.10.054901","article-title":"Confild-inlet: synthetic turbulence inflow using generative latent diffusion models with neural fields","volume":"10","author":"Liu","year":"2025","journal-title":"Phys. Rev. Fluids"},{"key":"10.1016\/j.jcp.2026.115359_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2024.117023","article-title":"Bayesian conditional diffusion models for versatile spatiotemporal turbulence generation","volume":"427","author":"Gao","year":"2024","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.jcp.2026.115359_bib0013","unstructured":"M. Mardani, J. Song, J. Kautz, A. Vahdat, A variational perspective on solving inverse problems with diffusion models, 2023, arXiv preprint arXiv: 2305.04391."},{"key":"10.1016\/j.jcp.2026.115359_bib0014","series-title":"Advances in Neural Information Processing Systems","first-page":"87647","article-title":"Learning diffusion priors from observations by expectation maximization","volume":"37","author":"Rozet","year":"2024"},{"key":"10.1016\/j.jcp.2026.115359_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2024.117478","article-title":"Neural differentiable modeling with diffusion-based super-resolution for two-dimensional spatiotemporal turbulence","volume":"433","author":"Fan","year":"2025","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.jcp.2026.115359_bib0016","doi-asserted-by":"crossref","unstructured":"P. Du, M. Xu, X. Zhu, J.-X. Wang, Hug-vas: a hierarchical nurbs-based generative model for aortic geometry synthesis and controllable editing(2025). arXiv preprint arXiv: 2507.11474.","DOI":"10.2139\/ssrn.6444278"},{"key":"10.1016\/j.jcp.2026.115359_bib0017","unstructured":"Y. Lipman, R.T. Chen, H. Ben-Hamu, M. Nickel, M. Le, Flow matching for generative modeling, 2022, arXiv preprint arXiv: 2210.02747."},{"key":"10.1016\/j.jcp.2026.115359_bib0018","unstructured":"A. Tong, K. Fatras, N. Malkin, G. Huguet, Y. Zhang, J. Rector-Brooks, G. Wolf, Y. Bengio, Improving and generalizing flow-based generative models with minibatch optimal transport, (2023). arXiv: 2302.00482."},{"key":"10.1016\/j.jcp.2026.115359_bib0019","unstructured":"Z. Li, A. Zhou, A.B. Farimani, Generative latent neural pde solver using flow matching, (2025). arXiv: 2503.22600."},{"key":"10.1016\/j.jcp.2026.115359_bib0020","unstructured":"G. Baldan, Q. Liu, A. Guardone, N. Thuerey, Flow matching meets pdes: a unified framework for physics-constrained generation, (2025). arXiv: 2506.08604."},{"key":"10.1016\/j.jcp.2026.115359_bib0021","doi-asserted-by":"crossref","unstructured":"U. Utkarsh, P. Cai, A. Edelman, R. Gomez-Bombarelli, C.V. Rackauckas, Physics-constrained flow matching: sampling generative models with hard constraints (2025). arXiv preprint arXiv: 2506.04171.","DOI":"10.52202\/085713-5354"},{"key":"10.1016\/j.jcp.2026.115359_bib0022","unstructured":"S. Wang, Z. Wu, D. van Dijk, L. Lu, Geofunflow: geometric function flow matching for inverse operator learning over complex geometries, 2025, arXiv preprint arXiv: 2509.24117."},{"key":"10.1016\/j.jcp.2026.115359_bib0023","unstructured":"A. Pokle, M.J. Muckley, R.T. Chen, B. Karrer, Training-free linear image inverses via flows, 2023, arXiv preprint arXiv: 2310.04432."},{"key":"10.1016\/j.jcp.2026.115359_bib0024","doi-asserted-by":"crossref","unstructured":"J. Kim, B.S. Kim, J.C. Ye, Flowdps: flow-driven posterior sampling for inverse problems (2025). arXiv preprint arXiv: 2503.08136.","DOI":"10.1109\/ICCV51701.2025.01146"},{"key":"10.1016\/j.jcp.2026.115359_bib0025","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"20895","article-title":"Improving diffusion inverse problem solving with decoupled noise annealing","author":"Zhang","year":"2025"},{"key":"10.1016\/j.jcp.2026.115359_bib0026","unstructured":"S. Martin, A. Gagneux, P. Hagemann, G. Steidl, PnP-Flow: plug-and-play image restoration with flow matching (2024). arXiv preprint arXiv: 2410.02423."},{"key":"10.1016\/j.jcp.2026.115359_bib0027","unstructured":"F.E. Kelvinius, Z. Zhao, F. Lindsten, Solving linear-gaussian bayesian inverse problems with decoupled diffusion sequential monte carlo (2025). arXiv preprint arXiv: 2502.06379."},{"key":"10.1016\/j.jcp.2026.115359_bib0028","series-title":"Advances in Neural Information Processing Systems","first-page":"117881","article-title":"Dmplug: a plug-in method for solving inverse problems with diffusion models","volume":"37","author":"Wang","year":"2024"},{"key":"10.1016\/j.jcp.2026.115359_bib0029","unstructured":"H. Ben-Hamu, O. Puny, I. Gat, B. Karrer, U. Singer, Y. Lipman, D-flow: differentiating through flows for controlled generation, 2024, arXiv preprint arXiv: 2402.14017."},{"key":"10.1016\/j.jcp.2026.115359_bib0030","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"28327","article-title":"Consistency posterior sampling for diverse image synthesis","author":"Purohit","year":"2025"},{"key":"10.1016\/j.jcp.2026.115359_bib0031","unstructured":"Z. Wang, A. Harting, M. Barreau, M.M. Zavlanos, K.H. Johansson, Source-guided flow matching, 2025, arXiv preprint arXiv: 2508.14807."},{"key":"10.1016\/j.jcp.2026.115359_bib0032","unstructured":"A. Kalaivanan, Z. Zhao, J. Sj\u00f6lund, F. Lindsten, Ess-flow: Training-free guidance of flow-based models as inference in source space, 2025, arXiv preprint arXiv: 2510.05849."},{"key":"10.1016\/j.jcp.2026.115359_bib0033","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Preconditioned stochastic gradient langevin dynamics for deep neural networks","volume":"30","author":"Li","year":"2016"},{"key":"10.1016\/j.jcp.2026.115359_bib0034","unstructured":"Y. Song, J. Sohl-Dickstein, D.P. Kingma, A. Kumar, S. Ermon, B. Poole, Score-based generative modeling through stochastic differential equations, 2020, arXiv preprint arXiv: 2011.13456."},{"key":"10.1016\/j.jcp.2026.115359_bib0035","doi-asserted-by":"crossref","unstructured":"H. Chung, J. Kim, J.C. Ye, Diffusion models for inverse problems, 2025, arXiv: 2508.01975.","DOI":"10.1007\/978-3-031-80965-1_7"},{"key":"10.1016\/j.jcp.2026.115359_bib0036","unstructured":"G. Dresdner, D. Kochkov, P. Norgaard, L. Zepeda-N\u00fa\u00f1ez, J.A. Smith, M.P. Brenner, S. Hoyer, Learning to correct spectral methods for simulating turbulent flows, 2022, 10.48550\/ARXIV.2207.00556."},{"key":"10.1016\/j.jcp.2026.115359_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2025.118455","article-title":"Diff-FlowFSI: a GPU-optimized differentiable CFD platform for high-fidelity turbulence and FSI simulations","volume":"448","author":"Fan","year":"2026","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.jcp.2026.115359_bib0038","series-title":"International Conference on Medical Image Computing and Computer-assisted Intervention","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.jcp.2026.115359_bib0039","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Film: visual reasoning with a general conditioning layer","volume":"32","author":"Perez","year":"2018"},{"issue":"78","key":"10.1016\/j.jcp.2026.115359_bib0040","first-page":"1","article-title":"POT: python optimal transport","volume":"22","author":"Flamary","year":"2021","journal-title":"J. Mach. Learn. Res."}],"container-title":["Journal of Computational Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0021999126007084?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0021999126007084?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T04:58:58Z","timestamp":1792126738000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0021999126007084"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":40,"alternative-id":["S0021999126007084"],"URL":"https:\/\/doi.org\/10.1016\/j.jcp.2026.115359","relation":{},"ISSN":["0021-9991"],"issn-type":[{"value":"0021-9991","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"D-Flow SGLD: Source-space posterior sampling for scientific inverse problems with flow matching","name":"articletitle","label":"Article Title"},{"value":"Journal of Computational Physics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jcp.2026.115359","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115359"}}