{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T13:52:04Z","timestamp":1775310724638,"version":"3.50.1"},"reference-count":106,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T00:00:00Z","timestamp":1696982400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T00:00:00Z","timestamp":1696982400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000105","name":"Office of Advanced Cyberinfrastructure","doi-asserted-by":"publisher","award":["2203821"],"award-info":[{"award-number":["2203821"]}],"id":[{"id":"10.13039\/100000105","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","award":["DE-SC0021515"],"award-info":[{"award-number":["DE-SC0021515"]}],"id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ML4Seismic Center"},{"DOI":"10.13039\/100008065","name":"Georgia Research Alliance","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Adv. Model. and Simul. in Eng. Sci."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Solving multiphysics-based inverse problems for geological carbon storage monitoring can be challenging when multimodal time-lapse data are expensive to collect and costly to simulate numerically. We overcome these challenges by combining computationally cheap learned surrogates with learned constraints. Not only does this combination lead to vastly improved inversions for the important fluid-flow property, permeability, it also provides a natural platform for inverting multimodal data including well measurements and active-source time-lapse seismic data. By adding a learned constraint, we arrive at a computationally feasible inversion approach that remains accurate. This is accomplished by including a trained deep neural network, known as a normalizing flow, which forces the model iterates to remain in-distribution, thereby safeguarding the accuracy of trained Fourier neural operators that act as surrogates for the computationally expensive multiphase flow simulations involving partial differential equation solves. By means of carefully selected experiments, centered around the problem of geological carbon storage, we demonstrate the efficacy of the proposed constrained optimization method on two different data modalities, namely time-lapse well and time-lapse seismic data. While permeability inversions from both these two modalities have their pluses and minuses, their joint inversion benefits from either, yielding valuable superior permeability inversions and CO<jats:sub>2<\/jats:sub> plume predictions near, and far away, from the monitoring wells.<\/jats:p>","DOI":"10.1186\/s40323-023-00252-0","type":"journal-article","created":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T15:02:20Z","timestamp":1697036540000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Solving multiphysics-based inverse problems with learned surrogates and constraints"],"prefix":"10.1186","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5024-8771","authenticated-orcid":false,"given":"Ziyi","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Orozco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Louboutin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix J.","family":"Herrmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,11]]},"reference":[{"issue":"4","key":"252_CR1","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6420\/abe10c","volume":"37","author":"A Alexanderian","year":"2021","unstructured":"Alexanderian A. Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review. Inverse Problems. 2021;37(4): 043001.","journal-title":"Inverse Problems"},{"key":"252_CR2","doi-asserted-by":"crossref","first-page":"5504","DOI":"10.1016\/j.egypro.2011.02.536","volume":"4","author":"H Alnes","year":"2011","unstructured":"Alnes H, Eiken O, Nooner S, Sasagawa G, Stenvold T, Zumberge M. Results from sleipner gravity monitoring: updated density and temperature distribution of the CO2 plume. Energy Procedia. 2011;4:5504\u201311.","journal-title":"Energy Procedia"},{"key":"252_CR3","unstructured":"Ardizzone L, Kruse J, Wirkert S, Rahner D, Pellegrini EW, Klessen RS, Maier-Hein L, Rother C, K\u00f6the U. Analyzing inverse problems with invertible neural networks; 2018. arXiv Preprint arXiv:1808.04730."},{"issue":"2","key":"252_CR4","doi-asserted-by":"crossref","first-page":"R41","DOI":"10.1088\/0266-5611\/15\/2\/022","volume":"15","author":"SR Arridge","year":"1999","unstructured":"Arridge SR. Optical tomography in medical imaging. Inverse problems. 1999;15(2):R41.","journal-title":"Inverse problems"},{"issue":"9\u201310","key":"252_CR5","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1016\/j.energy.2004.03.072","volume":"29","author":"R Arts","year":"2004","unstructured":"Arts R, Eiken O, Chadwick A, Peter Z, Van der Meer L, Zinszner B. Monitoring of CO2 injected at Sleipner using time-lapse seismic data. Energy. 2004;29(9\u201310):1383\u201392.","journal-title":"Energy."},{"issue":"8","key":"252_CR6","doi-asserted-by":"crossref","first-page":"5957","DOI":"10.1002\/2015WR016967","volume":"51","author":"MJ Asher","year":"2015","unstructured":"Asher MJ, Croke BFW, Jakeman AJ, Peeters LJM. A review of surrogate models and their application to groundwater modeling. Water Resour Res. 2015;51(8):5957\u201373.","journal-title":"Water Resour Res"},{"key":"252_CR7","unstructured":"Asim M, Daniels M, Leong O, Ahmed A, Hand P. Invertible generative models for inverse problems: mitigating representation error and dataset bias. In: International conference on machine learning; 2020. p. 399\u2013409. PMLR."},{"key":"252_CR8","volume-title":"Parameter estimation and inverse problems","author":"RC Aster","year":"2018","unstructured":"Aster RC, Borchers B, Thurber CH. Parameter estimation and inverse problems. Amsterdam: Elsevier; 2018."},{"key":"252_CR9","volume-title":"Quantitative seismic interpretation: applying rock physics tools to reduce interpretation risk","author":"P Avseth","year":"2010","unstructured":"Avseth P, Mukerji T, Mavko G. Quantitative seismic interpretation: applying rock physics tools to reduce interpretation risk. Cambridge: Cambridge University Press; 2010."},{"key":"252_CR10","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611973655","volume-title":"Introduction to nonlinear optimization: theory, algorithms, and applications with MATLAB","author":"A Beck","year":"2014","unstructured":"Beck A. Introduction to nonlinear optimization: theory, algorithms, and applications with MATLAB. Philadelphia: SIAM; 2014."},{"key":"252_CR11","unstructured":"Benitez JAL, Furuya T, Faucher F, Tricoche X, de Hoop MV. Fine-tuning neural-operator architectures for training and generalization; 2023. arXiv Preprint arXiv:2301.11509."},{"key":"252_CR12","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1016\/j.petrol.2019.02.037","volume":"177","author":"SWA Canchumuni","year":"2019","unstructured":"Canchumuni SWA, Emerick AA, Pacheco MAC. History matching geological facies models based on ensemble smoother and deep generative models. J Pet Sci Eng. 2019;177:941\u201358.","journal-title":"J Pet Sci Eng"},{"issue":"3","key":"252_CR13","doi-asserted-by":"crossref","first-page":"1076","DOI":"10.1137\/S1064827501380630","volume":"24","author":"Y Cao","year":"2003","unstructured":"Cao Y, Li S, Petzold L, Serban R. Adjoint sensitivity analysis for differential-algebraic equations: the adjoint DAE system and its numerical solution. SIAM J Sci Comput. 2003;24(3):1076\u201389.","journal-title":"SIAM J Sci Comput"},{"key":"252_CR14","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.petrol.2012.03.018","volume":"100","author":"JM Carcione","year":"2012","unstructured":"Carcione JM, Gei D, Picotti S, Michelini A. Cross-hole electromagnetic and seismic modeling for CO2 detection and monitoring in a saline aquifer. J Pet Sci Eng. 2012;100:162\u201372.","journal-title":"J Pet Sci Eng"},{"issue":"7","key":"252_CR15","doi-asserted-by":"crossref","first-page":"2959","DOI":"10.5194\/gmd-13-2959-2020","volume":"13","author":"R Chandra","year":"2020","unstructured":"Chandra R, Azam D, Kapoor A, M\u00fcller DR. Surrogate-assisted Bayesian inversion for landscape and basin evolution models. Geosci Model Dev. 2020;13(7):2959\u201379.","journal-title":"Geosci Model Dev."},{"issue":"434","key":"252_CR16","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1080\/01621459.1996.10476956","volume":"91","author":"MK Cowles","year":"1996","unstructured":"Cowles MK, Carlin BP. Markov Chain Monte Carlo convergence diagnostics: a comparative review. J Am Stat Assoc. 1996;91(434):883\u2013904.","journal-title":"J Am Stat Assoc"},{"issue":"48","key":"252_CR17","doi-asserted-by":"crossref","first-page":"30055","DOI":"10.1073\/pnas.1912789117","volume":"117","author":"K Cranmer","year":"2020","unstructured":"Cranmer K, Brehmer J, Louppe G. The frontier of simulation-based inference. Proc Natl Acad Sci. 2020;117(48):30055\u201362.","journal-title":"Proc Natl Acad Sci"},{"key":"252_CR18","doi-asserted-by":"crossref","unstructured":"De Hoop M, Huang DZ, Qian E, Stuart AM. The cost-accuracy trade-off in operator learning with neural networks; 2022. arXiv Preprint arXiv:2203.13181.","DOI":"10.4208\/jml.220509"},{"key":"252_CR19","unstructured":"Dinh L, Sohl-Dickstein J, Bengio S. Density estimation using real nvp; 2016. arXiv Preprint arXiv:1605.08803."},{"issue":"1","key":"252_CR20","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1137\/17M111328X","volume":"11","author":"E Esser","year":"2018","unstructured":"Esser E, Guasch L, van Leeuwen T, Aravkin AY, Herrmann FJ. Total variation regularization strategies in full-waveform inversion. SIAM J Imaging Sci. 2018;11(1):376\u2013406.","journal-title":"SIAM J Imaging Sci"},{"issue":"1","key":"252_CR21","doi-asserted-by":"crossref","first-page":"2277","DOI":"10.1016\/j.egypro.2009.01.296","volume":"1","author":"BM Freifeld","year":"2009","unstructured":"Freifeld BM, Daley TM, Hovorka SD, Henninges J, Underschultz J, Sharma S. Recent advances in well-based monitoring of CO2 sequestration. Energy Procedia. 2009;1(1):2277\u201384.","journal-title":"Energy Procedia"},{"key":"252_CR22","doi-asserted-by":"publisher","first-page":"3916","DOI":"10.1016\/j.egypro.2017.03.1523","volume":"114","author":"AK Furre","year":"2017","unstructured":"Furre AK, Eiken O, Vevatne Alnes, Vevatne JN, Ki\u00e6r AF. 20 years of monitoring CO2-injection at sleipner. Energy Procedia. 2017;114:3916\u201326. https:\/\/doi.org\/10.1016\/j.egypro.2017.03.1523.","journal-title":"Energy Procedia"},{"issue":"1","key":"252_CR23","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1137\/S0895479897326432","volume":"21","author":"GH Golub","year":"1999","unstructured":"Golub GH, Hansen PC, O\u2019Leary DP. Tikhonov regularization and total least squares. SIAM J Matrix Anal Appl. 1999;21(1):185\u201394.","journal-title":"SIAM J Matrix Anal Appl"},{"key":"252_CR24","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets. Adv Neural Inf Process Syst. 2014; 27. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/hash\/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html."},{"key":"252_CR25","doi-asserted-by":"crossref","unstructured":"Grady TJ, Khan R, Louboutin M, Yin Z, Witte PA, Chandra R, Hewett RJ, Herrmann FJ. Model-parallel fourier neural operators as learned surrogates for large-scale parametric PDEs. Comput Geosci. 2023; 105402. https:\/\/doi.org\/10.1016 j.cageo.2023.105402.","DOI":"10.1016\/j.cageo.2023.105402"},{"issue":"6","key":"252_CR26","first-page":"83","volume":"6","author":"A Griewank","year":"1989","unstructured":"Griewank A, et al. On automatic differentiation. Math Progr Recent Dev Appl. 1989;6(6):83\u2013107.","journal-title":"Math Progr Recent Dev Appl"},{"key":"252_CR27","doi-asserted-by":"crossref","unstructured":"Gross H, Mazuyer A. GEOSX: a multiphysics, multilevel simulator designed for exascale computing. In: SPE reservoir simulation conference OnePetro; 2021","DOI":"10.3997\/2214-4609.2021612014"},{"key":"252_CR28","doi-asserted-by":"crossref","unstructured":"Heidenreich S, Gross H, Henn MA, Elster C, B\u00e4r M. A surrogate model enables a Bayesian approach to the inverse problem of scatterometry. J Phys Conf Ser. 2014;490: 012007. (1. IOP publishing)","DOI":"10.1088\/1742-6596\/490\/1\/012007"},{"issue":"4","key":"252_CR29","doi-asserted-by":"crossref","first-page":"A23","DOI":"10.1190\/1.2944169","volume":"73","author":"G Hennenfent","year":"2008","unstructured":"Hennenfent G, van den Berg E, Friedlander MP, Herrmann FJ. New insights into one-norm solvers from the pareto curve. Geophysics. 2008;73(4):A23-26.","journal-title":"Geophysics"},{"issue":"1","key":"252_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40323-023-00242-2","volume":"10","author":"S Hijazi","year":"2023","unstructured":"Hijazi S, Freitag M, Landwehr N. POD-galerkin reduced order models and physics-informed neural networks for solving inverse problems for the Navier\u2013Stokes equations. Adv Model Simul Eng Sci. 2023;10(1):1\u201338.","journal-title":"Adv Model Simul Eng Sci"},{"key":"252_CR31","first-page":"12225","volume":"35","author":"C Horvat","year":"2022","unstructured":"Horvat C, Pfister JP. Intrinsic dimensionality estimation using normalizing flows. Adv Neural Inf Process Syst. 2022;35:12225\u201336.","journal-title":"Adv Neural Inf Process Syst"},{"key":"252_CR32","doi-asserted-by":"crossref","DOI":"10.1002\/9781119156871","volume-title":"Geophysical monitoring for geologic carbon storage","author":"L Huang","year":"2022","unstructured":"Huang L. Geophysical monitoring for geologic carbon storage. Hoboken: Wiley; 2022."},{"issue":"25","key":"252_CR33","doi-asserted-by":"crossref","first-page":"602","DOI":"10.21105\/joss.00602","volume":"3","author":"M Innes","year":"2018","unstructured":"Innes M. Flux: elegant machine learning with Julia. J Open Source Softw. 2018;3(25):602.","journal-title":"J Open Source Softw"},{"issue":"1","key":"252_CR34","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.compfluid.2010.09.039","volume":"46","author":"JD Jansen","year":"2011","unstructured":"Jansen JD. Adjoint-based optimization of multi-phase flow through porous media\u2014a review. Comput Fluids. 2011;46(1):40\u201351.","journal-title":"Comput Fluids"},{"issue":"6","key":"252_CR35","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","volume":"3","author":"GE Karniadakis","year":"2021","unstructured":"Karniadakis GE, Kevrekidis IG, Lu L, Perdikaris P, Wang S, Yang L. Physics-informed machine learning. Nat Rev Phys. 2021;3(6):422\u201340.","journal-title":"Nat Rev Phys"},{"key":"252_CR36","unstructured":"Kingma DP, Welling M. Auto-encoding variational Bayes; 2013. arXiv Preprint arXiv:1312.6114."},{"issue":"11","key":"252_CR37","doi-asserted-by":"crossref","first-page":"3964","DOI":"10.1109\/TPAMI.2020.2992934","volume":"43","author":"I Kobyzev","year":"2020","unstructured":"Kobyzev I, Prince SJD, Brubaker MA. Normalizing flows: an introduction and review of current methods. IEEE Trans Pattern Anal Mach Intell. 2020;43(11):3964\u201379.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"252_CR38","unstructured":"Kontolati K, Goswami S, Karniadakis GE, Shields MD. Learning in latent spaces improves the predictive accuracy of deep neural operators; 2023. arXiv Preprint arXiv:2304.07599."},{"key":"252_CR39","first-page":"13237","volume":"22","author":"N Kovachki","year":"2021","unstructured":"Kovachki N, Lanthaler S, Mishra S. On universal approximation and error bounds for Fourier neural operators. J Mach Learn Res. 2021;22:13237\u2013312.","journal-title":"J Mach Learn Res."},{"key":"252_CR40","unstructured":"Kovachki N, Li Z, Liu B, Azizzadenesheli K, Bhattacharya K, Stuart A, Anandkumar A. Neural operator: learning maps between function spaces; 2021. arXiv Preprint arXiv:2108.08481."},{"issue":"8191\u201399","key":"252_CR41","first-page":"9","volume":"35","author":"J Kruse","year":"2021","unstructured":"Kruse J, Detommaso G, K\u00f6the U, Scheichl R. HINT: hierarchical invertible neural transport for density estimation and Bayesian inference. Proc AAAI Conf Artif Intell. 2021;35(8191\u201399):9.","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"4","key":"252_CR42","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1137\/21M1439456","volume":"10","author":"S Lan","year":"2022","unstructured":"Lan S, Li S, Shahbaba B. Scaling up Bayesian uncertainty quantification for inverse problems using deep neural networks. SIAM\/ASA J Uncertainty Quant. 2022;10(4):1684\u2013713.","journal-title":"SIAM\/ASA J Uncertainty Quant"},{"issue":"4","key":"252_CR43","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s40687-022-00343-1","volume":"9","author":"K Lensink","year":"2022","unstructured":"Lensink K, Peters B, Haber E. Fully hyperbolic convolutional neural networks. Res Math Sci. 2022;9(4):60.","journal-title":"Res Math Sci"},{"issue":"8","key":"252_CR44","doi-asserted-by":"crossref","first-page":"e2019WR027032.","DOI":"10.1029\/2019WR027032","volume":"56","author":"D Li","year":"2020","unstructured":"Li D, Xu K, Harris JM, Darve E. Coupled time-lapse full-waveform inversion for subsurface flow problems using intrusive automatic differentiation. Water Resour Res. 2020;56(8):e2019WR027032.","journal-title":"Water Resour Res"},{"issue":"3","key":"252_CR45","doi-asserted-by":"crossref","first-page":"A13","DOI":"10.1190\/geo2011-0410.1","volume":"77","author":"X Li","year":"2012","unstructured":"Li X, Aravkin AY, van Leeuwen T, Herrmann FJ. Fast Randomized full-waveform inversion with compressive sensing. Geophysics. 2012;77(3):A13-17.","journal-title":"Geophysics"},{"key":"252_CR46","unstructured":"Li Z, Kovachki N, Azizzadenesheli K, Liu B, Bhattacharya K, Stuart A, Anandkumar A. Fourier neural operator for parametric partial differential equations; 2020. arXiv Preprint arXiv:2010.08895."},{"key":"252_CR47","unstructured":"Li Z, Zheng H, Kovachki N, Jin D, Chen H, Liu B, Azizzadenesheli K, Anandkumar A. Physics-informed neural operator for learning partial differential equations; 2021. arXiv Preprint arXiv:2111.03794."},{"key":"252_CR48","doi-asserted-by":"crossref","DOI":"10.1017\/9781108591416","volume-title":"An introduction to reservoir simulation using MATLAB\/GNU octave: user guide for the MATLAB reservoir simulation toolbox (MRST)","author":"KA Lie","year":"2019","unstructured":"Lie KA. An introduction to reservoir simulation using MATLAB\/GNU octave: user guide for the MATLAB reservoir simulation toolbox (MRST). Cambridge: Cambridge University Press; 2019."},{"issue":"1\u20133","key":"252_CR49","first-page":"503","volume":"45","author":"DC Liu","year":"1989","unstructured":"Liu DC, Nocedal J. On the limited memory BFGS method for large scale optimization. Math Progr. 1989;45(1\u20133):503\u201328.","journal-title":"Math Progr"},{"issue":"3","key":"252_CR50","first-page":"2022JB025322JB0","volume":"128","author":"M Liu","year":"2023","unstructured":"Liu M, Vashisth D, Grana D, Mukerji T. Joint inversion of geophysical data for geologic carbon sequestration monitoring: a differentiable physics-informed neural network model. J Geophys Res Solid Earth. 2023;128(3):2022JB025322JB0e2025372.","journal-title":"J Geophys Res Solid Earth"},{"key":"252_CR51","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-12-1165-2019","author":"M Louboutin","year":"2019","unstructured":"Louboutin M, Luporini F, Lange M, Kukreja N, Witte PA, Herrmann FJ, Velesko P, Gorman GJ. Devito (V3.1.0): an embedded domain-specific language for finite differences and geophysical exploration. Geosci Model Dev. 2019. https:\/\/doi.org\/10.5194\/gmd-12-1165-2019.","journal-title":"Geosci Model Dev"},{"key":"252_CR52","doi-asserted-by":"publisher","unstructured":"Louboutin M, Witte PA, Siahkoohi A, Rizzuti G, Yin Z, Orozco R, Herrmann FJ. Accelerating innovation with software abstractions for scalable computational geophysics; 2022. https:\/\/doi.org\/10.1190\/image2022-3750561.1.","DOI":"10.1190\/image2022-3750561.1"},{"key":"252_CR53","doi-asserted-by":"publisher","unstructured":"Louboutin M, Witte P, Yin Z, Modzelewski H, Carlos da Costa K, Nogueira P. Slimgroup\/JUDI.jl: V3.2.3 (version v3.2.3). Zenodo; 2023. https:\/\/doi.org\/10.5281\/zenodo.7785440.","DOI":"10.5281\/zenodo.7785440"},{"issue":"7","key":"252_CR54","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1190\/tle42070474.1","volume":"42","author":"M Louboutin","year":"2023","unstructured":"Louboutin M, Yin Z, Orozco R, Grady II TJ, Siahkoohi A, Rizzuti G, Witte PA, M\u00f8yner O, Gorman GJ, Herrmann FJ. Learned multiphysics inversion with differentiable programming and machine learning. Lead Edge. 2023;42(7):452\u2013516. https:\/\/doi.org\/10.1190\/tle42070474.1.","journal-title":"Lead Edge."},{"key":"252_CR55","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1016\/j.ymssp.2019.01.018","volume":"123","author":"K Lu","year":"2019","unstructured":"Lu K, Jin Y, Chen Y, Yang Y, Hou L, Zhang Z, Li Z, Chao F. Review for order reduction based on proper orthogonal decomposition and outlooks of applications in mechanical systems. Mech Syst Signal Process. 2019;123:264\u201397.","journal-title":"Mech Syst Signal Process"},{"key":"252_CR56","unstructured":"Lu L, Jin P, Karniadakis GE. Deeponet: learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators; 2019.\u201d arXiv Preprint arXiv:1910.03193."},{"issue":"2","key":"252_CR57","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1190\/1.3304817","volume":"29","author":"D Lumley","year":"2010","unstructured":"Lumley D. 4D seismic monitoring of CO2 sequestration. Lead Edge. 2010;29(2):150\u20135.","journal-title":"Lead Edge"},{"issue":"1","key":"252_CR58","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3374916","volume":"46","author":"F Luporini","year":"2020","unstructured":"Luporini F, Louboutin M, Lange M, Kukreja N, Witte P, H\u00fcckelheim J, Yount C, Kelly PHJ, Herrmann FJ, Gorman GJ. Architecture and performance of devito, a system for automated stencil computation. ACM Trans Math Softw(TOMS). 2020;46(1):1\u201328.","journal-title":"ACM Trans Math Softw(TOMS)"},{"key":"252_CR59","unstructured":"Mosser L, Dubrule O, Blunt MJ. Deepflow: history matching in the space of deep generative models; 2019. arXiv Preprint arXiv:1905.05749."},{"key":"252_CR60","doi-asserted-by":"publisher","unstructured":"M\u00f8yner O, Bruer G, Yin Z. Sintefmath\/JutulDarcy.jl: V0.2.3 (version v0.2.3). Zenodo; 2023. https:\/\/doi.org\/10.5281\/zenodo.7855628.","DOI":"10.5281\/zenodo.7855628"},{"key":"252_CR61","doi-asserted-by":"publisher","unstructured":"M\u00f8yner O, Johnsrud M, Nilsen HM, Raynaud X, Lye KO, Yin Z. Sintefmath\/Jutul.jl: V0.2.6 (version v0.2.6). Zenodo; 2023. https:\/\/doi.org\/10.5281\/zenodo.7855605.","DOI":"10.5281\/zenodo.7855605"},{"key":"252_CR62","doi-asserted-by":"crossref","first-page":"3620","DOI":"10.1016\/j.egypro.2011.02.292","volume":"4","author":"JP Nogues","year":"2011","unstructured":"Nogues JP, Nordbotten JM, Celia MA. Detecting leakage of brine or CO2 through abandoned wells in a geological sequestration operation using pressure monitoring wells. Energy Procedia. 2011;4:3620\u20137.","journal-title":"Energy Procedia"},{"issue":"2","key":"252_CR63","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/S1750-5836(07)00018-7","volume":"1","author":"SL Nooner","year":"2007","unstructured":"Nooner SL, Eiken O, Hermanrud C, Sasagawa GS, Stenvold T, Zumberge MA. Constraints on the in situ density of CO2 within the Utsira formation from time-lapse seafloor gravity measurements. Int J Greenhouse Gas Control. 2007;1(2):198\u2013214.","journal-title":"Int J Greenhouse Gas Control"},{"key":"252_CR64","doi-asserted-by":"crossref","DOI":"10.1002\/9781118137086","volume-title":"Geological storage of CO2: modeling approaches for large-scale simulation","author":"JM Nordbotten","year":"2011","unstructured":"Nordbotten JM, Celia MA. Geological storage of CO2: modeling approaches for large-scale simulation. Hoboken: John Wiley Sons; 2011."},{"key":"252_CR65","unstructured":"O\u2019Leary-Roseberry T, Chen P, Villa U, Ghattas O. Derivate informed neural operator: an efficient framework for high-dimensional parametric derivative learning; 2022. arXiv Preprint arXiv:2206.10745."},{"key":"252_CR66","unstructured":"Orozco R, Louboutin M, Herrmann FJ. Memory efficient invertible neural networks for 3D photoacoustic imaging; 2022. arXiv Preprint arXiv:2204.11850."},{"key":"252_CR67","unstructured":"Orozco R, Louboutin M, Siahkoohi A, Rizzuti G, van Leeuwen T, Herrmann F. Amortized normalizing flows for transcranial ultrasound with uncertainty quantification; 2023. https:\/\/openreview.net\/forum?id=LoJG-lUIlk."},{"key":"252_CR68","unstructured":"Orozco R, Siahkoohi A, Louboutin M, Herrmann FJ. Refining amortized posterior approximations using gradient-based summary statistics; 2023. arXiv Preprint arXiv:2305.08733."},{"key":"252_CR69","unstructured":"Orozco R, Siahkoohi A, Rizzuti G, van Leeuwen T, Herrmann FJ. Photoacoustic imaging with conditional priors from normalizing flows; 2021. https:\/\/openreview.net\/forum?id=woi1OTvROO1."},{"key":"252_CR70","doi-asserted-by":"publisher","unstructured":"Orozco R, Siahkoohi A, Rizzuti G, van Leeuwen T, Herrmann FJ. Adjoint operators enable fast and amortized machine learning based Bayesian uncertainty quantification. In: Medical imaging 2023: image processing, edited by Olivier Colliot and Ivana I\u00c5\u00a1gum, 12464:124641L. International Society for Optics; Photonics; SPIE; 2023. https:\/\/doi.org\/10.1117\/12.2651691.","DOI":"10.1117\/12.2651691"},{"issue":"1","key":"252_CR71","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1038\/s41524-020-00431-2","volume":"6","author":"R Pestourie","year":"2020","unstructured":"Pestourie R, Mroueh Y, Nguyen TV, Das P, Johnson SG. Active learning of deep surrogates for PDEs: application to metasurface design. NPJ Comput Mater. 2020;6(1):164.","journal-title":"NPJ Comput Mater"},{"issue":"1","key":"252_CR72","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1190\/tle36010094.1","volume":"36","author":"B Peters","year":"2017","unstructured":"Peters B, Herrmann FJ. Constraints versus penalties for edge-preserving full-waveform inversion. Lead Edge. 2017;36(1):94\u2013100.","journal-title":"Lead Edge"},{"issue":"2","key":"252_CR73","doi-asserted-by":"crossref","first-page":"R251","DOI":"10.1190\/geo2018-0192.1","volume":"84","author":"B Peters","year":"2019","unstructured":"Peters B, Smithyman BR, Herrmann FJ. Projection methods and applications for seismic nonlinear inverse problems with multiple constraints. Geophysics. 2019;84(2):R251-69.","journal-title":"Geophysics"},{"issue":"2","key":"252_CR74","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1111\/j.1365-246X.2006.02978.x","volume":"167","author":"RE Plessix","year":"2006","unstructured":"Plessix RE. A review of the adjoint-state method for computing the gradient of a functional with geophysical applications. Geophys J Int. 2006;167(2):495\u2013503.","journal-title":"Geophys J Int"},{"key":"252_CR75","doi-asserted-by":"publisher","unstructured":"Powell MJD. Radial basis functions for multivariable interpolation: a review. Algorithms for the approximation of functions and data; 1985. https:\/\/doi.org\/10.5555\/48424.48433.","DOI":"10.5555\/48424.48433"},{"key":"252_CR76","doi-asserted-by":"crossref","DOI":"10.1016\/j.physd.2020.132401","volume":"406","author":"E Qian","year":"2020","unstructured":"Qian E, Kramer B, Peherstorfer B, Willcox K. Lift & learn: physics-informed machine learning for large-scale nonlinear dynamical systems. Phys D Nonlinear Phenomena. 2020;406: 132401.","journal-title":"Phys D Nonlinear Phenomena"},{"key":"252_CR77","unstructured":"Rahman MA, Ross ZE, Azizzadenesheli K. U-No: u-shaped neural operators; 2022. arXiv Preprint arXiv:2204.11127."},{"key":"252_CR78","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.camwa.2020.05.014","volume":"81","author":"A Rasmussen","year":"2021","unstructured":"Rasmussen A, Sandve TH, Bao K, Lauser A, Hove J, Skaflestad B, Klofkorn R, Blatt M, Rustad AB, Saevareid O, Lie KA. The open porous media flow reservoir simulator. Comput Math Appl. 2021;81:159\u201385.","journal-title":"Comput Math Appl."},{"key":"252_CR79","doi-asserted-by":"publisher","DOI":"10.1029\/2011WR011527","author":"S Razavi","year":"2012","unstructured":"Razavi S, Tolson BA, Burn DH. Review of surrogate modeling in water resources. Water Resour Res. 2012. https:\/\/doi.org\/10.1029\/2011WR011527.","journal-title":"Water Resour Res"},{"key":"252_CR80","unstructured":"Rezende D, Mohamed S. Variational inference with normalizing flows. In: International conference on machine learning. PMLR.; 2015. p. 1530\u201338."},{"key":"252_CR81","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-78841-6","volume-title":"Model order reduction: theory, research aspects and applications","author":"WHA Schilders","year":"2008","unstructured":"Schilders WHA, Van der Vorst HA, Rommes J. Model order reduction: theory, research aspects and applications, vol. 13. Berlin: Springer; 2008."},{"key":"252_CR82","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139168359","volume-title":"Exploration seismology","author":"RE Sheriff","year":"1995","unstructured":"Sheriff RE, Geldart LP. Exploration seismology. Cambridge: Cambridge University Press; 1995."},{"key":"252_CR83","doi-asserted-by":"publisher","unstructured":"Siahkoohi A, Herrmann FJ. Learning by example: fast reliability-aware seismic imaging with normalizing flows. In: First international meeting for applied geoscience & energy. Society of exploration geophysicists; expanded abstracts; 2021. p. 1580\u201385 https:\/\/doi.org\/10.1190\/segam2021-3581836.1.","DOI":"10.1190\/segam2021-3581836.1"},{"key":"252_CR84","unstructured":"Siahkoohi A, Rizzuti G, Louboutin M, Witte PA, Herrmann FJ. Preconditioned training of normalizing flows for variational inference in inverse problems; 2021. https:\/\/openreview.net\/pdf?id=P9m1sMaNQ8T."},{"issue":"3","key":"252_CR85","doi-asserted-by":"crossref","first-page":"R297","DOI":"10.1190\/geo2022-0472.1","volume":"88","author":"A Siahkoohi","year":"2023","unstructured":"Siahkoohi A, Rizzuti G, Orozco R, Herrmann FJ. Reliable amortized variational inference with physics-based latent distribution correction. Geophysics. 2023;88(3):R297-322.","journal-title":"Geophysics"},{"key":"252_CR86","doi-asserted-by":"publisher","DOI":"10.1190\/geo2022-0472.1","author":"A Siahkoohi","year":"2023","unstructured":"Siahkoohi A, Rizzuti G, Orozco R, Herrmann FJ. Reliable amortized variational inference with physics-based latent distribution correction. Geophysics. 2023. https:\/\/doi.org\/10.1190\/geo2022-0472.1.","journal-title":"Geophysics"},{"key":"252_CR87","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/s11075-009-9350-8","volume":"54","author":"PS Stanimirovi\u0107","year":"2010","unstructured":"Stanimirovi\u0107 PS, Miladinovi\u0107 MB. Accelerated gradient descent methods with line search. Numer Algorithms. 2010;54:503\u201320.","journal-title":"Numer Algorithms"},{"issue":"8","key":"252_CR88","doi-asserted-by":"crossref","first-page":"1259","DOI":"10.1190\/1.1441754","volume":"49","author":"A Tarantola","year":"1984","unstructured":"Tarantola A. Inversion of seismic reflection data in the acoustic approximation. Geophysics. 1984;49(8):1259\u201366.","journal-title":"Geophysics"},{"key":"252_CR89","doi-asserted-by":"crossref","unstructured":"Tarantola A. Inverse problem theory and methods for model parameter estimation. SIAM; 2005.","DOI":"10.1137\/1.9780898717921"},{"issue":"4","key":"252_CR90","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process. 2004;13(4):600\u201312.","journal-title":"IEEE Trans Image Process"},{"key":"252_CR91","volume":"163","author":"G Wen","year":"2022","unstructured":"Wen G, Li Z, Azizzadenesheli K, Anandkumar A, Benson SM. U-FNO\u2014an enhanced fourier neural operator-based deep-learning model for multiphase flow. Adv Water Resour. 2022;163: 104180.","journal-title":"Adv Water Resour"},{"key":"252_CR92","doi-asserted-by":"crossref","first-page":"1732","DOI":"10.1039\/D2EE04204E","volume":"16","author":"G Wen","year":"2023","unstructured":"Wen G, Li Z, Long Q, Azizzadenesheli K, Anandkumar A, Benson SM. Real-time high-resolution CO2 geological storage prediction using nested fourier neural operators. Energy Environ Sci. 2023;16:1732\u201341.","journal-title":"Energy Environ Sci"},{"key":"252_CR93","unstructured":"Wen J, Ahmad R, Schniter P. A conditional normalizing flow for accelerated multi-coil MR imaging; 2023. arXiv Preprint arXiv:2306.01630."},{"key":"252_CR94","unstructured":"Witte PA, Hewett RJ, Saurabh K, Sojoodi A, Chandra R. SciAI4Industry\u2014solving PDEs for industry-scale problems with deep learning; 2022. arXiv Preprint arXiv:2211.12709."},{"key":"252_CR95","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijggc.2023.103880","volume":"126","author":"PA Witte","year":"2023","unstructured":"Witte PA, Konuk T, Skjetne E, Chandra R. Fast CO2 saturation simulations on large-scale geomodels with artificial intelligence-based wavelet neural operators. Int J Greenhouse Gas Control. 2023;126: 103880.","journal-title":"Int J Greenhouse Gas Control"},{"issue":"3","key":"252_CR96","doi-asserted-by":"publisher","first-page":"F57","DOI":"10.1190\/geo2018-0174.1","volume":"84","author":"PA Witte","year":"2019","unstructured":"Witte PA, Louboutin M, Kukreja N, Luporini F, Lange M, Gorman GJ, Herrmann FJ. A large-scale framework for symbolic implementations of seismic inversion algorithms in Julia. Geophysics. 2019;84(3):F57-71. https:\/\/doi.org\/10.1190\/geo2018-0174.1.","journal-title":"Geophysics"},{"key":"252_CR97","unstructured":"Witte PA, Redmond WA, Hewett RJ, Chandra R. Industry-scale CO2 flow simulations with model-parallel fourier neural operators. In: NeurIPS 2022 workshop tackling climate change with machine learning; 2022."},{"key":"252_CR98","doi-asserted-by":"publisher","unstructured":"Witte P, Louboutin M, Orozco R, Grizzuti AS, Herrmann F, Peters, P\u00e1ll Haraldsson B, Yin Z. Slimgroup\/InvertibleNetworks.jl: V2.2.5 (version v2.2.5). Zenodo; 2023. https:\/\/doi.org\/10.5281\/zenodo.7850287.","DOI":"10.5281\/zenodo.7850287"},{"key":"252_CR99","first-page":"1","volume":"61","author":"Y Yang","year":"2023","unstructured":"Yang Y, Gao AF, Azizzadenesheli K, Clayton RW, Ross ZE. Rapid seismic waveform modeling and inversion with neural operators. IEEE Trans Geosci Remote Sens. 2023;61:1\u201312.","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"252_CR100","doi-asserted-by":"publisher","unstructured":"Yin Z, Grant B, Mathias L. Slimgroup\/JutulDarcyRules.jl: V0.2.5 (version v0.2.5). Zenodo; 2023. https:\/\/doi.org\/10.5281\/zenodo.7863970.","DOI":"10.5281\/zenodo.7863970"},{"issue":"1","key":"252_CR101","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1190\/tle42010069.1","volume":"42","author":"Z Yin","year":"2023","unstructured":"Yin Z, Erdinc HT, Gahlot AP, Louboutin M, Herrmann FJ. Derisking geologic carbon storage from high-resolution time-lapse seismic to explainable leakage detection. Lead Edge. 2023;42(1):69\u201376. https:\/\/doi.org\/10.1190\/tle42010069.1.","journal-title":"Lead Edge"},{"key":"252_CR102","doi-asserted-by":"crossref","unstructured":"Yin Z, Siahkoohi A, Louboutin M, Herrmann FJ. Learned coupled inversion for carbon sequestration monitoring and forecasting with fourier neural operators; 2022. https:\/\/doi.org\/10.1190\/image2022-3722848.1.","DOI":"10.1190\/image2022-3722848.1"},{"issue":"4","key":"252_CR103","doi-asserted-by":"crossref","first-page":"e2019JB018589.","DOI":"10.1029\/2019JB018589","volume":"125","author":"X Zhang","year":"2020","unstructured":"Zhang X, Curtis A. Seismic tomography using variational inference methods. J Geophys Res Solid Earth. 2020;125(4):e2019JB018589.","journal-title":"J Geophys Res Solid Earth"},{"issue":"7","key":"252_CR104","doi-asserted-by":"crossref","first-page":"e2021JB022320.","DOI":"10.1029\/2021JB022320","volume":"126","author":"X Zhang","year":"2021","unstructured":"Zhang X, Curtis A. Bayesian geophysical inversion using invertible neural networks. J Geophys Res Solid Earth. 2021;126(7):e2021JB022320.","journal-title":"J Geophys Res Solid Earth"},{"issue":"1","key":"252_CR105","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1093\/gji\/ggab298","volume":"228","author":"X Zhao","year":"2021","unstructured":"Zhao X, Curtis A, Zhang X. Bayesian seismic tomography using normalizing flows. Geophys J Int. 2021;228(1):213\u201339. https:\/\/doi.org\/10.1093\/gji\/ggab298.","journal-title":"Geophys J Int."},{"key":"252_CR106","doi-asserted-by":"publisher","unstructured":"Zhdanov MS, Endo M, Black N, Spangler L, Fairweather SA, Hibbs A, Eiskamp GA, Will R. Electromagnetic monitoring of CO2 sequestration in deep reservoirs. First Break. 2013;31(2). https:\/\/doi.org\/10.3997\/1365-2397.31.2.66662.","DOI":"10.3997\/1365-2397.31.2.66662"}],"container-title":["Advanced Modeling and Simulation in Engineering Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40323-023-00252-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40323-023-00252-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40323-023-00252-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T09:16:01Z","timestamp":1700471761000},"score":1,"resource":{"primary":{"URL":"https:\/\/amses-journal.springeropen.com\/articles\/10.1186\/s40323-023-00252-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,11]]},"references-count":106,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["252"],"URL":"https:\/\/doi.org\/10.1186\/s40323-023-00252-0","relation":{},"ISSN":["2213-7467"],"issn-type":[{"value":"2213-7467","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,11]]},"assertion":[{"value":"17 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2023","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The spelling errors have been corrected","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"14"}}