{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T03:18:15Z","timestamp":1783048695898,"version":"3.54.6"},"reference-count":47,"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":[[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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42571032"],"award-info":[{"award-number":["42571032"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12271408"],"award-info":[{"award-number":["12271408"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational and Applied Mathematics"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.cam.2026.117777","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T02:24:29Z","timestamp":1778552669000},"page":"117777","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Reinforcement learning based data assimilation for unknown state model"],"prefix":"10.1016","volume":"488","author":[{"given":"Ziyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3410-1219","authenticated-orcid":false,"given":"Lijian","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinguang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cam.2026.117777_bib0001","series-title":"Data Assimilation: A Mathematical Introduction","author":"Law","year":"2015"},{"key":"10.1016\/j.cam.2026.117777_bib0002","series-title":"Data Assimilation: Methods, Algorithms, and Applications","author":"Asch","year":"2016"},{"key":"10.1016\/j.cam.2026.117777_bib0003","doi-asserted-by":"crossref","unstructured":"M. Roth, G. Hendeby, C. Fritsche and F. Gustafsson, The Ensemble Kalman filter: a signal processing perspective, EURASIP J. Adv. Signal Process., 2017, pp.1\u201316.","DOI":"10.1186\/s13634-017-0492-x"},{"key":"10.1016\/j.cam.2026.117777_bib0004","series-title":"Atmospheric Modeling, Data Assimilation and Predictability","author":"Kalnay","year":"2003"},{"key":"10.1016\/j.cam.2026.117777_bib0005","series-title":"Inverse Theory for Petroleum Reservoir Characterization and History Matching","author":"Oliver","year":"2008"},{"key":"10.1016\/j.cam.2026.117777_bib0006","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kalman","year":"1960","journal-title":"J. Basic Eng."},{"key":"10.1016\/j.cam.2026.117777_bib0007","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s10236-003-0036-9","article-title":"The ensemble Kalman filter: theoretical formulation and practical implementation","volume":"53","author":"Evensen","year":"2003","journal-title":"Ocean Dyn."},{"key":"10.1016\/j.cam.2026.117777_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2022.115282","article-title":"A multi-fidelity ensemble Kalman filter with hyperreduced reduced-order models","volume":"398","author":"Donoghue","year":"2022","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.cam.2026.117777_bib0009","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1080\/01621459.1999.10474153","article-title":"Filtering via simulation: auxiliary particle filters","volume":"94","author":"Pitt","year":"1999","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/j.cam.2026.117777_bib0010","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/nclimate2657","article-title":"Attribution of climate extreme events","volume":"5","author":"Trenberth","year":"2015","journal-title":"Nat. Clim. Change"},{"key":"10.1016\/j.cam.2026.117777_bib0011","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1063\/1.1404847","article-title":"Turbulent heat flow: structures and scaling","volume":"54","author":"Kadanoff","year":"2001","journal-title":"Phys. Today"},{"key":"10.1016\/j.cam.2026.117777_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2024.117201","article-title":"Multi-domain encoder\u2013decoder neural networks for latent data assimilation in dynamical systems","volume":"430","author":"Cheng","year":"2024","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.cam.2026.117777_bib0013","series-title":"International Conference on Machine Learning","first-page":"544","article-title":"Recurrent Kalman networks: factorized inference in high-dimensional deep feature spaces","volume":"97","author":"Becker","year":"2019"},{"key":"10.1016\/j.cam.2026.117777_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.cam.2024.116399","article-title":"Model free data assimilation with Takens embedding","volume":"460","author":"Wang","year":"2025","journal-title":"J. Comput. Appl. Math."},{"key":"10.1016\/j.cam.2026.117777_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2025.118285","article-title":"Flow-based Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems","volume":"446","author":"Wang","year":"2025","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.cam.2026.117777_bib0016","doi-asserted-by":"crossref","DOI":"10.1063\/1.4979665","article-title":"Reservoir observers: model-free inference of unmeasured variables in chaotic systems","volume":"27","author":"Lu","year":"2017","journal-title":"Chaos Interdiscip. J. Nonlinear Sci."},{"key":"10.1016\/j.cam.2026.117777_bib0017","article-title":"Ensemble Kalman filtering without a model","volume":"6","author":"Hamilton","year":"2016","journal-title":"Phys. Rev. X."},{"key":"10.1016\/j.cam.2026.117777_bib0018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"J. R. Stat. Soc.: Ser. B"},{"key":"10.1016\/j.cam.2026.117777_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.jocs.2020.101171","article-title":"Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 model","volume":"44","author":"Brajard","year":"2020","journal-title":"J. Comput. Sci."},{"key":"10.1016\/j.cam.2026.117777_bib0020","doi-asserted-by":"crossref","first-page":"55","DOI":"10.3934\/fods.2020004","article-title":"Bayesian inference of chaotic dynamics by merging data assimilation, machine learning and expectation-maximization","volume":"2","author":"Bocquet","year":"2020","journal-title":"Found. Data Sci."},{"key":"10.1016\/j.cam.2026.117777_bib0021","doi-asserted-by":"crossref","first-page":"1852","DOI":"10.1175\/1520-0493(2000)128<1852:AEKSFN>2.0.CO;2","article-title":"An ensemble Kalman smoother for nonlinear dynamics","volume":"128","author":"Evensen","year":"2000","journal-title":"Mon. Weather Rev."},{"key":"10.1016\/j.cam.2026.117777_bib0022","series-title":"Handbook of Nonlinear Filtering","first-page":"12","article-title":"A tutorial on particle filtering and smoothing: fifteen years later","author":"Doucet","year":"2009"},{"key":"10.1016\/j.cam.2026.117777_bib0023","unstructured":"D. Nguyen, S. Ouala, L. Drumetz, R. Fablet, Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations, 2020. arXiv: 2009.02296."},{"key":"10.1016\/j.cam.2026.117777_bib0024","series-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"1998"},{"key":"10.1016\/j.cam.2026.117777_bib0025","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: a brief survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"issue":"7540","key":"10.1016\/j.cam.2026.117777_bib0026","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.cam.2026.117777_bib0027","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1126\/science.aar6404","article-title":"A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play","volume":"362","author":"Silver","year":"2018","journal-title":"Science"},{"key":"10.1016\/j.cam.2026.117777_bib0028","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/j.cma.2018.11.026","article-title":"Meta-modeling game for deriving theory-consistent, microstructure-based traction\u2013separation laws via deep reinforcement learning","volume":"346","author":"Wang","year":"2019","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.cam.2026.117777_bib0029","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1177\/0278364913495721","article-title":"Reinforcement learning in robotics: a survey","volume":"32","author":"Kober","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.cam.2026.117777_bib0030","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","article-title":"Deep reinforcement learning for autonomous driving: a survey","volume":"23","author":"Kiran","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.cam.2026.117777_bib0031","doi-asserted-by":"crossref","DOI":"10.1029\/2023MS004178","article-title":"Data assimilation in chaotic systems using deep reinforcement learning","volume":"16","author":"Hammoud","year":"2024","journal-title":"J. Adv. Model. Earth Syst."},{"key":"10.1016\/j.cam.2026.117777_bib0032","doi-asserted-by":"crossref","unstructured":"P. Behnoudfar, N. Chen, RL-DAUNCE: Reinforcement Learning-Driven Data Assimilation with Uncertainty-Aware Constrained Ensembles, 2025. arXiv: 2505.05452.","DOI":"10.2139\/ssrn.5259995"},{"key":"10.1016\/j.cam.2026.117777_bib0033","unstructured":"J. Schulman, F. Wolski, P. Dhariwal, A. Radford, O. Klimov, Proximal policy optimization algorithms, (2017). arXiv: 1707.06347."},{"key":"10.1016\/j.cam.2026.117777_bib0034","series-title":"International Conference on Machine Learning","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"Schulman","year":"2015"},{"key":"10.1016\/j.cam.2026.117777_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2023.111945","article-title":"Deep reinforcement learning for optimal well control in subsurface systems with uncertain geology","volume":"477","author":"Nasir","year":"2023","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.cam.2026.117777_bib0036","unstructured":"J. Schulman, P. Moritz, S. Levine, M. Jordan, P. Abbeel, High-dimensional continuous control using generalized advantage estimation, (2015b). arXiv: 1506.02438."},{"key":"10.1016\/j.cam.2026.117777_bib0037","series-title":"International Conference on Machine Learning","first-page":"35970","article-title":"Learning belief representations for partially observable deep rl","volume":"202","author":"Wang","year":"2023"},{"key":"10.1016\/j.cam.2026.117777_bib0038","doi-asserted-by":"crossref","DOI":"10.1115\/1.4031175","article-title":"Closed-loop turbulence control: progress and challenges","volume":"67","author":"Brunton","year":"2015","journal-title":"Appl. Mech. Rev."},{"key":"10.1016\/j.cam.2026.117777_bib0039","series-title":"Advances in Neural Information Processing Systems","article-title":"Filtering variational objectives","volume":"30","author":"Maddison","year":"2017"},{"key":"10.1016\/j.cam.2026.117777_bib0040","series-title":"Feynman-Kac Formulae: Genealogical and Interacting Particle Systems With Applications","author":"Moral","year":"2004"},{"key":"10.1016\/j.cam.2026.117777_bib0041","doi-asserted-by":"crossref","first-page":"12326","DOI":"10.1109\/TVT.2023.3270353","article-title":"Split-KalmanNet: a robust model-based deep learning approach for state estimation","volume":"72","author":"Choi","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.cam.2026.117777_bib0042","doi-asserted-by":"crossref","first-page":"1669","DOI":"10.3934\/dcds.2010.28.1669","article-title":"Numerical approximations of Allen-Cahn and Cahn-Hilliard equations","volume":"28","author":"Shen","year":"2010","journal-title":"Discrete Contin. Dyn. Syst"},{"key":"10.1016\/j.cam.2026.117777_bib0043","doi-asserted-by":"crossref","first-page":"6241","DOI":"10.1016\/j.jcp.2008.03.012","article-title":"An efficient algorithm for solving the phase field crystal model","volume":"227","author":"Cheng","year":"2008","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.cam.2026.117777_bib0044","doi-asserted-by":"crossref","first-page":"6647","DOI":"10.1016\/j.jcp.2011.05.002","article-title":"First-order system least squares and the energetic variational approach for two-phase flow","volume":"230","author":"Adler","year":"2011","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.cam.2026.117777_bib0045","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1109\/TIP.2008.919367","article-title":"A wavelet-Laplace variational technique for image deconvolution and inpainting","volume":"17","author":"Dobrosotskaya","year":"2008","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cam.2026.117777_bib0046","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1007\/s00245-018-9546-1","article-title":"Optimal control problem for the Cahn\u2013Hilliard\/Allen\u2013Cahn equation with state constraint","volume":"82","author":"Zhang","year":"2020","journal-title":"Appl. Math. Optim."},{"key":"10.1016\/j.cam.2026.117777_bib0047","doi-asserted-by":"crossref","unstructured":"D.E. Ozan, A. N\u00f3voa, G. Rigas, L. Magri, Data-assimilated model-informed reinforcement learning, 2025. arXiv: 2506.01755.","DOI":"10.1098\/rspa.2025.0476"}],"container-title":["Journal of Computational and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S037704272600419X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S037704272600419X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T02:40:24Z","timestamp":1783046424000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S037704272600419X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":47,"alternative-id":["S037704272600419X"],"URL":"https:\/\/doi.org\/10.1016\/j.cam.2026.117777","relation":{},"ISSN":["0377-0427"],"issn-type":[{"value":"0377-0427","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Reinforcement learning based data assimilation for unknown state model","name":"articletitle","label":"Article Title"},{"value":"Journal of Computational and Applied Mathematics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cam.2026.117777","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"117777"}}