{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T04:30:47Z","timestamp":1749357047666,"version":"3.37.3"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T00:00:00Z","timestamp":1639958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T00:00:00Z","timestamp":1639958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"leverhulme centre for wildfires, environment and society","award":["RC-2018-023"],"award-info":[{"award-number":["RC-2018-023"]}]},{"DOI":"10.13039\/501100006289","name":"\u00e9lectricit\u00e9 de france","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006289","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2022,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Data assimilation techniques are widely used to predict complex dynamical systems with uncertainties, based on time-series observation data. Error covariance matrices modeling is an important element in data assimilation algorithms which can considerably impact the forecasting accuracy. The estimation of these covariances, which usually relies on empirical assumptions and physical constraints, is often imprecise and computationally expensive, especially for systems of large dimensions. In this work, we propose a data-driven approach based on long short term memory (LSTM) recurrent neural networks (RNN) to improve both the accuracy and the efficiency of observation covariance specification in data assimilation for dynamical systems. Learning the covariance matrix from observed\/simulated time-series data, the proposed approach does not require any knowledge or assumption about prior error distribution, unlike classical posterior tuning methods. We have compared the novel approach with two state-of-the-art covariance tuning algorithms, namely DI01 and D05, first in a Lorenz dynamical system and then in a 2D shallow water twin experiments framework with different covariance parameterization using ensemble assimilation. This novel method shows significant advantages in observation covariance specification, assimilation accuracy, and computational efficiency.<\/jats:p>","DOI":"10.1007\/s00521-021-06739-4","type":"journal-article","created":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T07:03:42Z","timestamp":1639983822000},"page":"13149-13167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Observation error covariance specification in dynamical systems for data assimilation using recurrent neural networks"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8707-2589","authenticated-orcid":false,"given":"Sibo","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Mingming","family":"Qiu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,20]]},"reference":[{"issue":"8","key":"6739_CR1","doi-asserted-by":"publisher","first-page":"1747","DOI":"10.1175\/1520-0493(1992)120<1747:TNMCSS>2.0.CO;2","volume":"120","author":"DF Parrish","year":"1992","unstructured":"Parrish DF, Derber JC (1992) The national meteorological centers spectral statistical-interpolation analysis system. Mon Weather Rev 120(8):1747\u20131763","journal-title":"Mon Weather Rev"},{"issue":"5","key":"6739_CR2","doi-asserted-by":"publisher","first-page":"e535","DOI":"10.1002\/wcc.535","volume":"9","author":"A Carrassi","year":"2018","unstructured":"Carrassi A, Bocquet M, Bertino L, Evensen G (2018) Data assimilation in the geosciences: an overview of methods, issues, and perspectives. Wiley Interdiscip Rev Climate Change 9(5):e535","journal-title":"Wiley Interdiscip Rev Climate Change"},{"issue":"5","key":"6739_CR3","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1007\/s00477-020-01933-7","volume":"35","author":"S Cheng","year":"2021","unstructured":"Cheng S, Argaud J-P, Iooss B, Lucor D, Pon\u00e7ot A (2021) Error covariance tuning in variational data assimilation: application to an operating hydrological model. Stoch Env Res Risk Assess 35(5):1019\u20131038","journal-title":"Stoch Env Res Risk Assess"},{"issue":"11","key":"6739_CR4","doi-asserted-by":"publisher","first-page":"2951","DOI":"10.5194\/nhess-14-2951-2014","volume":"14","author":"MC Rochoux","year":"2014","unstructured":"Rochoux MC, Ricci S, Lucor D, Cuenot B, Trouv\u00e9 A (2014) Towards predictive data-driven simulations of wildfire spread-part I: Reduced-cost ensemble Kalman filter based on a polynomial chaos surrogate model for parameter estimation. Nat Hazard 14(11):2951\u20132973","journal-title":"Nat Hazard"},{"key":"6739_CR5","doi-asserted-by":"publisher","first-page":"1864","DOI":"10.28991\/cej-2020-03091588","volume":"6","author":"D Harisuseno","year":"2020","unstructured":"Harisuseno D (2020) Meteorological drought and its relationship with southern oscillation index (soi). Civil Eng J 6:1864\u20131875","journal-title":"Civil Eng J"},{"key":"6739_CR6","doi-asserted-by":"publisher","first-page":"107346","DOI":"10.1016\/j.anucene.2020.107346","volume":"141","author":"H Gong","year":"2020","unstructured":"Gong H, Yu Y, Li Q, Quan C (2020) An inverse-distance-based fitting term for 3D-Var data assimilation in nuclear core simulation. Ann Nucl Energy 141:107346","journal-title":"Ann Nucl Energy"},{"key":"6739_CR7","doi-asserted-by":"crossref","unstructured":"Asch M, Bocquet M, Nodet M (2016) Data assimilation: methods, algorithms, and applications. Fundament Algorithms SIAM","DOI":"10.1137\/1.9781611974546"},{"issue":"2","key":"6739_CR8","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1175\/MWR-D-17-0263.1","volume":"146","author":"JP Mattern","year":"2018","unstructured":"Mattern JP, Edwards CA, Moore AM (2018) Improving variational data assimilation through background and observation error adjustments. Mon Weather Rev 146(2):485\u2013501","journal-title":"Mon Weather Rev"},{"issue":"671","key":"6739_CR9","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1002\/qj.1979","volume":"139","author":"JR Eyre","year":"2013","unstructured":"Eyre JR, Hilton FI (2013) Sensitivity of analysis error covariance to the mis-specification of background error covariance. Q J R Meteorol Soc 139(671):524\u2013533","journal-title":"Q J R Meteorol Soc"},{"issue":"1","key":"6739_CR10","doi-asserted-by":"publisher","first-page":"19546","DOI":"10.3402\/tellusa.v65i0.19546","volume":"65","author":"LM Stewart","year":"2013","unstructured":"Stewart LM, Dance SL, Nichols NK (2013) Data assimilation with correlated observation errors: experiments with a 1-D shallow water model. Tellus Dyn Meteorol Oceanogr 65(1):19546","journal-title":"Tellus Dyn Meteorol Oceanogr"},{"issue":"713","key":"6739_CR11","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1002\/qj.3130","volume":"144","author":"T Janji\u0107","year":"2018","unstructured":"Janji\u0107 T, Bormann N, Bocquet M, Carton JA, Cohn SE, Dance SL, Losa SN, Nichols NK, Potthast R, Waller JA, Weston P (2018) On the representation error in data assimilation. Q J R Meteorol Soc 144(713):1257\u20131278","journal-title":"Q J R Meteorol Soc"},{"issue":"1\/2","key":"6739_CR12","doi-asserted-by":"publisher","first-page":"32","DOI":"10.2307\/2331939","volume":"20A","author":"J Wishart","year":"1928","unstructured":"Wishart J (1928) The generalised product moment distribution in samples from a normal multivariate population. Biometrika 20A(1\/2):32\u201352","journal-title":"Biometrika"},{"key":"6739_CR13","doi-asserted-by":"crossref","unstructured":"Tandeo P, Ailliot P, Bocquet M, Carrassi A, Miyoshi T, Pulido M, Zhen Y (2020) A review of innovation-based methods to jointly estimate model and observation error covariance matrices in ensemble data assimilation. Monthly Weather Rev 1\u201368","DOI":"10.1175\/MWR-D-19-0240.1"},{"key":"6739_CR14","unstructured":"Fisher M (2003) Background error covariance modelling. In: Seminar on Recent developments in data assimilation for atmosphere and ocean (Shinfield Park, Reading, 8-12 September). ECMWF"},{"issue":"9","key":"6739_CR15","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1175\/1520-0485(1989)019<1333:AGODAS>2.0.CO;2","volume":"19","author":"J Derber","year":"1989","unstructured":"Derber J, Rosati A (1989) A global oceanic data assimilation system. J Phys Oceanogr 19(9):1333\u20131347","journal-title":"J Phys Oceanogr"},{"key":"6739_CR16","unstructured":"Sol\u00eds M (2014) Conditional covariance estimation for dimension reduction and sensitivity analysis. PhD thesis, Universit\u00e9 de Toulouse"},{"issue":"685","key":"6739_CR17","doi-asserted-by":"publisher","first-page":"2420","DOI":"10.1002\/qj.2306","volume":"140","author":"PP Weston","year":"2014","unstructured":"Weston PP, Bell W, Eyre JR (2014) Accounting for correlated error in the assimilation of high-resolution sounder data. Q J R Meteorol Soc 140(685):2420\u20132429","journal-title":"Q J R Meteorol Soc"},{"issue":"554","key":"6739_CR18","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1002\/qj.49712555417","volume":"125","author":"G Gaspari","year":"1999","unstructured":"Gaspari G, Cohn SE (1999) Construction of correlation functions in two and three dimensions. Q J R Meteorol Soc 125(554):723\u2013757","journal-title":"Q J R Meteorol Soc"},{"issue":"651","key":"6739_CR19","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1002\/qj.643","volume":"136","author":"I Mirouze","year":"2010","unstructured":"Mirouze I, Weaver A (2010) Representation of correlation functions in variational assimilation using an implicit diffusion operator. Q J R Meteorol Soc 136(651):1421\u20131443","journal-title":"Q J R Meteorol Soc"},{"issue":"C5","key":"6739_CR20","doi-asserted-by":"publisher","first-page":"10143","DOI":"10.1029\/94JC00572","volume":"99","author":"G Evensen","year":"1994","unstructured":"Evensen G (1994) Sequential data assimilation with a nonlinear quasi-geostrophic model using Monte Carlo methods to forecast error statistics. J Geophys Res Oceans 99(C5):10143\u201310162","journal-title":"J Geophys Res Oceans"},{"issue":"9","key":"6739_CR21","doi-asserted-by":"publisher","first-page":"2544","DOI":"10.3390\/s20092544","volume":"20","author":"M Lin","year":"2020","unstructured":"Lin M, Yoon J, Kim B (2020) Self-driving car location estimation based on a particle-aided unscented kalman filter. Sensors 20(9):2544","journal-title":"Sensors"},{"key":"6739_CR22","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.jcp.2018.10.042","volume":"379","author":"R Arcucci","year":"2018","unstructured":"Arcucci R, Mottet L, Pain C, Guo Y-K (2018) Optimal reduced space for variational data assimilation. J Comput Phys 379:51\u201369","journal-title":"J Comput Phys"},{"issue":"574","key":"6739_CR23","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1002\/qj.49712757417","volume":"127","author":"G Desroziers","year":"2001","unstructured":"Desroziers G, Ivanov S (2001) Diagnosis and adaptive tuning of observation-error parameters in a variational assimilation. Q J R Meteorol Soc 127(574):1433\u20131452","journal-title":"Q J R Meteorol Soc"},{"issue":"613","key":"6739_CR24","doi-asserted-by":"publisher","first-page":"3385","DOI":"10.1256\/qj.05.108","volume":"131","author":"G Desroziers","year":"2005","unstructured":"Desroziers G, Berre L, Chapnik B, Poli P (2005) Diagnosis of observation, background and analysis-error statistics in observation space. Q J R Meteorol Soc 131(613):3385\u20133396","journal-title":"Q J R Meteorol Soc"},{"issue":"15","key":"6739_CR25","doi-asserted-by":"publisher","first-page":"1770","DOI":"10.3390\/rs11151770","volume":"11","author":"Y-A Liu","year":"2019","unstructured":"Liu Y-A, Li Z, Huang M (2019) Towards a data-derived observation error covariance matrix for satellite measurements. Remote Sens 11(15):1770","journal-title":"Remote Sens"},{"issue":"11","key":"6739_CR26","doi-asserted-by":"publisher","first-page":"2033","DOI":"10.1007\/s00477-019-01743-6","volume":"33","author":"S Cheng","year":"2019","unstructured":"Cheng S, Argaud J-P, Iooss B, Lucor D, Pon\u00e7ot A (2019) Background error covariance iterative updating with invariant observation measures for data assimilation. Stoch Env Res Risk Assess 33(11):2033\u20132051","journal-title":"Stoch Env Res Risk Assess"},{"issue":"651","key":"6739_CR27","doi-asserted-by":"publisher","first-page":"1644","DOI":"10.1002\/qj.652","volume":"136","author":"E Kalnay","year":"2010","unstructured":"Kalnay E, Yang S-C (2010) Accelerating the spin-up of ensemble Kalman filtering. Q J R Meteorol Soc 136(651):1644\u20131651","journal-title":"Q J R Meteorol Soc"},{"issue":"694","key":"6739_CR28","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1002\/qj.2650","volume":"142","author":"R M\u00e9nard","year":"2016","unstructured":"M\u00e9nard R (2016) Error covariance estimation methods based on analysis residuals: theoretical foundation and convergence properties derived from simplified observation networks. Q J R Meteorol Soc 142(694):257\u2013273","journal-title":"Q J R Meteorol Soc"},{"issue":"715","key":"6739_CR29","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.1002\/qj.3395","volume":"144","author":"K Bathmann","year":"2018","unstructured":"Bathmann K (2018) Justification for estimating observation-error covariances with the Desroziers diagnostic. Q J R Meteorol Soc 144(715):1965\u20131974","journal-title":"Q J R Meteorol Soc"},{"issue":"1","key":"6739_CR30","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1175\/1520-0493(1992)120<0178:TLICAP>2.0.CO;2","volume":"120","author":"R Daley","year":"1992","unstructured":"Daley R (1992) The lagged innovation covariance: a performance diagnostic for atmospheric data assimilation. Mon Weather Rev 120(1):178\u2013196","journal-title":"Mon Weather Rev"},{"key":"6739_CR31","doi-asserted-by":"crossref","unstructured":"Rumelhart DE, Hinton GE, Williams RJ (1985) Learning internal representations by error propagation. Technical report, California Univ San Diego La Jolla Inst for Cognitive Science","DOI":"10.21236\/ADA164453"},{"key":"6739_CR32","unstructured":"Yin W, Kann K, Yu M, Sch\u00fctze H (2017) Comparative study of CNN and RNN for natural language processing. ArXiv, arXiv:1702.01923"},{"key":"6739_CR33","doi-asserted-by":"publisher","first-page":"25","DOI":"10.28991\/esj-2021-01254","volume":"5","author":"A Sarabu","year":"2021","unstructured":"Sarabu A, Santra A (2021) Human action recognition in videos using convolution long short-term memory network with spatio-temporal networks. Emerg Sci J 5:25\u201333","journal-title":"Emerg Sci J"},{"issue":"7","key":"6739_CR34","doi-asserted-by":"publisher","first-page":"076606","DOI":"10.1063\/5.0012853","volume":"32","author":"S Pawar","year":"2020","unstructured":"Pawar S, Ahmed SE, San O, Rasheed A, Navon IM (2020) Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows. Phys Fluids 32(7):076606","journal-title":"Phys Fluids"},{"key":"6739_CR35","doi-asserted-by":"crossref","unstructured":"Arcucci R, Zhu J, Hu S, Guo Y-K (2021) Deep data assimilation: integrating deep learning with data assimilation. Appl Sci 11(3)","DOI":"10.3390\/app11031114"},{"issue":"2194","key":"6739_CR36","doi-asserted-by":"publisher","first-page":"20200089","DOI":"10.1098\/rsta.2020.0089","volume":"379","author":"AJ Geer","year":"2021","unstructured":"Geer AJ (2021) Learning earth system models from observations: machine learning or data assimilation? Philos Trans R Soc A Math Phys Eng Sci 379(2194):20200089","journal-title":"Philos Trans R Soc A Math Phys Eng Sci"},{"key":"6739_CR37","doi-asserted-by":"publisher","first-page":"132615","DOI":"10.1016\/j.physd.2020.132615","volume":"412","author":"CQ Casas","year":"2020","unstructured":"Casas CQ, Arcucci R, Wu P, Pain C, Guo Y-K (2020) A reduced order deep data assimilation model. Phys D 412:132615","journal-title":"Phys D"},{"issue":"2194","key":"6739_CR38","doi-asserted-by":"publisher","first-page":"20200086","DOI":"10.1098\/rsta.2020.0086","volume":"379","author":"J Brajard","year":"2021","unstructured":"Brajard J, Carrassi A, Bocquet M, Bertino L (2021) Combining data assimilation and machine learning to infer unresolved scale parametrization. Philos Trans R Soc A Math Phys Eng Sci 379(2194):20200086","journal-title":"Philos Trans R Soc A Math Phys Eng Sci"},{"key":"6739_CR39","doi-asserted-by":"crossref","unstructured":"Liu K, Ok K, Vega-Brown W, Roy N (2018) Deep inference for covariance estimation: Learning gaussian noise models for state estimation. In: Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), pp 1436\u20131443. IEEE","DOI":"10.1109\/ICRA.2018.8461047"},{"issue":"705","key":"6739_CR40","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1002\/qj.3048","volume":"143","author":"D Dreano","year":"2017","unstructured":"Dreano D, Tandeo P, Pulido M, Ait-El-Fquih B, Chonavel T, Hoteit I (2017) Estimating model error covariances in nonlinear state-space models using Kalman smoothing and the expectation-maximisation algorithm. Q J R Meteorol Soc 143(705):1877\u20131885","journal-title":"Q J R Meteorol Soc"},{"key":"6739_CR41","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1090\/S0273-0979-00-00865-X","volume":"37","author":"W Fulton","year":"2000","unstructured":"Fulton W (2000) Eigenvalues, invariant factors, highest weights, and schubert calculus. Bull Am Math Soc 37:209\u2013250","journal-title":"Bull Am Math Soc"},{"issue":"12","key":"6739_CR42","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1016\/j.camwa.2014.01.024","volume":"67","author":"A Cioaca","year":"2014","unstructured":"Cioaca A, Sandu A (2014) Low-rank approximations for computing observation impact in 4D-Var data assimilation. Comput Math Appl 67(12):2112\u20132126","journal-title":"Comput Math Appl"},{"issue":"703","key":"6739_CR43","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1002\/qj.2982","volume":"143","author":"RN Bannister","year":"2017","unstructured":"Bannister RN (2017) A review of operational methods of variational and ensemble-variational data assimilation. Q J R Meteorol Soc 143(703):607\u2013633","journal-title":"Q J R Meteorol Soc"},{"issue":"8","key":"6739_CR44","doi-asserted-by":"publisher","first-page":"3227","DOI":"10.1007\/s00521-017-3264-5","volume":"31","author":"H Bazargan","year":"2019","unstructured":"Bazargan H, Adibifard M (2019) A stochastic well-test analysis on transient pressure data using iterative ensemble Kalman filter. Neural Comput Appl 31(8):3227\u20133243","journal-title":"Neural Comput Appl"},{"issue":"1","key":"6739_CR45","doi-asserted-by":"publisher","first-page":"187","DOI":"10.5194\/npg-21-187-2014","volume":"21","author":"Y Michel","year":"2014","unstructured":"Michel Y (2014) Diagnostics on the cost-function in variational assimilations for meteorological models. Nonlinear Process Geophys 21(1):187\u2013199","journal-title":"Nonlinear Process Geophys"},{"issue":"11","key":"6739_CR46","doi-asserted-by":"publisher","first-page":"2596","DOI":"10.1175\/JTECH-D-13-00018.1","volume":"30","author":"R Hoffman","year":"2013","unstructured":"Hoffman R, Ardizzone JV, Leidner S, Smith D, Atlas R (2013) Error estimates for ocean surface winds: applying desroziers diagnostics to the cross-calibrated, multiplatform analysis of wind speed. J Atmos Oceanic Tech 30(11):2596\u20132603","journal-title":"J Atmos Oceanic Tech"},{"issue":"601","key":"6739_CR47","doi-asserted-by":"publisher","first-page":"2253","DOI":"10.1256\/qj.03.26","volume":"130","author":"B Chapnik","year":"2004","unstructured":"Chapnik B, Desroziers G, Rabier F, Talagrand O (2004) Property and first application of an error-statistics tuning method in variational assimilation. Q J R Meteorol Soc 130(601):2253\u20132275","journal-title":"Q J R Meteorol Soc"},{"key":"6739_CR48","unstructured":"Talagrand O (1998) A posteriori evaluation and verification of analysis and assimilation algorithms. In: Workshop on diagnosis of data assimilation systems, pp 17\u201328, Shinfield Park, Reading"},{"issue":"677","key":"6739_CR49","doi-asserted-by":"publisher","first-page":"2033","DOI":"10.1002\/qj.2104","volume":"139","author":"S Migliorini","year":"2013","unstructured":"Migliorini S (2013) Information-based data selection for ensemble data assimilation. Q J R Meteorol Soc 139(677):2033\u20132054","journal-title":"Q J R Meteorol Soc"},{"issue":"8","key":"6739_CR50","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"issue":"2","key":"6739_CR51","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157\u2013166","journal-title":"IEEE Trans Neural Netw"},{"key":"6739_CR52","unstructured":"Lorenz E (1995) Predictability: a problem partly solved. In: Seminar on predictability, 4\u20138 September 1995, vol 1, pp 1\u201318, Shinfield Park, Reading. ECMWF, ECMWF"},{"issue":"10","key":"6739_CR53","doi-asserted-by":"publisher","first-page":"103121","DOI":"10.1063\/5.0019309","volume":"30","author":"S Ouala","year":"2020","unstructured":"Ouala S, Nguyen D, Drumetz L, Chapron B, Pascual A, Collard F, Gaultier L, Fablet R (2020) Learning latent dynamics for partially observed chaotic systems. Chaos Interdiscip J Nonlinear Sci 30(10):103121","journal-title":"Chaos Interdiscip J Nonlinear Sci"},{"key":"6739_CR54","doi-asserted-by":"crossref","unstructured":"Descombes G, Aulign\u00e9 T, Vandenberghe F, Barker D, Barr\u00e9 J (2015) Generalized background error covariance matrix model (GEN_BE v2. 0). Geosci Model Develop 8(3):669\u2013696","DOI":"10.5194\/gmd-8-669-2015"},{"key":"6739_CR55","doi-asserted-by":"publisher","first-page":"4566","DOI":"10.1109\/ACCESS.2020.3045078","volume":"9","author":"X Liu","year":"2020","unstructured":"Liu X, Xie L, Wang Y, Zou J, Xiong J, Ying Z, Vasilakos AV (2020) Privacy and security issues in deep learning: a survey. IEEE Access 9:4566\u20134593","journal-title":"IEEE Access"},{"key":"6739_CR56","doi-asserted-by":"crossref","unstructured":"Cheng S, Argaud JP, Iooss B, Pon\u00e7ot A, Lucor D.(2021) A graph clustering approach to localization for adaptive covariance tuning in data assimilation based on state-observation mapping. Math Geosci, 1\u201330","DOI":"10.1007\/s11004-021-09951-z"},{"key":"6739_CR57","doi-asserted-by":"publisher","first-page":"101405","DOI":"10.1016\/j.jocs.2021.101405","volume":"53","author":"S Cheng","year":"2021","unstructured":"Cheng S, Lucor D, Argaud J-P (2021) Observation data compression for variational assimilation of dynamical systems. J Comput Sci 53:101405","journal-title":"J Comput Sci"},{"key":"6739_CR58","doi-asserted-by":"crossref","unstructured":"Amendola M, Arcucci R, Mottet L, Casas CQ, Fan S, Pain C, Linden P, Guo Y-K (2020) Data assimilation in the latent space of a neural network. ArXiv, arXiv:2012.12056","DOI":"10.1007\/978-3-030-77977-1_30"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06739-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06739-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06739-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T08:04:56Z","timestamp":1676102696000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06739-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,20]]},"references-count":58,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["6739"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06739-4","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2021,12,20]]},"assertion":[{"value":"26 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest statement"}},{"value":"Code for the proposed LSTM-based covariance specification, together with DI01, D05 methods, for both Lorenz and shallow water models is available at .","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"S.Cheng: Conceptualization, Methodology, Software, Writing - Original draft preparation M.Qiu: Methodology, Software, Writing - Original draft preparation","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Contribution statement"}}]}}