{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T02:04:28Z","timestamp":1775873068457,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Lawrence Berkeley National Lab LDRD","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We present an approach that uses a deep learning model, in particular, a MultiLayer Perceptron, for estimating the missing values of a variable in multivariate time series data. We focus on filling a long continuous gap (e.g., multiple months of missing daily observations) rather than on individual randomly missing observations. Our proposed gap filling algorithm uses an automated method for determining the optimal MLP model architecture, thus allowing for optimal prediction performance for the given time series. We tested our approach by filling gaps of various lengths (three months to three years) in three environmental datasets with different time series characteristics, namely daily groundwater levels, daily soil moisture, and hourly Net Ecosystem Exchange. We compared the accuracy of the gap-filled values obtained with our approach to the widely used R-based time series gap filling methods  and . The results indicate that using an MLP for filling a large gap leads to better results, especially when the data behave nonlinearly. Thus, our approach enables the use of datasets that have a large gap in one variable, which is common in many long-term environmental monitoring observations.<\/jats:p>","DOI":"10.1007\/s00521-022-08165-6","type":"journal-article","created":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T17:19:01Z","timestamp":1671815941000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Long-term missing value imputation for time series data using deep neural networks"],"prefix":"10.1007","author":[{"given":"Jangho","family":"Park","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8627-1992","authenticated-orcid":false,"given":"Juliane","family":"M\u00fcller","sequence":"additional","affiliation":[]},{"given":"Bhavna","family":"Arora","sequence":"additional","affiliation":[]},{"given":"Boris","family":"Faybishenko","sequence":"additional","affiliation":[]},{"given":"Gilberto","family":"Pastorello","sequence":"additional","affiliation":[]},{"given":"Charuleka","family":"Varadharajan","sequence":"additional","affiliation":[]},{"given":"Reetik","family":"Sahu","sequence":"additional","affiliation":[]},{"given":"Deborah","family":"Agarwal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,23]]},"reference":[{"issue":"2","key":"8165_CR1","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s00521-009-0295-6","volume":"19","author":"PJ Garc\u00eda-Laencina","year":"2010","unstructured":"Garc\u00eda-Laencina PJ, Sancho-G\u00f3mez J-L, Figueiras-Vidal AR (2010) Pattern classification with missing data: a review. Neural Comput Appl 19(2):263\u2013282","journal-title":"Neural Comput Appl"},{"issue":"1\u20132","key":"8165_CR2","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s00704-012-0723-x","volume":"112","author":"C Yozgatligil","year":"2013","unstructured":"Yozgatligil C, Aslan S, Iyigun C, Batmaz I (2013) Comparison of missing value imputation methods in time series: the case of Turkish meteorological data. Theoret Appl Climatol 112(1\u20132):143\u2013167","journal-title":"Theoret Appl Climatol"},{"issue":"4","key":"8165_CR3","doi-asserted-by":"publisher","first-page":"420","DOI":"10.2166\/nh.2009.001","volume":"40","author":"AM Kalteh","year":"2009","unstructured":"Kalteh AM, Hjorth P (2009) Imputation of missing values in a precipitation-runoff process database. Hydrol Res 40(4):420\u2013432","journal-title":"Hydrol Res"},{"key":"8165_CR4","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.advwatres.2017.10.002","volume":"110","author":"M-AB Aissia","year":"2017","unstructured":"Aissia M-AB, Chebana F, Ouarda TB (2017) Multivariate missing data in hydrology-review and applications. Adv Water Resour 110:299\u2013309","journal-title":"Adv Water Resour"},{"key":"8165_CR5","doi-asserted-by":"crossref","unstructured":"Gu C, Anderson W, Maggi F (2012) Riparian biogeochemical hot moments induced by stream fluctuations. Water Resour Res 48(9)","DOI":"10.1029\/2011WR011720"},{"key":"8165_CR6","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1016\/j.scitotenv.2018.08.251","volume":"649","author":"B Arora","year":"2019","unstructured":"Arora B, Wainwright HM, Dwivedi D, Vaughn LJ, Curtis JB, Torn MS, Dafflon B, Hubbard SS (2019) Evaluating temporal controls on greenhouse gas (ghg) fluxes in an arctic tundra environment: An entropy-based approach. Sci Total Environ 649:284\u2013299","journal-title":"Sci Total Environ"},{"key":"8165_CR7","doi-asserted-by":"crossref","unstructured":"Thi-Thu-Hong\u00a0Phan B, Caillault EP, Bigand A (2019) edtwbi: Effective imputation method for univariate time series. In: Advanced Computational Methods for Knowledge Engineering: Proceedings of the 6th International Conference on Computer Science, Applied Mathematics and Applications, ICCSAMA 2019, vol. 1121, p 121 . Springer Nature","DOI":"10.1007\/978-3-030-38364-0_11"},{"key":"8165_CR8","unstructured":"Moritz S, Sard\u00e1 A, Bartz-Beielstein T, Zaefferer M, Stork J (2015) Comparison of different methods for univariate time series imputation in R. arXiv preprint arXiv:1510.03924"},{"issue":"1","key":"8165_CR9","doi-asserted-by":"publisher","first-page":"207","DOI":"10.32614\/RJ-2017-009","volume":"9","author":"S Moritz","year":"2017","unstructured":"Moritz S, Bartz-Beielstein T (2017) imputeTS: time series missing value imputation in R. The R J 9(1):207\u2013218","journal-title":"The R J"},{"key":"8165_CR10","doi-asserted-by":"crossref","unstructured":"Phan T-T-H (2020) Machine learning for univariate time series imputation. In: 2020 International Conference on Multimedia Analysis and Pattern Recognition (MAPR), pp 1\u20136","DOI":"10.1109\/MAPR49794.2020.9237768"},{"issue":"251\u2013260","key":"8165_CR11","first-page":"48","volume":"87","author":"GEAPA Batista","year":"2002","unstructured":"Batista GEAPA, Monard MC (2002) A study of K-nearest neighbour as an imputation method. Hybrid Intell Syst 87(251\u2013260):48","journal-title":"Hybrid Intell Syst"},{"issue":"1","key":"8165_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-24271-9","volume":"8","author":"Z Che","year":"2018","unstructured":"Che Z, Purushotham S, Cho K, Sontag D, Liu Y (2018) Recurrent neural networks for multivariate time series with missing values. Sci Rep 8(1):1\u201312","journal-title":"Sci Rep"},{"key":"8165_CR13","unstructured":"Cao W, Wang D, Li J, Zhou H, Li L, Li Y (2018) Brits: bidirectional recurrent imputation for time series. In: NeurIPS"},{"key":"8165_CR14","unstructured":"Luo Y, Cai X, Zhang Y, Xu J (2018) Multivariate time series imputation with generative adversarial networks. In: Advances in Neural Information Processing Systems, pp 1596\u20131607"},{"key":"8165_CR15","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.ins.2020.11.035","volume":"551","author":"Y Zhang","year":"2021","unstructured":"Zhang Y, Zhou B, Cai X, Guo W, Ding X, Yuan X (2021) Missing value imputation in multivariate time series with end-to-end generative adversarial networks. Inf Sci 551:67\u201382","journal-title":"Inf Sci"},{"key":"8165_CR16","doi-asserted-by":"crossref","unstructured":"Lingras P, Zhong M, Sharma S (2008) Evolutionary regression and neural imputations of missing values. In: Soft Computing Applications in Industry, pp 151\u2013163","DOI":"10.1007\/978-3-540-77465-5_8"},{"issue":"6","key":"8165_CR17","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1080\/03081060701698250","volume":"30","author":"M Zhong","year":"2007","unstructured":"Zhong M, Sharma S, Lingras P (2007) Rationalizing reliable imputation durations of genetically designed time delay neural network and locally weighted regression models. Transp Plan Technol 30(6):609\u2013626","journal-title":"Transp Plan Technol"},{"key":"8165_CR18","first-page":"1","volume":"10","author":"A Mahabbati","year":"2020","unstructured":"Mahabbati A, Beringer J, Leopold M, McHugh I, Cleverly J, Isaac P, Izady A (2020) A comparison of gap-filling algorithms for eddy covariance fluxes and their drivers. Geosci Instrum Methods Data Syst Discuss 10:1\u201331","journal-title":"Geosci Instrum Methods Data Syst Discuss"},{"key":"8165_CR19","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"issue":"3","key":"8165_CR20","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1111\/gcb.14845","volume":"26","author":"Y Kim","year":"2020","unstructured":"Kim Y, Johnson MS, Knox SH, Black TA, Dalmagro HJ, Kang M, Kim J, Baldocchi D (2020) Gap-filling approaches for eddy covariance methane fluxes: a comparison of three machine learning algorithms and a traditional method with principal component analysis. Glob Change Biol 26(3):1499\u20131518","journal-title":"Glob Change Biol"},{"issue":"3","key":"8165_CR21","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A Waibel","year":"1989","unstructured":"Waibel A, Hanazawa T, Hinton G, Shikano K, Lang KJ (1989) Phoneme recognition using time-delay neural networks. IEEE Trans Acoust Speech Signal Process 37(3):328\u2013339","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"8165_CR22","doi-asserted-by":"crossref","unstructured":"M\u00fcller J, Park J, Sahu R, Varadharajan C, Arora B, Faybishenko B, Agarwal D (2020) Surrogate optimization of deep neural networks for groundwater predictions. J Glob Optim 10\u2013100710898020009120","DOI":"10.1007\/s10898-020-00912-0"},{"key":"8165_CR23","unstructured":"Junger W Ponce de Leon, A.: Package \u2019mtsdi\u2019"},{"key":"8165_CR24","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. ICML\u201910, pp 807\u2013814. Omnipress, Madison, WI, USA"},{"key":"8165_CR25","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"issue":"6088","key":"8165_CR26","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533\u2013536","journal-title":"Nature"},{"issue":"1","key":"8165_CR27","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"8165_CR28","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT press Cambridge, Cambridge"},{"key":"8165_CR29","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-05318-5_1","volume-title":"Automated machine learning","author":"M Feurer","year":"2019","unstructured":"Feurer M, Hutter F (2019) Hyperparameter optimization. Automated machine learning. Springer, Berlin, pp 3\u201333"},{"key":"8165_CR30","unstructured":"Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13(2)"},{"key":"8165_CR31","doi-asserted-by":"crossref","unstructured":"Larochelle H, Erhan D, Courville A, Bergstra J, Bengio Y (2007) An empirical evaluation of deep architectures on problems with many factors of variation. In: Proceedings of the 24th International Conference on Machine Learning, pp 473\u2013480","DOI":"10.1145\/1273496.1273556"},{"key":"8165_CR32","unstructured":"Snoek J, Larochelle H, Adams RP (2012) Practical Bayesian optimization of machine learning algorithms. arXiv preprint arXiv:1206.2944"},{"key":"8165_CR33","doi-asserted-by":"crossref","unstructured":"Xie L, Yuille A (2017) Genetic CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1379\u20131388","DOI":"10.1109\/ICCV.2017.154"},{"key":"8165_CR34","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3389\/frwa.2020.573034","volume":"2","author":"RK Sahu","year":"2020","unstructured":"Sahu RK, M\u00fcller J, Park J, Varadharajan C, Arora B, Faybishenko B, Agarwal D (2020) Impact of input feature selection on groundwater level prediction from a multi-layer perceptron neural network. Front Water 2:46","journal-title":"Front Water"},{"key":"8165_CR35","unstructured":"\u0160im\u016dnek J, \u0160ejna M, Saito H, Sakai M, van Genuchten MT (2013) The HYDRUS-1D Software Package for Simulating the One-Dimensional Movement of Water, Heat, and Multiple Solutes in Variably-Saturated Media, Version 4.17, edn. Riverside, California, Riverside, California"},{"issue":"2","key":"8165_CR36","doi-asserted-by":"publisher","first-page":"782","DOI":"10.2136\/vzj2007.0074","volume":"7","author":"J \u0160im\u016dnek","year":"2008","unstructured":"\u0160im\u016dnek J, van Genuchten MT (2008) Modeling nonequilibrium flow and transport processes using hydrus. Vadose Zone J 7(2):782\u2013797","journal-title":"Vadose Zone J"},{"key":"8165_CR37","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1016\/j.scitotenv.2015.01.048","volume":"512","author":"B Arora","year":"2015","unstructured":"Arora B, Mohanty BP, McGuire JT (2015) An integrated Markov chain Monte Carlo algorithm for upscaling hydrological and geochemical parameters from column to field scale. Sci Total Environ 512:428\u2013443","journal-title":"Sci Total Environ"},{"key":"8165_CR38","doi-asserted-by":"publisher","first-page":"109920","DOI":"10.1016\/j.jenvman.2019.109920","volume":"261","author":"S Baek","year":"2020","unstructured":"Baek S, Ligaray M, Pachepsky Y, Chun JA, Yoon K-S, Park Y, Cho KH (2020) Assessment of a green roof practice using the coupled SWMM and HYDRUS models. J Environ Manage 261:109920","journal-title":"J Environ Manage"},{"issue":"1","key":"8165_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-020-0534-3","volume":"7","author":"G Pastorello","year":"2020","unstructured":"Pastorello G, Trotta C, Canfora E, Chu H, Christianson D, Cheah Y-W, Poindexter C, Chen J, Elbashandy A, Humphrey M (2020) The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data. Scientific Data 7(1):1\u201327","journal-title":"Scientific Data"},{"key":"8165_CR40","unstructured":"United States Department\u00a0of Energy, T.O.o.S.: FLUXNET2015 Dataset. https:\/\/fluxnet.org\/data\/fluxnet2015-dataset\/. Last accessed: 2021-1-1"},{"key":"8165_CR41","doi-asserted-by":"publisher","DOI":"10.18140\/flx\/1440083","author":"K Novick","year":"2016","unstructured":"Novick K, Phillips R (2016) FLUXNET2015 US-MMS morgan monroe state forest. FLUXNET; Indiana Univ. https:\/\/doi.org\/10.18140\/flx\/1440083","journal-title":"FLUXNET; Indiana Univ"},{"key":"8165_CR42","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in PyTorch. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA"},{"issue":"4","key":"8165_CR43","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF00344251","volume":"36","author":"K Fukushima","year":"1980","unstructured":"Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36(4):193\u2013202","journal-title":"Biol Cybern"},{"issue":"4","key":"8165_CR44","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541\u2013551","journal-title":"Neural Comput"},{"issue":"11","key":"8165_CR45","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"8165_CR46","unstructured":"Triebe O, Laptev N, Rajagopal R (2019) Ar-net: A simple auto-regressive neural network for time-series. arXiv preprint arXiv:1911.12436"},{"key":"8165_CR47","unstructured":"Triebe O, Hewamalage H, Pilyugina P, Laptev N, Bergmeir C, Rajagopal R (2021) Neuralprophet: Explainable forecasting at scale. arXiv preprint arXiv:2111.15397"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08165-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-08165-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08165-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T17:21:16Z","timestamp":1671816076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-08165-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,23]]},"references-count":47,"alternative-id":["8165"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-08165-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,23]]},"assertion":[{"value":"5 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There is no conflict of interest to disclose. This research does not involve Human Participants and\/or Animals. All authors are satisfied with the submitted version of the manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}