{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:04:10Z","timestamp":1781283850267,"version":"3.54.1"},"reference-count":58,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2020,9,25]],"date-time":"2020-09-25T00:00:00Z","timestamp":1600992000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000844","name":"European Space Agency","doi-asserted-by":"publisher","award":["4000130730\/20\/I-NB"],"award-info":[{"award-number":["4000130730\/20\/I-NB"]}],"id":[{"id":"10.13039\/501100000844","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>An efficient combination of remotely-sensed data and in situ measurements is needed to obtain accurate 3D ocean state estimates, representing a fundamental step to describe ocean dynamics and its role in the Earth climate system and marine ecosystems. Observations can either be assimilated in ocean general circulation models or used to feed data-driven reconstructions and diagnostic models. Here we describe an innovative deep learning algorithm that projects sea surface satellite data at depth after training with sparse co-located in situ vertical profiles. The technique is based on a stacked Long Short-Term Memory neural network, coupled to a Monte-Carlo dropout approach, and is applied here to the measurements collected between 2010 and 2018 over the North Atlantic Ocean. The model provides hydrographic vertical profiles and associated uncertainties from corresponding remotely sensed surface estimates, outperforming similar reconstructions from simpler statistical algorithms and feed-forward networks.<\/jats:p>","DOI":"10.3390\/rs12193151","type":"journal-article","created":{"date-parts":[[2020,9,25]],"date-time":"2020-09-25T08:57:32Z","timestamp":1601024252000},"page":"3151","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["A Deep Learning Network to Retrieve Ocean Hydrographic Profiles from Combined Satellite and In Situ Measurements"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3416-7189","authenticated-orcid":false,"given":"Bruno","family":"Buongiorno Nardelli","sequence":"first","affiliation":[{"name":"Consiglio Nazionale delle Ricerche, Istituto di Scienze Marine (CNR-ISMAR), 80133 Naples, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1073\/pnas.1609435114","article-title":"Mesoscale ocean fronts enhance carbon export due to gravitational sinking and subduction","volume":"114","author":"Stukel","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"McWilliams, J.C. (2019). A survey of submesoscale currents. Geosci. Lett., 6.","DOI":"10.1186\/s40562-019-0133-3"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1002\/2017JC013298","article-title":"Patterns of vertical velocity induced by Eddy Distortion in an ocean model","volume":"123","author":"Pilo","year":"2018","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/wcc.535","article-title":"Data assimilation in the geosciences: An overview of methods, issues, and perspectives","volume":"9","author":"Carrassi","year":"2018","journal-title":"Wiley Interdiscip. Rev. Clim. Chang."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fmars.2019.00090","article-title":"Synthesis of ocean observations using data assimilation for operational, real-time and reanalysis systems: A more complete picture of the state of the ocean","volume":"6","author":"Moore","year":"2019","journal-title":"Front. Mar. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Stammer, D., Balmaseda, M., Heimbach, P., K\u00f6hl, A., and Weaver, A. (2016). Ocean data assimilation in support of climate applications: Status and perspectives. Ann. Rev. Mar. Sci., 8.","DOI":"10.1146\/annurev-marine-122414-034113"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3071","DOI":"10.5194\/gmd-8-3071-2015","article-title":"ECCO Version 4: An integrated framework for non-linear inverse modeling and global ocean state estimation","volume":"8","author":"Forget","year":"2015","journal-title":"Geosci. Model Dev."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rio, M.-H., Santoleri, R., Bourdalle-Badie, R., Griffa, A., Piterbarg, L., and Taburet, G. (2016). Improving the altimeter-derived surface currents using high-resolution sea surface temperature data: A feasability study based on model outputs. J. Atmos. Ocean. Technol., 2769\u20132784.","DOI":"10.1175\/JTECH-D-16-0017.1"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1175\/JTECH-D-15-0163.1","article-title":"Dynamic mapping of along-track ocean altimetry: Method and performance from observing system simulation experiments","volume":"33","author":"Ubelmann","year":"2016","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ciani, D., Rio, M., Buongiorno Nardelli, B., Etienne, H., and Santoleri, R. (2020). Improving the altimeter-derived surface currents using sea surface temperature (SST) data: A sensitivity study to SST products. Remote Sens., 12.","DOI":"10.3390\/rs12101601"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.jmarsys.2003.11.022","article-title":"Combining argo and remote-sensing data to estimate the ocean three-dimensional temperature fields\u2014A first approach based on simulated observations","volume":"46","author":"Guinehut","year":"2004","journal-title":"J. Mar. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"845","DOI":"10.5194\/os-8-845-2012","article-title":"High resolution 3-D temperature and salinity fields derived from in situ and satellite observations","volume":"8","author":"Guinehut","year":"2012","journal-title":"Ocean Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1080\/07055900.2017.1399858","article-title":"Mesoscale reproducibility in regional ocean modelling with a three-dimensional stratification estimate based on aviso-argo data","volume":"56","author":"Uchiyama","year":"2018","journal-title":"Atmos. Ocean"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3171","DOI":"10.1002\/2015JC011491","article-title":"Decadal-Scale thermohaline variability in the atlantic sector of the southern ocean","volume":"121","author":"Hutchinson","year":"2016","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1175\/2010JTECHO790.1","article-title":"Estimating the Four-Dimensional structure of the southern ocean using satellite altimetry","volume":"28","author":"Meijers","year":"2011","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"21869","DOI":"10.1029\/2000JC900097","article-title":"Vertical structure and transport on a transect across the North Atlantic current near 42\u00b0N: Time Series and Mean","volume":"105","author":"Meinen","year":"2000","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"10042","DOI":"10.1002\/2017JC013314","article-title":"Southern ocean mixed-layer seasonal and interannual variations from combined satellite and in situ data","volume":"122","author":"Guinehut","year":"2017","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_18","first-page":"1533","article-title":"Three Dimensional Ageostrophic Motion and Water Mass Subduction in the Southern Ocean","volume":"23","author":"Mulet","year":"2018","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"885","DOI":"10.5194\/os-8-885-2012","article-title":"Towards high resolution mapping of 3-d mesoscale dynamics from observations","volume":"8","author":"Guinehut","year":"2012","journal-title":"Ocean Sci."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Jeong, Y., Hwang, J., Park, J., Jang, C.J., and Jo, Y.H. (2019). Reconstructed 3-D ocean temperature derived from remotely sensed sea surface measurements for mixed layer depth analysis. Remote Sens., 11.","DOI":"10.3390\/rs11243018"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2655","DOI":"10.1175\/2009JTECHO669.1","article-title":"A method to estimate three-dimensional thermal structure from satellite altimetry data","volume":"26","author":"Takano","year":"2009","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.5194\/essd-12-1711-2020","article-title":"A multi-year timeseries of observation-based 3D horizontal and vertical quasi-geostrophic global ocean currents","volume":"12","year":"2020","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.dsr2.2012.04.012","article-title":"A new estimate of the global 3D geostrophic ocean circulation based on satellite data and in-situ measurements","volume":"77\u201380","author":"Mulet","year":"2012","journal-title":"Deep Sea Res. Part II Top. Stud. Oceanogr."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3245","DOI":"10.1175\/JPO-D-19-0118.1","article-title":"Reconstructing the ocean interior from high-resolution sea surface information","volume":"49","author":"Liu","year":"2019","journal-title":"J. Phys. Oceanogr."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lapeyre, G. (2017). Surface quasi-geostrophy. Fluids, 2.","DOI":"10.3390\/fluids2010007"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2424","DOI":"10.1175\/JPO-D-14-0206.1","article-title":"Estimating subsurface velocities from surface fields with idealized stratification","volume":"45","author":"LaCasce","year":"2015","journal-title":"J. Phys. Oceanogr."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1175\/JPO-D-12-0204.1","article-title":"Reconstructing the ocean\u2019s interior from surface data","volume":"43","author":"Wang","year":"2013","journal-title":"J. Phys. Oceanogr."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1002\/2013JC009176","article-title":"Diagnosis of high-resolution upper ocean dynamics from noisy sea surface temperatures","volume":"119","year":"2014","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1612","DOI":"10.1002\/2017JC013400","article-title":"Reconstruction of the 3-D dynamics from surface variables in a high-resolution simulation of North Atlantic","volume":"123","author":"Fresnay","year":"2018","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yan, H., Wang, H., Zhang, R., Chen, J., Bao, S., and Wang, G. (2020). A Dynamical-statistical approach to retrieve the ocean interior structure from surface data: SQG-mEOF-R. J. Geophys. Res. Oceans.","DOI":"10.5194\/egusphere-egu2020-5286"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.rse.2019.04.009","article-title":"Subsurface temperature estimation from remote sensing data using a clustering-neural network method","volume":"229","author":"Lu","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1175\/JTECH-D-17-0226.1","article-title":"Salinity Profile estimation in the pacific ocean from satellite surface salinity observations","volume":"36","author":"Bao","year":"2019","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1675","DOI":"10.1175\/JTECH-D-12-00013.1","article-title":"Estimation of subsurface temperature anomaly in the North Atlantic Using a self-organizing map neural network","volume":"29","author":"Wu","year":"2012","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Sammartino, M., Marullo, S., Santoleri, R., and Scardi, M. (2018). Modelling the vertical distribution of phytoplankton biomass in the mediterranean sea from satellite data: A neural network approach. Remote Sens., 10.","DOI":"10.3390\/rs10101666"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.cageo.2014.07.012","article-title":"Neural Approach to inverting complex system: Application to ocean salinity profile estimation from surface parameters","volume":"72","author":"Gueye","year":"2014","journal-title":"Comput. Geosci."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Su, H., Yang, X., Lu, W., and Yan, X.-H. (2019). Estimating subsurface thermohaline structure of the global ocean using surface remote sensing observations. Remote Sens., 11.","DOI":"10.3390\/rs11131598"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.rse.2015.01.001","article-title":"Estimation of subsurface temperature anomaly in the indian ocean during recent global surface warming hiatus from satellite measurements: A support vector machine approach","volume":"160","author":"Su","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fmars.2018.00328","article-title":"An alternative to static climatologies: Robust estimation of open ocean CO2 variables and nutrient concentrations from T, S, and O2 data using bayesian neural networks","volume":"5","author":"Bittig","year":"2018","journal-title":"Front. Mar. Sci."},{"key":"ref_39","first-page":"1","article-title":"Estimates of Water-column nutrient concentrations and carbonate system parameters in the global ocean: A novel approach based on neural networks","volume":"4","author":"Bittig","year":"2017","journal-title":"Front. Mar. Sci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1016\/j.dsr.2009.05.017","article-title":"Linear and non-linear T-S models for the Eastern North Atlantic from argo data: Role of surface salinity observations","volume":"56","author":"Mourre","year":"2009","journal-title":"Deep. Res. Part I Oceanogr. Res. Pap."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_42","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 19\u201324). Dropout As a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. Proceedings of the 33rd International Conference On Machine Learning, New York, NY, USA."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"6215","DOI":"10.1175\/JCLI-D-11-00648.1","article-title":"Daily, Global, high-resolution SST and sea ice reanalysis for 1985\u20132007 Using the OSTIA System","volume":"25","author":"Fiedler","year":"2012","journal-title":"J. Clim."},{"key":"ref_44","unstructured":"Buongiorno Nardelli, B. (2020). ESA-WOC North Atlantic Sea Surface Salinity maps from a multivariate combination of satellite and in situ surface measurements (2010\u20132018) (Version v1.0), [Data set]. Zenodo."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1175\/JTECH-D-15-0194.1","article-title":"Combining in-situ and satellite observations to retrieve salinity and density at the ocean surface","volume":"33","author":"Droghei","year":"2016","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1175\/JTECH-D-11-00099.1","article-title":"A Novel approach for the high-resolution interpolation of in situ sea surface salinity","volume":"29","year":"2012","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fmars.2018.00084","article-title":"A new global sea surface salinity and density dataset from multivariate observations (1993\u20132016)","volume":"5","author":"Droghei","year":"2018","journal-title":"Front. Mar. Sci."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"8918","DOI":"10.1002\/2014GL061773","article-title":"Beyond GOCE for the ocean circulation estimate: Synergetic use of altimetry, gravimetry, and in situ data provides new insight into geostrophic and ekman currents","volume":"41","author":"Rio","year":"2014","journal-title":"Geophys. Res. Lett."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.5194\/os-15-1601-2019","article-title":"The CORA 5.2 dataset for global in situ temperature and salinity measurements: Data description and validation","volume":"15","author":"Szekely","year":"2019","journal-title":"Ocean Sci."},{"key":"ref_50","unstructured":"Levitus, S., and Mishonov, A. (2013). World Ocean Atlas 2013. Volume 1: Temperature, NODC."},{"key":"ref_51","unstructured":"Zweng, M.M., Reagan, J.R., Antonov, J.I., Mishonov, A.V., Boyer, T.P., Garcia, H.E., Baranova, O.K., Johnson, D.R., Seidov, D., and Bidlle, M.M. (2013). World Ocean Atlas 2013, Volume 2: Salinity, NODC."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Buongiorno Nardelli, B., Cavalieri, O., Rio, M.-H., and Santoleri, R. (2006). Subsurface geostrophic velocities inference from altimeter data: Application to the Sicily Channel (Mediterranean Sea). J. Geophys. Res., 111.","DOI":"10.1029\/2005JC003191"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1762","DOI":"10.1175\/JTECH1792.1","article-title":"Methods for the reconstruction of vertical profiles from surface data: Multivariate analyses, residual GEM, and variable temporal signals in the North Pacific Ocean","volume":"22","author":"Santoleri","year":"2005","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"5609","DOI":"10.1002\/jgrc.20345","article-title":"Vortex waves and vertical motion in a mesoscale cyclonic eddy","volume":"118","year":"2013","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_55","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R.R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. arXiv."},{"key":"ref_56","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Buongiorno Nardelli, B. (2020). Developing a deep Learning network to retrieve ocean hydrographic profiles in the North Atlantic from combined satellite and in situ measurements: Test datasets. (Version v1.0), [Data set]. Zenodo.","DOI":"10.1002\/essoar.10503703.1"},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Efron, B., and Tibshirani, R.J. (1993). An Introduction to the Bootstrap, Chapman & Hall\/CRC.","DOI":"10.1007\/978-1-4899-4541-9"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/19\/3151\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:13:41Z","timestamp":1760177621000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/19\/3151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,25]]},"references-count":58,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2020,10]]}},"alternative-id":["rs12193151"],"URL":"https:\/\/doi.org\/10.3390\/rs12193151","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,25]]}}}