{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T06:44:22Z","timestamp":1769841862710,"version":"3.49.0"},"reference-count":41,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2018,12,22]],"date-time":"2018-12-22T00:00:00Z","timestamp":1545436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002644","name":"Pukyong National University","doi-asserted-by":"publisher","award":["2014"],"award-info":[{"award-number":["2014"]}],"id":[{"id":"10.13039\/501100002644","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Warming of the Arctic leads to a decrease in sea ice, and the decrease of sea ice, in turn, results in warming of the Arctic again. Several microwave sensors have provided continuously updated sea ice data for over 30 years. Many studies have been conducted to investigate the relationships between the satellite-derived sea ice concentration (SIC) of the Arctic and climatic factors associated with the accelerated warming. However, linear equations using the general circulation model (GCM) data, with low spatial resolution, cannot sufficiently cope with the problem of complexity or non-linearity. Time-series techniques are effective for one-step-ahead forecasting, but are not appropriate for future prediction for about ten or twenty years because of increasing uncertainty when forecasting multiple steps ahead. This paper describes a new approach to near-future prediction of Arctic SIC by employing a deep learning method with multi-model ensemble. We used the regional climate model (RCM) data provided in higher resolution, instead of GCM. The RCM ensemble was produced by Bayesian model averaging (BMA) to minimize the uncertainty which can arise from a single RCM. The accuracies of RCM variables were much improved by the BMA2 method, which took into consideration temporal and spatial variations to minimize the uncertainty of individual RCMs. A deep neural network (DNN) method was used to deal with the non-linear relationships between SIC and climate variables, and to provide a near-future prediction for the forthcoming 10 to 20 years. We adjusted the DNN model for optimized SIC prediction by adopting best-fitted layer structure, loss function, optimizer algorithm, and activation function. The accuracy was much improved when the DNN model was combined with BMA2 ensemble, showing the correlation coefficient of 0.888. This study provides a viable option for monitoring Arctic sea ice change of the near future.<\/jats:p>","DOI":"10.3390\/rs11010019","type":"journal-article","created":{"date-parts":[[2018,12,24]],"date-time":"2018-12-24T10:37:49Z","timestamp":1545647869000},"page":"19","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Satellite-Based Prediction of Arctic Sea Ice Concentration Using a Deep Neural Network with Multi-Model Ensemble"],"prefix":"10.3390","volume":"11","author":[{"given":"Jiwon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Spatial Information Engineering, Pukyong National University, Busan 48513, Korea"}]},{"given":"Kwangjin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Spatial Information Engineering, Pukyong National University, Busan 48513, Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3375-4357","authenticated-orcid":false,"given":"Jaeil","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Applied Plant Science, Chonnam National University, Gwangju 61186, Korea"}]},{"given":"Yong Q.","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Oceanography, Pukyong National University, Busan 48513, Korea"}]},{"given":"Hong-Joo","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department of Spatial Information Engineering, Pukyong National University, Busan 48513, Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5251-6100","authenticated-orcid":false,"given":"Yang-Won","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Spatial Information Engineering, Pukyong National University, Busan 48513, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2018,12,22]]},"reference":[{"key":"ref_1","unstructured":"Intergovernmental Panel on Climate Change (IPCC) (2014). Climate Change 2014: Synthesis Report. Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change, IPCC."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1175\/1520-0442(1995)008<0240:SIACFM>2.0.CO;2","article-title":"Sea ice-albedo climate feedback mechanism","volume":"8","author":"Curry","year":"1995","journal-title":"J. Clim."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"71","DOI":"10.3189\/172756408784700699","article-title":"Arctic sea-ice variability revisited","volume":"48","author":"Stroeve","year":"2008","journal-title":"Ann. Glaciol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1378","DOI":"10.1175\/2010JCLI3527.1","article-title":"Origins and levels of seasonal forecast skill for sea ice in Hudson Bay using canonical correlation analysis","volume":"24","author":"Tivy","year":"2011","journal-title":"J. Clim."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"L10501","DOI":"10.1029\/2006GL026216","article-title":"A long-range forecast of Arctic summer sea-ice minimum extent","volume":"33","author":"Drobot","year":"2006","journal-title":"Geophys. Res. Lett."},{"key":"ref_6","unstructured":"Pritchard, R.S. (1980). Empirical orthogonal functions and the statistical predictability of sea ice extent. Sea Ice Processes and Models, University of Washington Press."},{"key":"ref_7","unstructured":"Kim, J.H., Joeng, J.H., Kim, B.M., and Shin, J.H. (2016). Mid-Long Term Prediction of Arctic Sea Ice Concentration using Statistical Method. [Master\u2019s Thesis, Chonnam National University]."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5520","DOI":"10.3390\/rs6065520","article-title":"Statistical Modeling of Sea Ice Concentration Using Satellite Imagery and Climate Reanalysis Data in the Barents and Kara Seas, 1979\u20132012","volume":"6","author":"Ahn","year":"2014","journal-title":"Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Chi, J., and Kim, H.C. (2017). Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network. Remote Sens., 9.","DOI":"10.3390\/rs9121305"},{"key":"ref_10","first-page":"382","article-title":"Bayesian model averaging: A tutorial","volume":"14","author":"Hoeting","year":"1999","journal-title":"Stat. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5103","DOI":"10.1175\/JCLI-D-15-0669.1","article-title":"Dynamical link between the Barents\u2013Kara sea ice and the Arctic Oscillation","volume":"29","author":"Yang","year":"2016","journal-title":"J. Clim."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2281","DOI":"10.1016\/S0967-0637(02)00125-5","article-title":"Atlantic water flow through the Barents and Kara Seas","volume":"49","author":"Schauer","year":"2002","journal-title":"Deep Sea Res. Part I Oceanogr. Res. Pap."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4772","DOI":"10.1175\/JCLI3885.1","article-title":"Atmospheric forcing on the Barents Sea winter ice extent","volume":"19","author":"Sorteberg","year":"2006","journal-title":"J. Clim."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5092","DOI":"10.1175\/JCLI-D-13-00536.1","article-title":"The early winter sea ice variability under the recent Arctic climate shift","volume":"27","author":"Yang","year":"2014","journal-title":"J. Clim."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1002\/rog.20017","article-title":"The role of the Barents Sea in the Arctic climate system","volume":"51","author":"Smedsrud","year":"2013","journal-title":"Rev. Geophys."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sato, K., Inoue, J., and Watanabe, M. (2014). Influence of the Gulf Stream on the Barents Sea ice retreat and Eurasian coldness during early winter. Environ. Res. Lett., 9.","DOI":"10.1088\/1748-9326\/9\/8\/084009"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3925","DOI":"10.1175\/JCLI-D-15-0611.1","article-title":"Impact of ural blocking on winter warm Arctic-cold Eurasian anomalies. Part I: Blocking-induced amplification","volume":"29","author":"Luo","year":"2016","journal-title":"J. Clim."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Serreze, M.C., and Barry, R.G. (2014). The Arctic Climate System, Cambridge University Press. [2nd ed.].","DOI":"10.1017\/CBO9781139583817"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5355","DOI":"10.1029\/JD089iD04p05355","article-title":"Determination of sea ice parameters with the Nimbus 7 SMMR","volume":"89","author":"Cavalieri","year":"1984","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1029\/JC091iC01p00975","article-title":"Characteristics of Arctic winter sea ice from satellite multispectral microwave observations","volume":"91","author":"Comiso","year":"1986","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_21","unstructured":"National Snow and Ice Data Center (NSIDC) (2018, October 20). Climate Data Record (CDR) Program: Climate Algorithm Theoretical Basis Document (C-ATBD) Sea Ice Concentration. Available online: https:\/\/nsidc.org\/sites\/nsidc.org\/files\/technical-references\/SeaIce_CDR_CATBD_final.pdf."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2537","DOI":"10.1002\/2017JD027703","article-title":"Cyclone activity in the Arctic from an ensemble of regional climate models (Arctic CORDEX)","volume":"123","author":"Akperov","year":"2018","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5829","DOI":"10.1002\/jgrc.20414","article-title":"Moisture flux changes and trends for the entire Arctic in 2003\u20132011 derived from EOS Aqua data","volume":"118","author":"Boisvert","year":"2013","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.5194\/tc-10-2191-2016","article-title":"Mechanism of seasonal Arctic sea ice evolution and Arctic amplification","volume":"10","author":"Kim","year":"2016","journal-title":"Cryosphere"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.1175\/JCLI-D-11-00113.1","article-title":"Large decadal decline of the Arctic multiyear ice cover","volume":"25","author":"Comiso","year":"2012","journal-title":"J. Clim."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"139","DOI":"10.5194\/asr-14-139-2017","article-title":"Seasonal co-variability of surface downwelling longwave radiation for the 1982\u20132009 period in the Arctic","volume":"14","author":"Boccolari","year":"2017","journal-title":"Adv. Sci. Res."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1002\/2017GL075375","article-title":"Revisiting the Cause of the 1989\u20132009 Arctic Surface Warming Using the Surface Energy Budget: Downward Infrared Radiation Dominates the Surface Fluxes","volume":"44","author":"Lee","year":"2017","journal-title":"Geophys. Res. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1175\/JTECH-D-14-00165.1","article-title":"CERES synoptic product: Methodology and validation of surface radiant flux","volume":"32","author":"Rutan","year":"2015","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"18","DOI":"10.3189\/2015AoG69A909","article-title":"Comparing and contrasting the behaviour of Arctic and Antarctic sea ice over the 35 years period 1979\u20132013","volume":"56","author":"Simmonds","year":"2015","journal-title":"Ann. Glaciol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1007\/s10584-011-0101-1","article-title":"The Arctic\u2019s rapidly shrinking sea ice cover: A research synthesis","volume":"110","author":"Stroeve","year":"2012","journal-title":"Clim. Chang."},{"key":"ref_31","first-page":"133","article-title":"The role of natural versus forced change in future rapid summer Arctic ice loss","volume":"Volume 180","author":"Holland","year":"2008","journal-title":"Arctic Sea Ice Decline: Observations, Projections, Mechanisms, and Implications"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2243","DOI":"10.1007\/s00382-011-1105-2","article-title":"Declining summer snowfall in the Arctic: Causes, impacts and feedbacks","volume":"38","author":"Screen","year":"2012","journal-title":"Clim. Dyn."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"L19501","DOI":"10.1029\/2011GL048970","article-title":"Trends in Arctic sea ice drift and role of wind forcing: 1992\u20132009","volume":"38","author":"Spreen","year":"2011","journal-title":"Geophys. Res. Lett."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"L02501","DOI":"10.1029\/2011GL050118","article-title":"Atmospheric forcing on the drift of Arctic sea ice in 1989\u20132009","volume":"39","author":"Vihma","year":"2012","journal-title":"Geophys. Res. Lett."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1851","DOI":"10.1016\/S0277-3791(01)00016-6","article-title":"Freshwater and Atlantic water inflows to the deep northern Barents and Kara seas since ca 13 14C ka: Foraminifera and stable isotopes","volume":"20","author":"Lubinski","year":"2001","journal-title":"Quat. Sci. Rev."},{"key":"ref_36","unstructured":"(2018, September 11). National Snow and Ice Data Center. Available online: https:\/\/nsidc.org\/arcticseaicenews."},{"key":"ref_37","unstructured":"Johannessen, O.M., Muench, R.D., and Overland, J.E. (1994). The northern Barents Sea: Water mass distribution and modification. The Polar Oceans and Their Role in Shaping the Global Environment, American Geophysical Union. [85th ed.]."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2639","DOI":"10.1175\/JCLI-D-16-0548.1","article-title":"Ural blocking as an amplifier of the Arctic sea ice decline in winter","volume":"30","author":"Gong","year":"2017","journal-title":"J. Clim."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"054017","DOI":"10.1088\/1748-9326\/aa69d0","article-title":"Atmospheric circulation patterns which promote winter Arctic sea ice decline","volume":"12","author":"Luo","year":"2017","journal-title":"Environ. Res. Lett."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1175\/JCLI-D-15-0448.1","article-title":"On anomalous ocean heat transport toward the Arctic and associated climate predictability","volume":"29","author":"Eldevik","year":"2016","journal-title":"J. Clim."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1175\/2010JCLI3775.1","article-title":"Persistence and inherent predictability of Arctic sea ice in a GCM ensemble and observations","volume":"24","author":"Armour","year":"2011","journal-title":"J. Clim."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/1\/19\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:35:44Z","timestamp":1760196944000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/1\/19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,22]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,1]]}},"alternative-id":["rs11010019"],"URL":"https:\/\/doi.org\/10.3390\/rs11010019","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,22]]}}}