{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:34:27Z","timestamp":1760060067211,"version":"build-2065373602"},"reference-count":45,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T00:00:00Z","timestamp":1753660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011033","name":"AEI","doi-asserted-by":"publisher","award":["PID2021-125324OB-I00","2023 DI 0007"],"award-info":[{"award-number":["PID2021-125324OB-I00","2023 DI 0007"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003030","name":"Doctorat Industrial (AGAUR)","doi-asserted-by":"publisher","award":["PID2021-125324OB-I00","2023 DI 0007"],"award-info":[{"award-number":["PID2021-125324OB-I00","2023 DI 0007"]}],"id":[{"id":"10.13039\/501100003030","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>This study evaluates machine learning-based methods for retrieving thin Arctic sea ice thickness (SIT) from L-band radiometry, using data from the European Space Agency\u2019s (ESA) Soil Moisture and Ocean Salinity (SMOS) satellite. In addition to the operational ESA product, three alternative approaches are assessed: a Random Forest (RF) algorithm, a Convolutional Neural Network (CNN) that incorporates spatial coherence, and a Long Short-Term Memory (LSTM) neural network designed to capture temporal coherence. Validation against in situ data from the Beaufort Gyre Exploration Project (BGEP) moorings and the ESA SMOSice campaign demonstrates that the RF algorithm achieves robust performance comparable to the ESA product, despite its simplicity and lack of explicit spatial or temporal modeling. The CNN exhibits a tendency to overestimate SIT and shows higher dispersion, suggesting limited added value when spatial coherence is already present in the input data. The LSTM approach does not improve retrieval accuracy, likely due to the mismatch between satellite resolution and the temporal variability of sea ice conditions. These results highlight the importance of L-band sea ice emission modeling over increasing algorithm complexity and suggest that simpler, adaptable methods such as RF offer a promising foundation for future SIT retrieval efforts. The findings are relevant for refining current methods used with SMOS and for developing upcoming satellite missions, such as ESA\u2019s Copernicus Imaging Microwave Radiometer (CIMR).<\/jats:p>","DOI":"10.3390\/computers14080305","type":"journal-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T10:51:14Z","timestamp":1753699874000},"page":"305","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessment of Machine Learning-Driven Retrievals of Arctic Sea Ice Thickness from L-Band Radiometry Remote Sensing"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9529-9095","authenticated-orcid":false,"given":"Ferran","family":"Hern\u00e1ndez-Maci\u00e0","sequence":"first","affiliation":[{"name":"Barcelona Polar Lab (BPL), Institute of Marine Sciences (ICM-CSIC), 08003 Barcelona, Spain"},{"name":"Department of Computer Architecture and Operating Systems, Autonomous University of Barcelona (UAB), 08193 Bellaterra, Spain"},{"name":"isardSAT, S.L., 08005 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1406-3320","authenticated-orcid":false,"given":"Gemma","family":"Sanjuan Gomez","sequence":"additional","affiliation":[{"name":"Department of Computer Architecture and Operating Systems, Autonomous University of Barcelona (UAB), 08193 Bellaterra, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0004-1964","authenticated-orcid":false,"given":"Carolina","family":"Gabarr\u00f3","sequence":"additional","affiliation":[{"name":"Barcelona Polar Lab (BPL), Institute of Marine Sciences (ICM-CSIC), 08003 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7780-7334","authenticated-orcid":false,"given":"Maria Jos\u00e9","family":"Escorihuela","sequence":"additional","affiliation":[{"name":"isardSAT, S.L., 08005 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"611","DOI":"10.3402\/tellusa.v21i5.10109","article-title":"The effect of solar radiation variations on the climate of the Earth","volume":"21","author":"Budyko","year":"1969","journal-title":"Tellus"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"105005","DOI":"10.1088\/1748-9326\/aae3ec","article-title":"Arctic sea ice thickness, volume, and multiyear ice coverage: Losses and coupled variability (1958\u20132018)","volume":"13","author":"Kwok","year":"2018","journal-title":"Environ. Res. Lett."},{"key":"ref_3","unstructured":"Meredith, M., Sommerkorn, M., Cassotta, S., Derksen, C., Ekaykin, A., Hollowed, A., Kofinas, G., Mackintosh, A., Melbourne-Thomas, J., and Muelbert, M. (2019). Polar Regions. IPCC Special Report on the Ocean and Cryosphere in a Changing Climate, Cambridge University Press."},{"key":"ref_4","first-page":"25","article-title":"Getting down to business-SMOS operations and products","volume":"137","author":"Mecklenburg","year":"2009","journal-title":"ESA Bull."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1109\/JPROC.2010.2043032","article-title":"The SMOS mission: New tool for monitoring key elements of the global water cycle","volume":"98","author":"Kerr","year":"2010","journal-title":"Proc. IEEE"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1109\/JPROC.2010.2043918","article-title":"The Soil Moisture Active Passive (SMAP) mission","volume":"98","author":"Entekhabi","year":"2010","journal-title":"Proc. IEEE"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"L05501","DOI":"10.1029\/2012GL050916","article-title":"Sea ice thickness retrieval from SMOS brightness temperatures during the Arctic freeze-up period","volume":"39","author":"Kaleschke","year":"2012","journal-title":"Geophys. Res. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"997","DOI":"10.5194\/tc-8-997-2014","article-title":"SMOS-derived thin sea ice thickness: Algorithm baseline, product specifications and initial verification","volume":"8","author":"Kaleschke","year":"2014","journal-title":"Cryosphere"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"9","DOI":"10.3189\/2015AoG69A886","article-title":"Snow thickness retrieval from L-band brightness temperatures: A model comparison","volume":"56","author":"Maass","year":"2015","journal-title":"Ann. Glaciol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"439","DOI":"10.5194\/tc-8-439-2014","article-title":"Empirical sea ice thickness retrieval during the freeze-up period from SMOS high incident angle observations","volume":"8","author":"Huntemann","year":"2014","journal-title":"Cryosphere"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4795","DOI":"10.1109\/JSTARS.2016.2582690","article-title":"Spaceborne GNSS-R Sea Ice Detection Using Delay-Doppler Maps: First Results From the U.K. TechDemoSat-1 Mission","volume":"9","author":"Yan","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1007\/s10291-022-01309-0","article-title":"Can sea ice thickness be retrieved using GNSS-interferometric reflectometry?","volume":"26","author":"Wang","year":"2022","journal-title":"GPS Solut."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.5194\/tc-13-2421-2019","article-title":"Estimating snow depth on Arctic sea ice using satellite microwave radiometry and a neural network","volume":"13","author":"Donlon","year":"2019","journal-title":"Cryosphere"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yan, Q., and Huang, W. (2020, January 5\u201330). Sea Ice Thickness Estimation From TechDemoSat-1 and Soil Moisture Ocean Salinity Data Using Machine Learning Methods. Proceedings of the Global Oceans 2020: Singapore\u2013U.S. Gulf Coast, Biloxi, MS, USA.","DOI":"10.1109\/IEEECONF38699.2020.9388974"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"812","DOI":"10.1080\/15481603.2021.1943213","article-title":"Retrieval of daily sea ice thickness from AMSR2 passive microwave data using ensemble convolutional neural networks","volume":"58","author":"Chi","year":"2021","journal-title":"GIScience Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e2022EA002542","DOI":"10.1029\/2022EA002542","article-title":"Arctic Sea Ice Thickness Estimation From Passive Microwave Satellite Observations Between 1.4 and 36 GHz","volume":"10","author":"Soriot","year":"2023","journal-title":"Earth Space Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Soriot, C., Vancoppenolle, M., Prigent, C., Jimenez, C., and Frappart, F. (2024). Winter Arctic sea ice volume decline: Uncertainties reduced using passive microwave-based sea ice thickness. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-70136-9"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Herbert, C., Munoz-Martin, J.F., Llaveria, D., Pablos, M., and Camps, A. (2021). Sea Ice Thickness Estimation Based on Regression Neural Networks Using L-Band Microwave Radiometry Data from the FSSCat Mission. Remote Sens., 13.","DOI":"10.5194\/egusphere-egu21-12946"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Camps, A., Golkar, A., Gutierrez, A., de Azua, J.R., Munoz-Martin, J., Fernandez, L., Diez, C., Aguilella, A., Briatore, S., and Akhtyamov, R. (2018, January 22\u201327). Fsscat, the 2017 Copernicus Masters\u2019 \u201cEsa Sentinel Small Satellite Challenge\u201d Winner: A Federated Polar and Soil Moisture Tandem Mission Based on 6U Cubesats. Proceedings of the IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8518405"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"112851","DOI":"10.1016\/j.rse.2021.112851","article-title":"Spatio-temporal distribution of sea-ice thickness using a machine learning approach with Google Earth Engine and Sentinel-1 GRD data","volume":"270","author":"Shamshiri","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_21","first-page":"1","article-title":"Sea Ice Type and Thickness Identification Based on Vibration Sensor Networks and Machine Learning","volume":"72","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"10752","DOI":"10.1109\/JSTARS.2024.3406921","article-title":"A Machine Learning Approach on SMOS Thin Sea Ice Thickness Retrieval","volume":"17","author":"Gomez","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1729","DOI":"10.1109\/36.942551","article-title":"Soil moisture retrieval from space: The Soil Moisture and Ocean Salinity (SMOS) mission","volume":"39","author":"Kerr","year":"2001","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_24","first-page":"79","article-title":"Method of forecasting flexural strength of an ice cover","volume":"45","author":"Ryvlin","year":"1974","journal-title":"Probl. Arct. Antarct."},{"key":"ref_25","unstructured":"Tian-Kunze, X., Kaleschke, L., and Crapolicchio, R. (2021). SMOS L3 Sea Ice Thickness ATBD: Algorithm Theoretical Baseline Document, European Space Agency (ESA). Technical Report."},{"key":"ref_26","unstructured":"Karagali, I., Nielsen-Englyst, P., Kolbe, W.M., and H\u00f8yer, J.L. (2025, July 24). Arctic Ocean-Sea and Ice Surface Temperature REPROCESSED. Available online: https:\/\/data.marine.copernicus.eu\/product\/SEAICE_ARC_PHY_CLIMATE_L4_MY_011_016\/description."},{"key":"ref_27","unstructured":"Huntemann, M. (2015). Thickness Retrieval and Emissivity Modeling of Thin Sea Ice at L-Band for SMOS Satellite Observations. [Ph.D. Thesis, University of Bremen]."},{"key":"ref_28","unstructured":"Ali, A., Burud, A., Williams, T., Xie, J., Yumruktepe, C., Wakamatsu, T., Melsom, A., Bertino, L., and Gao, S. (2025, July 24). Arctic Ocean Physics Reanalysis. Available online: https:\/\/data.marine.copernicus.eu\/product\/ARCTIC_MULTIYEAR_PHY_002_003\/description."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Kovacs, A., U.S. Army, Corps of Engineers, and Cold Regions Research and Engineering Laboratory (U.S.) (1996). Sea Ice: Bulk Salinity Versus Ice Floe Thickness, U.S. Army Cold Regions Research and Engineering Laboratory. Number Part 1 in CRREL Report.","DOI":"10.21236\/ADA312027"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1029\/JC084iC01p00287","article-title":"Comparison of 2.8- and 21-cm microwave radiometer observations over soils with emission model calculations","volume":"84","author":"Burke","year":"1979","journal-title":"J. Geophys. Res."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1063\/1.325018","article-title":"The complex-dielectric constant of sea ice at frequencies in the range 0.1\u201340 GHz","volume":"49","author":"Vant","year":"1978","journal-title":"J. Appl. Phys."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1109\/TGE.1978.294577","article-title":"Radiative Transfer in a Plane Stratified Dielectric","volume":"16","author":"Wilheit","year":"1978","journal-title":"IEEE Trans. Geosci. Electron."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2763","DOI":"10.5194\/gmd-11-2763-2018","article-title":"SMRT: An active\u2013passive microwave radiative transfer model for snow with multiple microstructure and scattering formulations (v1.0)","volume":"11","author":"Picard","year":"2018","journal-title":"Geosci. Model Dev."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"e37","DOI":"10.1017\/aog.2024.38","article-title":"On sea ice emission modeling for MOSAiC\u2019s L-band radiometric measurements","volume":"65","author":"Huntemann","year":"2024","journal-title":"Ann. Glaciol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2189","DOI":"10.5194\/tc-14-2189-2020","article-title":"Satellite-based sea ice thickness changes in the Laptev Sea from 2002 to 2017: Comparison to mooring observations","volume":"14","author":"Belter","year":"2020","journal-title":"Cryosphere"},{"key":"ref_36","unstructured":"Vinje, T., and Finnek\u00e5sa, \u00d8. (1986). The Ice Transport Through the Fram Strait, Norsk Polarinstitutt."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1016\/j.rse.2016.03.009","article-title":"SMOS sea ice product: Operational application and validation in the Barents Sea marginal ice zone","volume":"180","author":"Kaleschke","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5556","DOI":"10.1029\/2019GC008515","article-title":"The Generic Mapping Tools Version 6","volume":"20","author":"Wessel","year":"2019","journal-title":"Geochem. Geophys. Geosyst."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","article-title":"Stochastic gradient boosting","volume":"38","author":"Friedman","year":"2002","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"315","DOI":"10.3189\/S0022143000015409","article-title":"Growth Rate and Salinity Profile of First-Year Sea Ice in the High Arctic","volume":"27","author":"Nakawo","year":"1981","journal-title":"J. Glaciol."},{"key":"ref_42","unstructured":"O\u2019Shea, K., and Nash, R. (2015). An Introduction to Convolutional Neural Networks. arXiv."},{"key":"ref_43","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_44","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/8\/305\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:17:15Z","timestamp":1760033835000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/8\/305"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,28]]},"references-count":45,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["computers14080305"],"URL":"https:\/\/doi.org\/10.3390\/computers14080305","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2025,7,28]]}}}