{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T08:21:44Z","timestamp":1769242904894,"version":"3.49.0"},"reference-count":42,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T00:00:00Z","timestamp":1651795200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Maritime surveillance of the Arctic region is of growing importance as shipping, fishing and tourism are increasing due to the sea ice retreat caused by global warming. Ships that do not identify themselves with a transponder system, so-called dark ships, pose a security risk. They can be detected by SAR satellites, which can monitor the vast Arctic region through clouds, day and night, with the caveat that the abundant icebergs in the Arctic cause false alarms. We collect and analyze 200 Sentinel-1 horizontally polarized SAR scenes from areas with high maritime traffic and from the Arctic region with a high density of icebergs. Ships and icebergs are detected using a continuous wavelet transform, which is optimized by correlating ships to known AIS positions. Globally, we are able to assign 72% of the AIS signals to a SAR ship and 32% of the SAR ships to an AIS signal. The ships are used to construct an annotated dataset of more than 9000 ships and ten times as many icebergs. The dataset is used for training several convolutional neural networks, and we propose a new network which achieves state of the art performance compared to previous ship\u2013iceberg discrimination networks, reaching 93% validation accuracy. Furthermore, we collect a smaller test dataset consisting of 424 ships from 100 Arctic scenes which are correlated to AIS positions. This dataset constitutes an operational Arctic test scenario. We find these ships harder to classify with a lower test accuracy of 83%, because some of the ships sail near icebergs and ice floes, which confuses the classification algorithms.<\/jats:p>","DOI":"10.3390\/rs14092236","type":"journal-article","created":{"date-parts":[[2022,5,8]],"date-time":"2022-05-08T23:27:25Z","timestamp":1652052445000},"page":"2236","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["SAR Ship\u2013Iceberg Discrimination in Arctic Conditions Using Deep Learning"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8847-634X","authenticated-orcid":false,"given":"Peder","family":"Heiselberg","sequence":"first","affiliation":[{"name":"Geodesy and Earth Observation, National Space Institute of Denmark, Technical University of Denmark, 2800 Kongens Lyngby, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6443-1297","authenticated-orcid":false,"given":"Kristian A.","family":"S\u00f8rensen","sequence":"additional","affiliation":[{"name":"Geodesy and Earth Observation, National Space Institute of Denmark, Technical University of Denmark, 2800 Kongens Lyngby, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2229-2000","authenticated-orcid":false,"given":"Henning","family":"Heiselberg","sequence":"additional","affiliation":[{"name":"Geodesy and Earth Observation, National Space Institute of Denmark, Technical University of Denmark, 2800 Kongens Lyngby, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-3415","authenticated-orcid":false,"given":"Ole B.","family":"Andersen","sequence":"additional","affiliation":[{"name":"Geodesy and Earth Observation, National Space Institute of Denmark, Technical University of Denmark, 2800 Kongens Lyngby, Denmark"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,6]]},"reference":[{"key":"ref_1","unstructured":"Barkham, P. (The Guardian, 2017). Russian Tanker Sails through Arctic without Icebreaker for First Time, The Guardian."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1016\/j.accre.2021.02.002","article-title":"Variation of sea ice and perspectives of the Northwest Passage in the Arctic Ocean","volume":"12","author":"Chen","year":"2021","journal-title":"Adv. Clim. Chang. Res."},{"key":"ref_3","unstructured":"Ball, H. (2013). Satellite AIS for Dummies, Wiley."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.actaastro.2007.07.001","article-title":"Space-based AIS for global maritime traffic monitoring","volume":"62","author":"Eriksen","year":"2008","journal-title":"Acta Astronaut."},{"key":"ref_5","unstructured":"BBC (BBC News, 2021). Warship Positions Faked Including UK Aircraft Carrier, BBC News."},{"key":"ref_6","unstructured":"Crisp, D.J. (2021, June 01). The State-of-the-Art in Ship Detection in Synthetic Aperture Radar Imagery; Technical Report; Defence Science And Technology Organisation Salisbury (Australia). Available online: https:\/\/citeseerx.ist.psu.edu\/viewdoc\/download?doi=10.1.1.1000.6717&rep=rep1&type=pdf."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Greidanus, H., Alvarez, M., Santamaria, C., Thoorens, F.X., Kourti, N., and Argentieri, P. (2017). The SUMO Ship Detector Algorithm for Satellite Radar Images. Remote Sens., 9.","DOI":"10.3390\/rs9030246"},{"key":"ref_8","unstructured":"Palubinskas, G., Reinartz, P., Brusch, S., and Lehner, S. (2021, June 01). Joint Use of Optical and SAR Data for Ship Detection. Available online: https:\/\/elib.dlr.de."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1080\/07038992.2001.10854875","article-title":"Ocean Surveillance with Polarimetric SAR","volume":"27","author":"Yeremy","year":"2001","journal-title":"Can. J. Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"552","DOI":"10.5589\/m04-002","article-title":"Ship detection and characterization using polarimetric SAR","volume":"30","author":"Touzi","year":"2004","journal-title":"Can. J. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Touzi, R., Charbonneau, F., Hawkins, R., Murnaghan, K., and Kavoun, X. (2001, January 9\u201313). Ship-sea contrast optimization when using polarimetric SARs. Proceedings of the IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217), Sydney, Ausralia.","DOI":"10.4095\/219781"},{"key":"ref_12","unstructured":"Sciotti, M., Pastina, D., and Lombardo, P. (2001, January 9\u201313). Polarimetric detectors of extended targets for ship detection in SAR images. Proceedings of the IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217), Sydney, Ausralia."},{"key":"ref_13","unstructured":"Sciotti, M., Pastina, D., and Lombardo, P. (2002, January 24\u201328). Exploiting the polarimetric information for the detection of ship targets in non-homogeneous SAR images. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Toronto, ON, Canada."},{"key":"ref_14","unstructured":"Howell, C., Youden, J., Lane, K., Power, D., Randell, C., and Flett, D. (2004, January 20\u201324). Iceberg and ship discrimination with ENVISAT multipolarization ASAR. Proceedings of the IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium, Anchorage, AL, USA."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Howell, C., Mills, J., Power, D., Youden, J., Dodge, K., Randell, C., Churchill, S., and Flett, D. (August, January 31). A multivariate approach to iceberg and ship classification in HH\/HV ASAR data. Proceedings of the 2006 IEEE International Symposium on Geoscience and Remote Sensing, Denver, CO, USA.","DOI":"10.1109\/IGARSS.2006.918"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Heiselberg, P., and Heiselberg, H. (2017). Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification. Remote Sens., 9.","DOI":"10.3390\/rs9111156"},{"key":"ref_17","unstructured":"Bentes, C., Frost, A., Velotto, D., and Tings, B. (2016, January 6\u20139). Ship-Iceberg Discrimination with Convolutional Neural Networks in High Resolution SAR Images. Proceedings of the EUSAR 2016: 11th European Conference on Synthetic Aperture Radar, Hamburg, Germany."},{"key":"ref_18","unstructured":"Statoil\/C-CORE (2021, April 01). Statoil\/C-CORE Iceberg Classifier Challenge. Available online: https:\/\/www.kaggle.com\/c\/statoil-iceberg-classifier-challenge."},{"key":"ref_19","unstructured":"Jang, H., Kim, S., and Lam, T. (2017). Kaggle Competitions: Author Identification & Statoil\/C-CORE Iceberg Classifier Challenge, School of Informatics, Computing, and Engineering, Indiana University. Technical Report."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"82320","DOI":"10.1109\/ACCESS.2020.2990985","article-title":"A Computational Framework for Iceberg and Ship Discrimination: Case Study on Kaggle Competition","volume":"8","author":"Yang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Heiselberg, H. (2020). Ship-iceberg classification in SAR and multispectral satellite images with neural networks. Remote Sens., 12.","DOI":"10.3390\/rs12152353"},{"key":"ref_22","unstructured":"(2021, October 01). ESA Copernicus Program, Sentinel Scientific Data Hub. Available online: https:\/\/scihub.copernicus.eu\/."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhang, X., Ke, X., Zhan, X., Shi, J., Wei, S., Pan, D., Li, J., Su, H., and Zhou, Y. (2020). LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images. Remote Sens., 12.","DOI":"10.3390\/rs12182997"},{"key":"ref_24","unstructured":"(2021, October 01). Alaska Satellite Facility (ASF) Distributed Active Archive Center. Available online: https:\/\/asf.alaska.edu\/."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8741","DOI":"10.1029\/96JB00104","article-title":"A global, self-consistent, hierarchical, high-resolution shoreline database","volume":"101","author":"Wessel","year":"1996","journal-title":"J. Geophys. Res. Solid Earth"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2059","DOI":"10.1093\/bioinformatics\/btl355","article-title":"Improved peak detection in mass spectrum by incorporating continuous wavelet transform-based pattern matching","volume":"22","author":"Du","year":"2006","journal-title":"Bioinformatics"},{"key":"ref_27","unstructured":"(2022, March 14). European Marine 140 Observation and Data Network (EMODnet). Available online: https:\/\/www.emodnet-humanactivities.eu\/view-data.php."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Sang, L.Z., Yan, X.P., Mao, Z., and Ma, F. (2012, January 19\u201322). Restoring method of vessel track based on AIS information. Proceedings of the 2012 11th International Symposium on Distributed Computing and Applications to Business, Engineering & Science, Guilin, China.","DOI":"10.1109\/DCABES.2012.84"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Rodger, M., and Guida, R. (2020). Classification-Aided SAR and AIS Data Fusion for Space-Based Maritime Surveillance. Remote Sens., 13.","DOI":"10.3390\/rs13010104"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Heiselberg, H. (2019). Aircraft and Ship Velocity Determination in Sentinel-2 Multispectral Images. Sensors, 19.","DOI":"10.3390\/s19132873"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2014). Going Deeper with Convolutions. arXiv.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Li, Y., Ding, Z., Zhang, C., Wang, Y., and Chen, J. (August, January 28). SAR ship detection based on resnet and transfer learning. Proceedings of the 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019), Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8900290"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4379","DOI":"10.1109\/JSTARS.2019.2949006","article-title":"Ship velocity estimation from ship wakes detected using convolutional neural networks","volume":"12","author":"Kang","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7\u201312). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Marcel, S., and Rodriguez, Y. (2010, January 25\u201329). Torchvision the machine-vision package of torch. Proceedings of the 18th ACM international conference on Multimedia, Firenze, Italy.","DOI":"10.1145\/1873951.1874254"},{"key":"ref_36","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Curran Associates, Inc.. Available online: http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf."},{"key":"ref_37","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M. (2014). Striving for simplicity: The all convolutional net. arXiv."},{"key":"ref_38","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_39","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 7\u20139). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_40","unstructured":"Richards, M.A. (2014). Fundamentals of Radar Signal Processing, McGraw-Hill Education."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"124003","DOI":"10.1088\/1742-5468\/ac3a74","article-title":"Deep double descent: Where bigger models and more data hurt","volume":"2021","author":"Nakkiran","year":"2021","journal-title":"J. Stat. Mech. Theory Exp."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"235","DOI":"10.12716\/1001.14.01.30","article-title":"Ship-iceberg detection & classification in sentinel-1 SAR images","volume":"14","author":"Heiselberg","year":"2020","journal-title":"TransNav"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/9\/2236\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:07:17Z","timestamp":1760137637000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/9\/2236"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,6]]},"references-count":42,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["rs14092236"],"URL":"https:\/\/doi.org\/10.3390\/rs14092236","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,6]]}}}