{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:39:10Z","timestamp":1773736750939,"version":"3.50.1"},"reference-count":56,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2022,6,24]],"date-time":"2022-06-24T00:00:00Z","timestamp":1656028800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","award":["RGPIN-2017-04869"],"award-info":[{"award-number":["RGPIN-2017-04869"]}]},{"name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","award":["DGDND-2017-00078"],"award-info":[{"award-number":["DGDND-2017-00078"]}]},{"name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","award":["RGPAS2017-50794"],"award-info":[{"award-number":["RGPAS2017-50794"]}]},{"name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","award":["RGPIN-2019-06744"],"award-info":[{"award-number":["RGPIN-2019-06744"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Sea ice mapping plays an integral role in ship navigation and meteorological modeling in the polar regions. Numerous published studies in sea ice classification using synthetic aperture radar (SAR) have reported high classification rates. However, many of these focus on numerical results based on sample points and ignore the quality of the inferred sea ice maps. We have designed and implemented a novel SAR sea ice classification algorithm where the spatial context, obtained by the unsupervised IRGS segmentation algorithm, is integrated with texture features extracted by a residual neural network (ResNet) and, using regional pooling, classifies ice and water. This algorithm is trained and tested on a published dataset and cross-validated using leave-one-out (LOO) strategy, obtaining an overall accuracy of 99.67% and outperforming several existing algorithms. In addition, visual results show that this new method produces sea ice maps with natural ice\u2013water boundaries and fewer ice and water errors.<\/jats:p>","DOI":"10.3390\/rs14133025","type":"journal-article","created":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T22:43:00Z","timestamp":1656024180000},"page":"3025","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Sea Ice\u2013Water Classification of RADARSAT-2 Imagery Based on Residual Neural Networks (ResNet) with Regional Pooling"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0603-8339","authenticated-orcid":false,"given":"Mingzhe","family":"Jiang","sequence":"first","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"}]},{"given":"Linlin","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6383-0875","authenticated-orcid":false,"given":"David A.","family":"Clausi","sequence":"additional","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,24]]},"reference":[{"key":"ref_1","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_2","doi-asserted-by":"crossref","unstructured":"Bobylev, L.P., and Miles, M.W. (2020). Sea Ice in the Arctic Paleoenvironments. Sea Ice in the Arctic, Springer.","DOI":"10.1007\/978-3-030-21301-5_2"},{"key":"ref_3","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_4","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1007\/s10584-009-9683-2","article-title":"Perspectives of Northern Sea Route and Northwest Passage in the twenty-first century","volume":"100","author":"Khon","year":"2010","journal-title":"Clim. Chang."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zakhvatkina, N., Smirnov, V., and Bychkova, I. (2019). Satellite SAR data-based sea ice classification: An overview. Geosciences, 9.","DOI":"10.3390\/geosciences9040152"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"White, L., Millard, K., Banks, S., Richardson, M., Pasher, J., and Duffe, J. (2017). Moving to the RADARSAT constellation mission: Comparing synthesized compact polarimetry and dual polarimetry data with fully polarimetric RADARSAT-2 data for image classification of peatlands. Remote Sens., 9.","DOI":"10.3390\/rs9060573"},{"key":"ref_7","unstructured":"De Lisle, D., Iris, S., Arsenault, E., Smyth, J., and Kroupnik, G. (2018, January 4\u20137). RADARSAT Constellation Mission status update. Proceedings of the EUSAR 2018, 12th European Conference on Synthetic Aperture Radar, Aachen, Germany."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1109\/TGRS.2009.2031806","article-title":"Mapping of Different Sea Ice Regimes Using Images From Sentinel-1 and ALOS Synthetic Aperture Radar","volume":"48","author":"Dierking","year":"2010","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1038\/ngeo1627","article-title":"Wind-driven trends in Antarctic sea-ice drift","volume":"5","author":"Holland","year":"2012","journal-title":"Nat. Geosci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1109\/TGRS.2004.842017","article-title":"Sea ice mapping method for SeaWinds","volume":"43","author":"Anderson","year":"2005","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","unstructured":"Scheuchl, B., Caves, R., Cumming, I., and Staples, G. (2001, January 9\u201313). Automated sea ice classification using spaceborne polarimetric SAR data. IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings of the IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No. 01CH37217), Sydney, Ausralia."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2593","DOI":"10.1109\/TGRS.2002.806991","article-title":"Incidence angle dependence of the statistical properties of C-band HH-polarization backscattering signatures of the Baltic Sea ice","volume":"40","author":"Makynen","year":"2002","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3188","DOI":"10.1109\/TGRS.2015.2513159","article-title":"Incidence angle correction of SAR sea ice data based on locally linear mapping","volume":"54","author":"Lang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6686","DOI":"10.1109\/TGRS.2018.2841343","article-title":"Incidence angle dependence of HH-polarized C-and L-band wintertime backscatter over Arctic sea ice","volume":"56","author":"Mahmud","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/LGRS.2019.2895656","article-title":"Sea ice change detection in SAR images based on convolutional-wavelet neural networks","volume":"16","author":"Gao","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wenbo, W., Yusong, W., Xue, D., Xiaotong, J., Yida, K., and Xiangli, W. (2015, January 18\u201320). Sea ice classification of SAR image based on wavelet transform and gray level co-occurrence matrix. Proceedings of the 2015 Fifth International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC), Qinhuangdao, China.","DOI":"10.1109\/IMCCC.2015.29"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5831","DOI":"10.1109\/JSTARS.2021.3074068","article-title":"Prediction of categorized Sea Ice Concentration from Sentinel-1 SAR images based on a Fully Convolutional Network","volume":"14","author":"Colin","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3715","DOI":"10.1109\/TGRS.2018.2809504","article-title":"Arctic Sea Ice Characterization Using Spaceborne Fully Polarimetric L-, C-, and X-Band SAR With Validation by Airborne Measurements","volume":"56","author":"Singha","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"285","DOI":"10.3189\/2015AoG69A802","article-title":"Assessing polarimetric SAR sea-ice classifications using consecutive day images","volume":"56","author":"Moen","year":"2015","journal-title":"Ann. Glaciol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ressel, R., and Singha, S. (2016). Comparing near coincident space borne C and X band fully polarimetric SAR data for Arctic sea ice classification. Remote Sens., 8.","DOI":"10.3390\/rs8030198"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"306","DOI":"10.5589\/m12-025","article-title":"Evaluation of C-band SAR polarimetric parameters for discrimination of first-year sea ice types","volume":"38","author":"Gill","year":"2012","journal-title":"Can. J. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Dabboor, M., Montpetit, B., and Howell, S. (2018). Assessment of the high resolution SAR mode of the RADARSAT constellation mission for first year ice and multiyear ice characterization. Remote Sens., 10.","DOI":"10.3390\/rs10040594"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7476","DOI":"10.1109\/TGRS.2019.2913796","article-title":"Contextual classification of sea-ice types using compact polarimetric SAR data","volume":"57","author":"Ghanbari","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1109\/TGRS.2017.2713123","article-title":"ST-IRGS: A region-based self-training algorithm applied to hyperspectral image classification and segmentation","volume":"56","author":"Li","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1109\/36.752194","article-title":"Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices","volume":"37","author":"Soh","year":"1999","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1017\/aog.2018.6","article-title":"Method for detection of leads from Sentinel-1 SAR images","volume":"59","author":"Murashkin","year":"2018","journal-title":"Ann. Glaciol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, B., Xia, L., Song, D., Li, Z., and Wang, N. (2021). A Two-Round Weight Voting Strategy-Based Ensemble Learning Method for Sea Ice Classification of Sentinel-1 Imagery. Remote Sens., 13.","DOI":"10.3390\/rs13193945"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"45","DOI":"10.5589\/m02-004","article-title":"An analysis of co-occurrence texture statistics as a function of grey level quantization","volume":"28","author":"Clausi","year":"2002","journal-title":"Can. J. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3040","DOI":"10.1109\/TGRS.2020.3007789","article-title":"Extraction of sea ice cover by Sentinel-1 SAR based on support vector machine with unsupervised generation of training data","volume":"59","author":"Li","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lyu, H., Huang, W., and Mahdianpari, M. (2021, January 12\u201317). Sea Ice Detection From the RADARSAT Constellation Mission Experiment Data. Proceedings of the 2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Virtual.","DOI":"10.1109\/CCECE53047.2021.9569052"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1109\/TGRS.2016.2612821","article-title":"Convolutional neural networks for large-scale remote-sensing image classification","volume":"55","author":"Maggiori","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Han, Y., Liu, Y., Hong, Z., Zhang, Y., Yang, S., and Wang, J. (2021). Sea Ice Image Classification Based on Heterogeneous Data Fusion and Deep Learning. Remote Sens., 13.","DOI":"10.3390\/rs13040592"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhang, T., Yang, Y., Shokr, M., Mi, C., Li, X.M., Cheng, X., and Hui, F. (2021). Deep Learning Based Sea Ice Classification with Gaofen-3 Fully Polarimetric SAR Data. Remote Sens., 13.","DOI":"10.3390\/rs13081452"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Boulze, H., Korosov, A., and Brajard, J. (2020). Classification of sea ice types in Sentinel-1 SAR data using convolutional neural networks. Remote Sens., 12.","DOI":"10.3390\/rs12132165"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/TGRS.2020.2992454","article-title":"Evaluation of a Neural Network With Uncertainty for Detection of Ice and Water in SAR Imagery","volume":"59","author":"Asadi","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Song, W., Li, M., Gao, W., Huang, D., Ma, Z., Liotta, A., and Perra, C. (2021). Automatic Sea-Ice Classification of SAR Images Based on Spatial and Temporal Features Learning. IEEE Trans. Geosci. Remote Sens.","DOI":"10.1109\/TGRS.2020.3049031"},{"key":"ref_37","first-page":"1","article-title":"Development of a Dual-Attention U-Net Model for Sea Ice and Open Water Classification on SAR Images","volume":"19","author":"Ren","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chi, J., Bae, J., and Kwon, Y.J. (2021). Two-Stream Convolutional Long-and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction. Remote Sens., 13.","DOI":"10.3390\/rs13173413"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.patcog.2005.07.010","article-title":"Preserving boundaries for image texture segmentation using grey level co-occurring probabilities","volume":"39","author":"Jobanputra","year":"2006","journal-title":"Pattern Recognit."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2126","DOI":"10.1109\/TPAMI.2008.15","article-title":"IRGS: Image segmentation using edge penalties and region growing","volume":"30","author":"Yu","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"5529","DOI":"10.1109\/TGRS.2013.2290231","article-title":"Automated ice\u2013water classification using dual polarization SAR satellite imagery","volume":"52","author":"Leigh","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Jiang, M., Clausi, D.A., and Xu, L. (2021). Sea Ice Mapping of RADARSAT-2 Imagery by Integrating Spatial Contexture with Textural Features. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., unpublished.","DOI":"10.1109\/JSTARS.2022.3205849"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"345","DOI":"10.5589\/m04-007","article-title":"RADARSAT-2 SAR image quality and calibration operations","volume":"30","author":"Luscombe","year":"2004","journal-title":"Can. J. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Choi, H., and Jeong, J. (2019). Speckle noise reduction technique for SAR images using statistical characteristics of speckle noise and discrete wavelet transform. Remote Sens., 11.","DOI":"10.3390\/rs11101184"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1017\/aog.2020.45","article-title":"Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle","volume":"61","author":"Lohse","year":"2020","journal-title":"Ann. Glaciol."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, T., Spreen, G., Melsheimer, C., Huntemann, M., Hughes, N., Zhang, S., and Li, F. (2021). Sea ice and water classification on dual-polarized Sentinel-1 imagery during melting season. Cryosphere Discuss., 1\u201326.","DOI":"10.5194\/tc-2021-85"},{"key":"ref_47","first-page":"1","article-title":"Arctic sea ice cover data from spaceborne SAR by deep learning","volume":"2020","author":"Wang","year":"2020","journal-title":"Earth Syst. Sci. Data Discuss"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"2839","DOI":"10.1016\/j.patcog.2015.03.009","article-title":"Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation","volume":"48","author":"Wong","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_49","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst., 25."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_51","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, PMLR, Lille, France."},{"key":"ref_52","unstructured":"Xu, B., Wang, N., Chen, T., and Li, M. (2015). Empirical evaluation of rectified activations in convolutional network. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7\u201313). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_54","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Hoekstra, M., Jiang, M., Clausi, D.A., and Duguay, C. (2020). Lake Ice-Water Classification of RADARSAT-2 Images by Integrating IRGS Segmentation with Pixel-Based Random Forest Labeling. Remote Sens., 12.","DOI":"10.3390\/rs12091425"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1109\/JSTARS.2018.2889798","article-title":"Sea Ice Classification Using TerraSAR-X ScanSAR Data With Removal of Scalloping and Interscan Banding","volume":"12","author":"Zhang","year":"2019","journal-title":"IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/13\/3025\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:39:01Z","timestamp":1760139541000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/13\/3025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,24]]},"references-count":56,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["rs14133025"],"URL":"https:\/\/doi.org\/10.3390\/rs14133025","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,24]]}}}