{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T04:00:45Z","timestamp":1774324845994,"version":"3.50.1"},"reference-count":40,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"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":["4000132124\/20\/I-DT"],"award-info":[{"award-number":["4000132124\/20\/I-DT"]}],"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>The Copernicus Sentinel-2 mission operated by the European Space Agency (ESA) provides comprehensive and continuous multi-spectral observations of all the Earth\u2019s land surface since mid-2015. Clouds and cloud shadows significantly decrease the usability of optical satellite data, especially in agricultural applications; therefore, an accurate and reliable cloud mask is mandatory for effective EO optical data exploitation. During the last few years, image segmentation techniques have developed rapidly with the exploitation of neural network capabilities. With this perspective, the KappaMask processor using U-Net architecture was developed with the ability to generate a classification mask over northern latitudes into the following classes: clear, cloud shadow, semi-transparent cloud (thin clouds), cloud and invalid. For training, a Sentinel-2 dataset covering the Northern European terrestrial area was labelled. KappaMask provides a 10 m classification mask for Sentinel-2 Level-2A (L2A) and Level-1C (L1C) products. The total dice coefficient on the test dataset, which was not seen by the model at any stage, was 80% for KappaMask L2A and 76% for KappaMask L1C for clear, cloud shadow, semi-transparent and cloud classes. A comparison with rule-based cloud mask methods was then performed on the same test dataset, where Sen2Cor reached 59% dice coefficient for clear, cloud shadow, semi-transparent and cloud classes, Fmask reached 61% for clear, cloud shadow and cloud classes and Maja reached 51% for clear and cloud classes. The closest machine learning open-source cloud classification mask, S2cloudless, had a 63% dice coefficient providing only cloud and clear classes, while KappaMask L2A, with a more complex classification schema, outperformed S2cloudless by 17%.<\/jats:p>","DOI":"10.3390\/rs13204100","type":"journal-article","created":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T21:48:39Z","timestamp":1634161719000},"page":"4100","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["KappaMask: AI-Based Cloudmask Processor for Sentinel-2"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5414-6089","authenticated-orcid":false,"given":"Marharyta","family":"Domnich","sequence":"first","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"},{"name":"Institute of Computer Science, University of Tartu Estonia, 51009 Tartu, Estonia"}]},{"given":"Indrek","family":"S\u00fcnter","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"}]},{"given":"Heido","family":"Trofimov","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"}]},{"given":"Olga","family":"Wold","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"}]},{"given":"Fariha","family":"Harun","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"}]},{"given":"Anton","family":"Kostiukhin","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"}]},{"given":"Mihkel","family":"J\u00e4rveoja","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"}]},{"given":"Mihkel","family":"Veske","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"}]},{"given":"Tanel","family":"Tamm","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"}]},{"given":"Kaupo","family":"Voormansik","sequence":"additional","affiliation":[{"name":"KappaZeta Ltd., 51007 Tartu, Estonia"},{"name":"Tartu Observatory, University of Tartu, 61602 T\u00f5ravere, Estonia"}]},{"given":"Aire","family":"Olesk","sequence":"additional","affiliation":[{"name":"Tartu Observatory, University of Tartu, 61602 T\u00f5ravere, Estonia"}]},{"given":"Valentina","family":"Boccia","sequence":"additional","affiliation":[{"name":"European Space Agency, ESA-ESRIN, Largo Galileo Galilei, 1, 00044 Frascati, RM, Italy"}]},{"given":"Nicolas","family":"Longepe","sequence":"additional","affiliation":[{"name":"European Space Agency, ESA-ESRIN, Largo Galileo Galilei, 1, 00044 Frascati, RM, Italy"}]},{"given":"Enrico Giuseppe","family":"Cadau","sequence":"additional","affiliation":[{"name":"European Space Agency, ESA-ESRIN, Largo Galileo Galilei, 1, 00044 Frascati, RM, Italy"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Main-Knorn, M., Pflug, B., Louis, J., Debaecker, V., M\u00fcller-Wilm, U., and Gascon, F. (2017, January 4). Sen2Cor for Sentinel-2. Proceedings of the Image and Signal Processing for Remote Sensing XXIII, Warsaw, Poland.","DOI":"10.1117\/12.2278218"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"111205","DOI":"10.1016\/j.rse.2019.05.024","article-title":"Fmask 4.0: Improved cloud and cloud shadow detection in Landsats 4\u20138 and Sentinel-2 imagery","volume":"231","author":"Qiu","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_3","unstructured":"Hagolle, O., Huc, M., Pascual, D.V., and Dedieu, G. (2021, October 10). MAJA. Available online: https:\/\/github.com\/CNES\/MAJA."},{"key":"ref_4","unstructured":"Zupanc, A. (2020, November 18). Improving Cloud Detection with Machine Learning. Available online: https:\/\/medium.com\/sentinel-hub\/improving-cloud-detection-with-machine-learning-c09dc5d7cf13."},{"key":"ref_5","unstructured":"(2020, November 22). FastAI. Available online: https:\/\/github.com\/fastai\/fastai."},{"key":"ref_6","unstructured":"(2021, October 10). LightGBM. Available online: https:\/\/lightgbm.readthedocs.io\/en\/latest\/."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Dr\u00f6nner, J., Korfhage, N., Egli, S., M\u00fchling, M., Thies, B., Bendix, J., Freisleben, B., and Seeger, B. (2018). Fast Cloud Segmentation Using Convolutional Neural Networks. Remote Sens., 10.","DOI":"10.3390\/rs10111782"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"111203","DOI":"10.1016\/j.rse.2019.05.022","article-title":"Multi-sensor cloud and cloud shadow segmentation with a convolutional neural network","volume":"230","author":"Wieland","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.rse.2019.03.039","article-title":"A cloud detection algorithm for satellite imagery based on deep learning","volume":"229","author":"Jeppesen","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/j.rse.2017.03.026","article-title":"Cloud detection algorithm comparison and validation for operational Landsat data products","volume":"194","author":"Foga","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_11","unstructured":"(2021, October 10). L8 SPARCS Cloud Validation Masks, Available online: https:\/\/www.usgs.gov\/core-science-systems\/nli\/landsat."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.isprsjprs.2019.02.017","article-title":"Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors","volume":"150","author":"Li","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1600","DOI":"10.1109\/LGRS.2018.2846802","article-title":"Cloud and cloud shadow detection using multilevel feature fused segmentation network","volume":"15","author":"Yan","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2218","DOI":"10.1109\/TGRS.2008.2010404","article-title":"Active Learning Methods for Remote Sensing Image Classification","volume":"47","author":"Tuia","year":"2009","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Baetens, L., Desjardins, C., and Hagolle, O. (2019). Validation of copernicus Sentinel-2 cloud masks obtained from MAJA, Sen2Cor, and FMask processors using reference cloud masks generated with a supervised active learning procedure. Remote Sens., 11.","DOI":"10.3390\/rs11040433"},{"key":"ref_17","unstructured":"Baetens, L., and Hagolle, O. (2020, November 18). Sentinel-2 Reference Cloud Masks Generated by an Active Learning Method. Available online: https:\/\/zenodo.org\/record\/1460961#.YWMSJ9pByUk."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, J., Wu, Z., Hu, Z., Jian, C., Luo, S., Mou, L., Zhu, X.X., and Molinier, M. (2021). A Lightweight Deep Learning-Based Cloud Detection Method for Sentinel-2A Imagery Fusing Multiscale Spectral and Spatial Features. IEEE Trans. Geosci. Remote Sens., 1\u201319.","DOI":"10.1109\/TGRS.2021.3069641"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1109\/LGRS.2019.2955071","article-title":"Self-Attentive Generative Adversarial Network for Cloud Detection in High Resolution Remote Sensing Images","volume":"17","author":"Wu","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_20","unstructured":"(2021, October 10). KappaMask Predictor. Available online: https:\/\/github.com\/kappazeta\/cm_predict."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"L\u00f3pez-Puigdollers, D., Mateo-Garc\u00eda, G., and G\u00f3mez-Chova, L. (2021). Benchmarking Deep Learning Models for Cloud Detection in Landsat-8 and Sentinel-2 Images. Remote Sens., 13.","DOI":"10.3390\/rs13050992"},{"key":"ref_22","unstructured":"(2020, November 19). CREODIAS. Available online: https:\/\/creodias.eu\/data-offer."},{"key":"ref_23","unstructured":"(2021, January 18). Data and Information Access Services (DIAS). Available online: https:\/\/www.copernicus.eu\/en\/access-data\/dias."},{"key":"ref_24","unstructured":"(2021, October 10). Copernicus Open Access Hub. Available online: https:\/\/scihub.copernicus.eu\/."},{"key":"ref_25","unstructured":"(2020, November 19). PEPS: French Access to the Sentinel Products. Available online: https:\/\/peps.cnes.fr\/rocket\/#\/home."},{"key":"ref_26","unstructured":"(2020, November 19). The Finnish Data Hub. Available online: https:\/\/nsdc.fmi.fi\/services\/service_finhub_overview."},{"key":"ref_27","unstructured":"Francis, A. (2021, March 07). Sentinel-2 Cloud Mask Catalogue. Available online: https:\/\/zenodo.org\/record\/4172871#.X6popcgzZaR."},{"key":"ref_28","unstructured":"(2021, October 10). Sentinel-2 KappaZeta Cloud and Cloud Shadow Masks. Available online: https:\/\/zenodo.org\/record\/5095024#.YQTuzI4zaUk."},{"key":"ref_29","unstructured":"(2021, October 10). Computer Vision Annotation Tool. Available online: https:\/\/cvat.org\/."},{"key":"ref_30","unstructured":"(2021, October 10). Segments.ai Dataset Tool. Available online: https:\/\/segments.ai\/."},{"key":"ref_31","unstructured":"Francis, A. (2021, October 10). \u2018IRIS Toolkit\u2019. Available online: https:\/\/github.com\/ESA-PhiLab\/iris."},{"key":"ref_32","unstructured":"(2021, October 10). CEOS-WGCV ACIX II CMIX Atmospheric Correction Inter-Comparison Exercise Cloud Masking Inter-Comparison Exercise 2nd Workshop. Available online: https:\/\/earth.esa.int\/eogateway\/events\/ceos-wgcv-acix-ii-cmix-atmospheric-correction-inter-comparison-exercise-cloud-masking-inter-comparison-exercise-2nd-workshop."},{"key":"ref_33","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"},{"key":"ref_34","unstructured":"Kingma, D.P., and Ba, J. (2021, October 10). \u2018Adam: A Method for Stochastic Optimization\u2019. Available online: https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., and Jorge Cardoso, M. (2017). Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations. BT\u2014Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer.","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref_36","unstructured":"(2021, October 10). KappaMask Comparison with Rule-Based Methods. Available online: https:\/\/kappazeta.ee\/cloudcomparison."},{"key":"ref_37","first-page":"1","article-title":"All Models are Wrong, but Many are Useful: Learning a Variable\u2019s Importance by Studying an Entire Class of Prediction Models Simultaneously","volume":"20","author":"Fisher","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","article-title":"Unet++: Redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_39","unstructured":"Hoffer, E., Hubara, I., and Soudry, D. (2021, October 10). Train Longer, Generalize Better: Closing the Generalization Gap in Large Batch Training of Neural Networks. Available online: http:\/\/arxiv.org\/abs\/1705.08741."},{"key":"ref_40","unstructured":"University of Tartu (2021, October 10). \u201cUT Rocket\u201d. share.neic.no. Available online: https:\/\/share.neic.no\/marketplace-public-offering\/c8107e145e0d41f7a016b72825072287\/."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/20\/4100\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:12:43Z","timestamp":1760166763000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/20\/4100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,13]]},"references-count":40,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["rs13204100"],"URL":"https:\/\/doi.org\/10.3390\/rs13204100","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,13]]}}}