{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:10:49Z","timestamp":1775913049723,"version":"3.50.1"},"reference-count":54,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2018,11,10]],"date-time":"2018-11-10T00:00:00Z","timestamp":1541808000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["FR-791\/15-1, SE-553\/7-2"],"award-info":[{"award-number":["FR-791\/15-1, SE-553\/7-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Information about clouds is important for observing and predicting weather and climate as well as for generating and distributing solar power. Most existing approaches extract cloud information from satellite data by classifying individual pixels instead of using closely integrated spatial information, ignoring the fact that clouds are highly dynamic, spatially continuous entities. This paper proposes a novel cloud classification method based on deep learning. Relying on a Convolutional Neural Network (CNN) architecture for image segmentation, the presented Cloud Segmentation CNN (CS-CNN), classifies all pixels of a scene simultaneously rather than individually. We show that CS-CNN can successfully process multispectral satellite data to classify continuous phenomena such as highly dynamic clouds. The proposed approach produces excellent results on Meteosat Second Generation (MSG) satellite data in terms of quality, robustness, and runtime compared to other machine learning methods such as random forests. In particular, comparing CS-CNN with the CLAAS-2 cloud mask derived from MSG data shows high accuracy (0.94) and Heidke Skill Score (0.90) values. In contrast to a random forest, CS-CNN produces robust results and is insensitive to challenges created by coast lines and bright (sand) surface areas. Using GPU acceleration, CS-CNN requires only 25 ms of computation time for classification of images of Europe with     508 \u00d7 508     pixels.<\/jats:p>","DOI":"10.3390\/rs10111782","type":"journal-article","created":{"date-parts":[[2018,11,14]],"date-time":"2018-11-14T02:42:41Z","timestamp":1542163361000},"page":"1782","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":94,"title":["Fast Cloud Segmentation Using Convolutional Neural Networks"],"prefix":"10.3390","volume":"10","author":[{"given":"Johannes","family":"Dr\u00f6nner","sequence":"first","affiliation":[{"name":"Department of Mathmatics and Computer Science, University of Marburg, 35043 Marburg, Germany"}]},{"given":"Nikolaus","family":"Korfhage","sequence":"additional","affiliation":[{"name":"Department of Mathmatics and Computer Science, University of Marburg, 35043 Marburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4050-226X","authenticated-orcid":false,"given":"Sebastian","family":"Egli","sequence":"additional","affiliation":[{"name":"Laboratory for Climatology and Remote Sensing, University of Marburg, 35037 Marburg, Germany"}]},{"given":"Markus","family":"M\u00fchling","sequence":"additional","affiliation":[{"name":"Department of Mathmatics and Computer Science, University of Marburg, 35043 Marburg, Germany"}]},{"given":"Boris","family":"Thies","sequence":"additional","affiliation":[{"name":"Laboratory for Climatology and Remote Sensing, University of Marburg, 35037 Marburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6559-2033","authenticated-orcid":false,"given":"J\u00f6rg","family":"Bendix","sequence":"additional","affiliation":[{"name":"Laboratory for Climatology and Remote Sensing, University of Marburg, 35037 Marburg, Germany"}]},{"given":"Bernd","family":"Freisleben","sequence":"additional","affiliation":[{"name":"Department of Mathmatics and Computer Science, University of Marburg, 35043 Marburg, Germany"}]},{"given":"Bernhard","family":"Seeger","sequence":"additional","affiliation":[{"name":"Department of Mathmatics and Computer Science, University of Marburg, 35043 Marburg, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2018,11,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1016\/j.renene.2016.08.013","article-title":"Critical weather situations for renewable energies\u2014Part B: Low stratus risk for solar power","volume":"101","author":"Steiner","year":"2017","journal-title":"Renew. Energy"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"229","DOI":"10.3112\/erdkunde.2011.03.01","article-title":"Fog\u2014Boon or bane?","volume":"65","author":"Bendix","year":"2011","journal-title":"Erdkunde"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1175\/BAMS-D-12-00117.1","article-title":"Assessment of Global Cloud Datasets from Satellites: Project and Database Initiated by the GEWEX Radiation Panel","volume":"94","author":"Stubenrauch","year":"2013","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1038\/nature18273","article-title":"Evidence for climate change in the satellite cloud record","volume":"536","author":"Norris","year":"2016","journal-title":"Nature"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1175\/2009JAMC2103.1","article-title":"Comparison of GOES cloud classification algorithms employing explicit and implicit physics","volume":"48","author":"Bankert","year":"2009","journal-title":"J. Appl. Meteorol. Climatol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1002\/met.288","article-title":"Satellite based remote sensing of weather and climate: Recent achievements and future perspectives","volume":"18","author":"Thies","year":"2011","journal-title":"Meteorol. Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1016\/j.solener.2012.11.015","article-title":"Equipment and methodologies for cloud detection and classification: A review","volume":"95","author":"Tapakis","year":"2013","journal-title":"Sol. Energy"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Egli, S., Thies, B., and Bendix, J. (2018). A hybrid approach for fog retrieval based on a combination of satellite and ground truth data. Remote Sens., 10.","DOI":"10.3390\/rs10040628"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_10","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). ImageNet Classification with Deep Convolutional Neural Networks. Proceedings of the Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, NV, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the 2015 IEEE International Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_12","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume":"Volume 9351","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention (MICCAI)"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wu, L., Xie, Z., and Chen, Z. (2018). Building extraction in very high resolution remote sensing imagery using deep learning and guided filters. Remote Sens., 10.","DOI":"10.3390\/rs10010144"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1175\/BAMS-83-7-Schmetz-2","article-title":"An introduction to Meteosat Second Generation (MSG)","volume":"83","author":"Schmetz","year":"2002","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1080\/01431168808954841","article-title":"An improved method for detecting clear sky and cloudy radiances from AVHRR data","volume":"9","author":"Saunders","year":"1988","journal-title":"Int. J. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1007\/s00024-007-0213-8","article-title":"Dynamical nighttime fog\/low stratus detection based on Meteosat SEVIRI data: A feasibility study","volume":"164","author":"Cermak","year":"2007","journal-title":"Pure Appl. Geophys."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1016\/j.solener.2003.07.038","article-title":"Operational method for deriving high resolution direct normal irradiance from satellite data","volume":"76","author":"Schillings","year":"2004","journal-title":"Sol. Energy"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"32141","DOI":"10.1029\/1998JD200032","article-title":"Discriminating clear sky from clouds with MODIS","volume":"103","author":"Ackerman","year":"1998","journal-title":"J. Geophys. Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"881","DOI":"10.5194\/essd-9-881-2017","article-title":"Cloud property datasets retrieved from AVHRR, MODIS, AATSR and MERIS in the framework of the Cloud_cci project","volume":"9","author":"Stengel","year":"2017","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"415","DOI":"10.5194\/essd-9-415-2017","article-title":"The MSG-SEVIRI-based cloud property data record CLAAS-2","volume":"9","author":"Benas","year":"2017","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1002\/met.239","article-title":"Cloud detection in Meteosat Second Generation imagery at the Met Office","volume":"18","author":"Hocking","year":"2010","journal-title":"Meteorol. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2016.01.011","article-title":"Random forest in remote sensing: A review of applications and future directions","volume":"114","author":"Belgiu","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1175\/1520-0426(2004)021<0159:CCOSRD>2.0.CO;2","article-title":"Cloud Classification of Satellite Radiance Data by Multicategory Support Vector Machines","volume":"21","author":"Lee","year":"2004","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hollstein, A., Segl, K., Guanter, L., Brell, M., and Enesco, M. (2016). Ready-to-use methods for the detection of clouds, cirrus, snow, shadow, water and clear sky pixels in Sentinel-2 MSI images. Remote Sens., 8.","DOI":"10.3390\/rs8080666"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1016\/j.atmosres.2015.09.021","article-title":"Comparison of four machine learning algorithms for their applicability in satellite-based optical rainfall retrievals","volume":"169","author":"Meyer","year":"2016","journal-title":"Atmos. Res."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.3390\/rs70201529","article-title":"Multilayer Perceptron Neural Networks Model for Meteosat Second Generation SEVIRI Daytime Cloud Masking","volume":"7","author":"Taravat","year":"2015","journal-title":"Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1049\/ip-f-2.1989.0037","article-title":"Comparison of techniques for measuring cloud texture in remotely sensed satellite meteorological image data","volume":"136","author":"Gu","year":"1989","journal-title":"IEE Proc. F Radar Signal Process."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4491","DOI":"10.1080\/01431160410001735120","article-title":"Cloud classification using the textural features of Meteosat images","volume":"25","author":"Ameur","year":"2004","journal-title":"Int. J. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1080\/19475705.2011.578263","article-title":"A texton-based cloud detection algorithm for MSG-SEVIRI multispectral images","volume":"2","author":"Ganci","year":"2011","journal-title":"Geomat. Nat. Hazards Risk"},{"key":"ref_31","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Le Goff, M., Tourneret, J.Y., Wendt, H., Ortner, M., and Spigai, M. (2017, January 11\u201313). Deep Learning for Cloud Detection. Proceedings of the 8th International Conference of Pattern Recognition Systems (ICPRS 2017), Madrid, Spain.","DOI":"10.1049\/cp.2017.0139"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3631","DOI":"10.1109\/JSTARS.2017.2686488","article-title":"Multilevel Cloud Detection in Remote Sensing Images Based on Deep Learning","volume":"10","author":"Xie","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_34","unstructured":"Li, F., and Taylor, G. (2015, January 7\u201312). Alter-CNN: An Approach to Learning from Label Proportions with Application to Ice-Water Classification. Proceedings of the Neural Information Processing Systems 28 (NIPS) Deep Learning and Representation Learning Workshop on Learning and Privacy with Incomplete Data and Weak Supervision, Montr\u00e9al, QC, Canada."},{"key":"ref_35","unstructured":"Castelluccio, M., Poggi, G., Sansone, C., and Verdoliva, L. (arXiv, 2015). Land Use Classification in Remote Sensing Images by Convolutional Neural Networks, arXiv."},{"key":"ref_36","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":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., and Han, B. (2015, January 13\u201316). Learning deconvolution network for semantic segmentation. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref_38","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_39","doi-asserted-by":"crossref","unstructured":"Wu, G., Shao, X., Guo, Z., Chen, Q., Yuan, W., Shi, X., Xu, Y., and Shibasaki, R. (2018). Automatic Building Segmentation of Aerial Imagery Using Multi-Constraint Fully Convolutional Networks. Remote Sens., 10.","DOI":"10.3390\/rs10030407"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Alonso, I., Cambra, A.B., Munoz, A., Treibitz, T., and Murillo, A.C. (2017, January 22\u201329). Coral-Segmentation: Training Dense Labeling Models with Sparse Ground Truth. Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy.","DOI":"10.1109\/ICCVW.2017.339"},{"key":"ref_41","unstructured":"EUMETSAT (2010). MSG Level 1.5 Image Data Format Description, European Organisation for the Exploitation of Meteorological Satellites. Technical Report."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1002\/qj.2941","article-title":"A 10 year fog and low stratus climatology for Europe based on Meteosat Second Generation data","volume":"143","author":"Egli","year":"2017","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_43","unstructured":"EUMETSAT (2012). Effective Radiance and Brightness Temperature Relation Tables for Meteosat Second Generation, European Organisation for the Exploitation of Meteorological Satellites. Technical Report."},{"key":"ref_44","unstructured":"EUMETSAT (2012). The Conversion from Effective Radiances to Equivalent Brightness Temperatures, European Organisation for the Exploitation of Meteorological Satellites. Technical Report."},{"key":"ref_45","unstructured":"CM SAF (2016). Algorithm Theoretical Basis Document SEVIRI Cloud Physical Products CLAAS Edition 2, SAF\/CM\/KNMI\/ATBD\/SEVIRI\/CPP; Satellite Application Facility on Climate Monitoring (CM SAF). Technical Report 2.2."},{"key":"ref_46","unstructured":"Derrien, M., Gl\u00e9au, H., and Fernandez, P. (2013). Algorithm Theoretical Basis Document for Cloud Products (CMa-PGE01 v3. 2, CT-PGE02 v2. 2 & CTTHPGE03 v2. 2), NWC SAF. SAF\/NWC\/CDOP2\/MFL\/SCI\/ATBD\/01."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. (2014, January 3\u20137). Caffe: Convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM international conference on Multimedia, Orlando, FL, USA.","DOI":"10.1145\/2647868.2654889"},{"key":"ref_48","unstructured":"Kingma, D.P., and Ba, J. (arXiv, 2014). Adam: A method for stochastic optimization, arXiv."},{"key":"ref_49","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_50","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_51","unstructured":"Jolliffe, I.T., and Stephenson, D.B. (2003). Forecast Verification: A Practitioner\u2019s Guide in Atmospheric Science, John Wiley & Sons."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Beusch, L., Foresti, L., Gabella, M., and Hamann, U. (2018). Satellite-based rainfall retrieval: From generalized linear models to artificial neural networks. Remote Sens., 10.","DOI":"10.3390\/rs10060939"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Schulz, H., Waldvogel, B., Sheikh, R., and Behnke, S. (2015, January 11\u201314). CURFIL: Random Forests for Image Labeling on GPU. Proceedings of the 10th International Conference on Computer Vision Theory and Applications, Berlin, Germany.","DOI":"10.5220\/0005316201560164"},{"key":"ref_54","unstructured":"Beilschmidt, C., Dr\u00f6nner, J., Mattig, M., and Seeger, B. (2017, January 21\u201324). VAT: A System for Data-Driven Biodiversity Research. Proceedings of the 20th International Conference on Extending Database Technology (EDBT 2017), Venice, Italy."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/11\/1782\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:29:00Z","timestamp":1760196540000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/11\/1782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,10]]},"references-count":54,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2018,11]]}},"alternative-id":["rs10111782"],"URL":"https:\/\/doi.org\/10.3390\/rs10111782","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,10]]}}}