{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:46:07Z","timestamp":1760143567208,"version":"build-2065373602"},"reference-count":35,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001858","name":"VINNOVA","doi-asserted-by":"publisher","award":["2021-03643","2023-02787"],"award-info":[{"award-number":["2021-03643","2023-02787"]}],"id":[{"id":"10.13039\/501100001858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Cloud formations often obscure optical satellite-based monitoring of the Earth\u2019s surface, thus limiting Earth observation (EO) activities such as land cover mapping, ocean color analysis, and cropland monitoring. The integration of machine learning (ML) methods within the remote sensing domain has significantly improved performance for a wide range of EO tasks, including cloud detection and filtering, but there is still much room for improvement. A key bottleneck is that ML methods typically depend on large amounts of annotated data for training, which are often difficult to come by in EO contexts. This is especially true when it comes to cloud optical thickness (COT) estimation. A reliable estimation of COT enables more fine-grained and application-dependent control compared to using pre-specified cloud categories, as is common practice. To alleviate the COT data scarcity problem, in this work, we propose a novel synthetic dataset for COT estimation, which we subsequently leverage for obtaining reliable and versatile cloud masks on real data. In our dataset, top-of-atmosphere radiances have been simulated for 12 of the spectral bands of the Multispectral Imagery (MSI) sensor onboard Sentinel-2 platforms. These data points have been simulated under consideration of different cloud types, COTs, and ground surface and atmospheric profiles. Extensive experimentation of training several ML models to predict COT from the measured reflectivity of the spectral bands demonstrates the usefulness of our proposed dataset. In particular, by thresholding COT estimates from our ML models, we show on two satellite image datasets (one that is publicly available, and one which we have collected and annotated) that reliable cloud masks can be obtained. The synthetic data, the newly collected real dataset, code and models have been made publicly available.<\/jats:p>","DOI":"10.3390\/rs16040694","type":"journal-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T06:00:25Z","timestamp":1708063225000},"page":"694","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI"],"prefix":"10.3390","volume":"16","author":[{"given":"Aleksis","family":"Pirinen","sequence":"first","affiliation":[{"name":"Department of Computer Science, RISE Research Institutes of Sweden, 501 15 Bor\u00e5s, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5922-7889","authenticated-orcid":false,"given":"Nosheen","family":"Abid","sequence":"additional","affiliation":[{"name":"Machine Learning, Department of Computer Science, Electrical and Space Engineering, Lule\u00e5 University of Technology, 971 87 Lule\u00e5, Sweden"}]},{"given":"Nuria Agues","family":"Paszkowsky","sequence":"additional","affiliation":[{"name":"Department of Computer Science, RISE Research Institutes of Sweden, 501 15 Bor\u00e5s, Sweden"}]},{"given":"Thomas Ohlson","family":"Timoudas","sequence":"additional","affiliation":[{"name":"Department of Computer Science, RISE Research Institutes of Sweden, 501 15 Bor\u00e5s, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3841-1721","authenticated-orcid":false,"given":"Ronald","family":"Scheirer","sequence":"additional","affiliation":[{"name":"Swedish Meteorological and Hydrological Institute, 601 76 Norrk\u00f6ping, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4767-9925","authenticated-orcid":false,"given":"Chiara","family":"Ceccobello","sequence":"additional","affiliation":[{"name":"AI Sweden, 417 56 Gothenburg, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0546-116X","authenticated-orcid":false,"given":"Gy\u00f6rgy","family":"Kov\u00e1cs","sequence":"additional","affiliation":[{"name":"Machine Learning, Department of Computer Science, Electrical and Space Engineering, Lule\u00e5 University of Technology, 971 87 Lule\u00e5, Sweden"}]},{"given":"Anders","family":"Persson","sequence":"additional","affiliation":[{"name":"The Swedish Forest Agency, 551 83 J\u00f6nk\u00f6ping, Sweden"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"key":"ref_1","first-page":"102568","article-title":"UCL: Unsupervised Curriculum Learning for water body classification from remote sensing imagery","volume":"105","author":"Abid","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_2","unstructured":"Mateo-Garcia, G., Oprea, S., Smith, L., Veitch-Michaelis, J., Schumann, G., Gal, Y., Baydin, A.G., and Backes, D. (2019). Flood detection on low cost orbital hardware. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Abid, N., Malik, M.I., Shahzad, M., Shafait, F., Ali, H., Ghaffar, M.M., Weis, C., Wehn, N., and Liwicki, M. (December, January 29). Burnt Forest Estimation from Sentinel-2 Imagery of Australia using Unsupervised Deep Learning. Proceedings of the 2021 Digital Image Computing: Techniques and Applications (DICTA), Gold Coast, Australia.","DOI":"10.1109\/DICTA52665.2021.9647174"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.rse.2006.06.004","article-title":"Retrieval of oceanic chlorophyll concentration with relevance vector machines","volume":"105","year":"2006","journal-title":"Remote Sens. Environ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.patrec.2005.08.004","article-title":"Urban monitoring using multi-temporal SAR and multi-spectral data","volume":"27","author":"Calpe","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"024019","DOI":"10.1088\/1748-9326\/ab68ac","article-title":"Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt","volume":"15","author":"Wolanin","year":"2020","journal-title":"Environ. Res. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4105","DOI":"10.1109\/TGRS.2007.905312","article-title":"Cloud-screening algorithm for ENVISAT\/MERIS multispectral images","volume":"45","author":"Guanter","year":"2007","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/j.rse.2014.12.014","article-title":"Improvement and expansion of the Fmask algorithm: Cloud, cloud shadow, and snow detection for Landsats 4\u20137, 8, and Sentinel 2 images","volume":"159","author":"Zhu","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_9","unstructured":"Louis, J., Debaecker, V., Pflug, B., Main-Knorn, M., Bieniarz, J., Mueller-Wilm, U., Cadau, E., and Gascon, F. (2016, January 9\u201313). Sentinel-2 Sen2Cor: L2A processor for users. Proceedings of the Living Planet Symposium 2016, Spacebooks Online, Prague, Czech Republik."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.isprsjprs.2019.11.024","article-title":"Transferring deep learning models for cloud detection between Landsat-8 and Proba-V","volume":"160","author":"Laparra","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11082-020-02500-8","article-title":"Lightweight U-Net for cloud detection of visible and thermal infrared remote sensing images","volume":"52","author":"Zhang","year":"2020","journal-title":"Opt. Quantum Electron."},{"key":"ref_12","first-page":"100417","article-title":"CloudX-net: A robust encoder-decoder architecture for cloud detection from satellite remote sensing images","volume":"20","author":"Kanu","year":"2020","journal-title":"Remote Sens. Appl. Soc. Environ."},{"key":"ref_13","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_14","doi-asserted-by":"crossref","first-page":"14301","DOI":"10.1029\/2001JD900130","article-title":"On the accuracy of the independent column approximation in calculating the downward fluxes in the UVA, UVB, and PAR spectral ranges","volume":"106","author":"Scheirer","year":"2001","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2620","DOI":"10.1175\/1520-0442(1995)008<2620:IODOBC>2.0.CO;2","article-title":"Inferring optical depth of broken clouds from Landsat data","volume":"8","author":"Liu","year":"1995","journal-title":"J. Clim."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"D14209","DOI":"10.1029\/2005JD006955","article-title":"Remote sensing of stratocumulus clouds: Uncertainties and biases due to inhomogeneity","volume":"111","author":"Zinner","year":"2006","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2227","DOI":"10.1175\/1520-0469(2002)059<2227:EOCHIO>2.0.CO;2","article-title":"Effects of cloud horizontal inhomogeneity on the optical thickness retrieved from moderate-resolution satellite data","volume":"59","author":"Iwabuchi","year":"2002","journal-title":"J. Atmos. Sci."},{"key":"ref_18","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","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, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4747","DOI":"10.5194\/amt-10-4747-2017","article-title":"Retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning","volume":"10","author":"Okamura","year":"2017","journal-title":"Atmos. Meas. Tech."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sde-Chen, Y., Schechner, Y.Y., Holodovsky, V., and Eytan, E. (2021, January 11\u201317). 3DeepCT: Learning volumetric scattering tomography of clouds. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00562"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3177","DOI":"10.5194\/amt-11-3177-2018","article-title":"Neural network cloud top pressure and height for MODIS","volume":"11","author":"Adok","year":"2018","journal-title":"Atmos. Meas. Tech."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2717","DOI":"10.5194\/gmd-11-2717-2018","article-title":"An update on the RTTOV fast radiative transfer model (currently at version 12)","volume":"11","author":"Saunders","year":"2018","journal-title":"Geosci. Model Dev."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1016\/j.rse.2008.11.007","article-title":"The ASTER spectral library version 2.0","volume":"113","author":"Baldridge","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"111196","DOI":"10.1016\/j.rse.2019.05.015","article-title":"The ECOSTRESS spectral library version 1.0","volume":"230","author":"Meerdink","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"9535","DOI":"10.5194\/acp-10-9535-2010","article-title":"Testing remote sensing on artificial observations: Impact of drizzle and 3-D cloud structure on effective radius retrievals","volume":"10","author":"Zinner","year":"2010","journal-title":"Atmos. Chem. Phys."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Domnich, M., S\u00fcnter, I., Trofimov, H., Wold, O., Harun, F., Kostiukhin, A., J\u00e4rveoja, M., Veske, M., Tamm, T., and Voormansik, K. (2021). KappaMask: Ai-based cloudmask processor for sentinel-2. Remote Sens., 13.","DOI":"10.3390\/rs13204100"},{"key":"ref_28","unstructured":"Chevallier, F., Di Michele, S., and McNally, A. (2006). Diverse Profile Datasets from the ECMWF 91-Level Short-Range Forecasts, European Centre for Medium-Range Weather Forecasts."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ikeuchi, K. (2014). Computer Vision: A Reference Guide, Springer.","DOI":"10.1007\/978-0-387-31439-6"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1175\/1520-0477(1998)079<0831:OPOAAC>2.0.CO;2","article-title":"Optical Properties of Aerosols and Clouds: The Software Package OPAC","volume":"79","author":"Hess","year":"1998","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_31","unstructured":"Segelstein, D. (1981). The Complex Refractive Index of Water, Department of Physics, University of Missouri-Kansas City."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1175\/2010JAMC2608.1","article-title":"Improvements in Shortwave Bulk Scattering and Absorption Models for the Remote Sensing of Ice Clouds","volume":"50","author":"Baum","year":"2011","journal-title":"J. Appl. Meteorol. Climatol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1175\/1520-0477(1999)080<2261:AIUCFI>2.0.CO;2","article-title":"Advances in understanding clouds from ISCCP","volume":"80","author":"Rossow","year":"1999","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_34","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_35","unstructured":"Wada, K. (2023, April 14). pytorch-fcn: PyTorch Implementation of Fully Convolutional Networks. Available online: https:\/\/github.com\/wkentaro\/pytorch-fcn."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/4\/694\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:00:32Z","timestamp":1760104832000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/4\/694"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,16]]},"references-count":35,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["rs16040694"],"URL":"https:\/\/doi.org\/10.3390\/rs16040694","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2024,2,16]]}}}