{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T04:03:27Z","timestamp":1783915407269,"version":"3.55.0"},"reference-count":42,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T00:00:00Z","timestamp":1566518400000},"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>The Sentinel-2 satellite mission offers high resolution multispectral time-series image data, enabling the production of detailed land cover maps globally. When mapping large territories, the trade-off between processing time and result quality is a central design decision. Currently, this machine learning task is usually performed using pixel-wise classification methods. However, the radical shift of the computer vision field away from hand-engineered image features and towards more automation by representation learning comes with many promises, including higher quality results and less engineering effort. In particular, convolutional neural networks learn features which take into account the context of the pixels and, therefore, a better representation of the data can be obtained. In this paper, we assess fully convolutional neural network architectures as replacements for a Random Forest classifier in an operational context for the production of high resolution land cover maps with Sentinel-2 time-series at the country scale. Our contributions include a framework for working with Sentinel-2 L2A time-series image data, an adaptation of the U-Net model (a fully convolutional neural network) for dealing with sparse annotation data while maintaining high resolution output, and an analysis of those results in the context of operational production of land cover maps. We conclude that fully convolutional neural networks can yield improved results with respect to pixel-wise Random Forest classifiers for classes where texture and context are pertinent. However, this new approach shows higher variability in quality across different landscapes and comes with a computational cost which could be to high for operational systems.<\/jats:p>","DOI":"10.3390\/rs11171986","type":"journal-article","created":{"date-parts":[[2019,8,26]],"date-time":"2019-08-26T04:38:23Z","timestamp":1566794303000},"page":"1986","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":101,"title":["Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems"],"prefix":"10.3390","volume":"11","author":[{"given":"Andrei","family":"Stoian","sequence":"first","affiliation":[{"name":"Thales\/SIX\/ThereSiS, 91477 Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Poulain","sequence":"additional","affiliation":[{"name":"Thales Services, 31555 Toulouse, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6896-0049","authenticated-orcid":false,"given":"Jordi","family":"Inglada","sequence":"additional","affiliation":[{"name":"Centre d\u2019Etudes Spatiales de la BIOsphere (CESBIO), Universit\u00e9 de Toulouse, CNES\/CNRS\/IRD\/UPS\/INRA, 31555 Toulouse, France"},{"name":"Centre National d\u2019Etudes Spatiales (CNES), 31555 Toulouse, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7758-0985","authenticated-orcid":false,"given":"Victor","family":"Poughon","sequence":"additional","affiliation":[{"name":"Centre National d\u2019Etudes Spatiales (CNES), 31555 Toulouse, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawa","family":"Derksen","sequence":"additional","affiliation":[{"name":"Centre d\u2019Etudes Spatiales de la BIOsphere (CESBIO), Universit\u00e9 de Toulouse, CNES\/CNRS\/IRD\/UPS\/INRA, 31555 Toulouse, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,8,23]]},"reference":[{"key":"ref_1","unstructured":"Heymann, Y. (1994). CORINE Land Cover: Technical Guide, Office for Official Publications of the European Communities."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Arino, O., Gross, D., Ranera, F., Leroy, M., Bicheron, P., Brockman, C., Defourny, P., Vancutsem, C., Achard, F., and Durieux, L. (2007, January 23\u201328). GlobCover: ESA service for global land cover from MERIS. Proceedings of the 2007 IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain.","DOI":"10.1109\/IGARSS.2007.4423328"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.rse.2011.11.026","article-title":"Sentinel-2: ESA\u2019s Optical High-Resolution Mission for GMES Operational Services","volume":"120","author":"Drusch","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.3390\/rs70201482","article-title":"Meeting Earth Observation Requirements for Global Agricultural Monitoring: An Evaluation of the Revisit Capabilities of Current and Planned Moderate Resolution Optical Earth Observing Missions","volume":"7","author":"Whitcraft","year":"2015","journal-title":"Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.isprsjprs.2014.09.002","article-title":"Global Land Cover Mapping At 30m Resolution: A Pok-Based Operational Approach","volume":"103","author":"Chen","year":"2015","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_6","unstructured":"Inglada, J., Vincent, A., and Thierion, V. (2019, August 22). Theia Oso Land Cover Map 2106. Available online: https:\/\/zenodo.org\/record\/1048161."},{"key":"ref_7","unstructured":"Inglada, J., Vincent, A., and Thierion, V. (2019, August 22). 2017 Metropolitan France Land Cover Map\u2014CESBIO-OSO. Available online: https:\/\/zenodo.org\/record\/1993595."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Inglada, J., Vincent, A., Arias, M., Tardy, B., Morin, D., and Rodes, I. (2017). Operational High Resolution Land Cover Map Production At the Country Scale Using Satellite Image Time Series. Remote Sens., 9.","DOI":"10.3390\/rs9010095"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1046\/j.1365-2699.1999.00139.x","article-title":"Global Land Cover Characterization From Satellite Data: From Research To Operational Implementation. GCTE\/LUCC Research Review","volume":"8","author":"Defries","year":"1999","journal-title":"Glob. Ecol. Biogeogr."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.rse.2011.08.024","article-title":"A Review of Large Area Monitoring of Land Cover Change Using Landsat Data","volume":"122","author":"Hansen","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MGRS.2017.2762307","article-title":"Deep learning in remote sensing: A comprehensive review and list of resources","volume":"5","author":"Zhu","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_12","unstructured":"Badrinarayanan, V., Kendall, A., and Cipolla, R. (2015). Segnet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. CoRR."},{"key":"ref_13","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_14","doi-asserted-by":"crossref","first-page":"183","DOI":"10.5194\/isprs-annals-IV-1-W1-183-2017","article-title":"Investigating the potential of deep neural networks for large-scale classification of very high resolution satellite images","volume":"IV-1\/W1","author":"Postadjian","year":"2017","journal-title":"ISPRS Ann. Photogramm. Remote. Sens. Spat. Inf. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Maggiolo, L., Marcos, D., Moser, G., and Tuia, D. (2018, January 22\u201327). Improving Maps from Cnns Trained with Sparse, Scribbled Ground Truths Using Fully Connected Crfs. Proceedings of the IGARSS 2018\u20142018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8517947"},{"key":"ref_16","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2016). Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected Crfs. CoRR."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1109\/TGRS.2016.2616585","article-title":"Dense Semantic Labeling of Subdecimeter Resolution Images With Convolutional Neural Networks","volume":"55","author":"Volpi","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., Jia, J., He, K., and Sun, J. (2016, January 27\u201330). ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.344"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.isprsjprs.2017.11.009","article-title":"Classification with an Edge: Improving Semantic Image Segmentation With Boundary Detection","volume":"135","author":"Marmanis","year":"2018","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_20","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_21","doi-asserted-by":"crossref","unstructured":"Fu, T., Ma, L., Li, M., and Johnson, B.A. (2018). Using Convolutional Neural Network To Identify Irregular Segmentation Objects From Very High-Resolution Remote Sensing Imagery. J. Appl. Remote Sens., 12.","DOI":"10.1117\/1.JRS.12.025010"},{"key":"ref_22","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_23","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/LGRS.2017.2681128","article-title":"Deep learning classification of land cover and crop types using remote sensing data","volume":"14","author":"Kussul","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ji, S., Zhang, C., Xu, A., Shi, Y., and Duan, Y. (2018). 3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images. Remote Sens., 10.","DOI":"10.3390\/rs10010075"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mou, L., Bruzzone, L., and Zhu, X.X. (2018). Learning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery. arXiv.","DOI":"10.1109\/TGRS.2018.2863224"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ienco, D., Gaetano, R., Dupaquier, C., and Maurel, P. (2017). Land Cover Classification Via Multitemporal Spatial Data By Deep Recurrent Neural Networks. IEEE Geosci. Remote. Sens. Lett.","DOI":"10.1109\/LGRS.2017.2728698"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"12242","DOI":"10.3390\/rs70912242","article-title":"SPOT4 (Take5): Simulation of Sentinel-2 Time Series on 45 Large sites","volume":"7","author":"Hagolle","year":"2015","journal-title":"Remote Sens."},{"key":"ref_28","unstructured":"Bossard, M., Feranec, J., and Otahel, J. (2000). CORINE Land Cover Technical Guide. Addendum 2000, European Environment Agency."},{"key":"ref_29","unstructured":"Maugeais, E., Lecordix, F., Halbecq, X., and Braun, A. (2011, January 3\u20138). D\u00e9rivation cartographique multi \u00e9chelles de la BDTopo de l\u2019IGN France: Mise en \u0153uvre du processus de production de la Nouvelle Carte de Base. Proceedings of the 25th International Cartographic Conference, Paris, France."},{"key":"ref_30","unstructured":"Cantelaube, P., and Carles, M. (2014). Le Registre Parcellaire Graphique: Des donn\u00e9es g\u00e9ographiques pour d\u00e9crire la couverture du sol agricole. Le Cahier des Techniques de l\u2019INRA, 58\u201364."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"537","DOI":"10.3189\/2014JoG13J176","article-title":"The Randolph Glacier Inventory: A Globally Complete Inventory of Glaciers","volume":"60","author":"Pfeffer","year":"2014","journal-title":"J. Glaciol."},{"key":"ref_32","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D., Wong, W., and Woo, W. (2015). Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. arXiv."},{"key":"ref_33","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. Lect. Notes Comput. Sci., 240\u2013248.","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref_34","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., and He, K. (2017). Accurate, large minibatch SGD: Training imagenet in 1 hour. arXiv."},{"key":"ref_35","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4407","DOI":"10.1080\/01431161.2011.552923","article-title":"Death To Kappa: Birth of Quantity Disagreement and Allocation Disagreement for Accuracy Assessment","volume":"32","author":"Pontius","year":"2011","journal-title":"Int. J. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2587","DOI":"10.1109\/TGRS.2006.875360","article-title":"A multilevel context-based system for classification of very high spatial resolution images","volume":"44","author":"Bruzzone","year":"2006","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"35","DOI":"10.5201\/ipol.2012.gjmr-lsd","article-title":"LSD: A line segment detector","volume":"2","author":"Jakubowicz","year":"2012","journal-title":"Image Process. Line"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Tardy, B., Inglada, J., and Michel, J. (2019). Assessment of Optimal Transport for Operational Land-Cover Mapping Using High-Resolution Satellite Images Time Series without Reference Data of the Mapping Period. Remote Sens., 11.","DOI":"10.3390\/rs11091047"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Richmond, D., Kainmueller, D., Yang, M., Myers, E., and Rother, C. (2016, January 19\u201322). Mapping Auto-Context Decision Forests to Deep Convnets for Semantic Segmentation. Proceedings of the British Machine Vision Conference 2016, York, UK.","DOI":"10.5244\/C.30.144"},{"key":"ref_41","unstructured":"Liu, H., Simonyan, K., and Yang, Y. (2018). Darts: Differentiable architecture search. arXiv."},{"key":"ref_42","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in Neural Information Processing Systems 30, Curran Associates, Inc."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/17\/1986\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:13:18Z","timestamp":1760188398000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/17\/1986"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,23]]},"references-count":42,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2019,9]]}},"alternative-id":["rs11171986"],"URL":"https:\/\/doi.org\/10.3390\/rs11171986","relation":{"has-preprint":[{"id-type":"doi","id":"10.20944\/preprints201906.0270.v1","asserted-by":"object"},{"id-type":"doi","id":"10.20944\/preprints201906.0270.v2","asserted-by":"object"}]},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,23]]}}}