{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T22:16:39Z","timestamp":1776377799429,"version":"3.51.2"},"reference-count":47,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2020,12,28]],"date-time":"2020-12-28T00:00:00Z","timestamp":1609113600000},"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>Land cover and its change are crucial for many environmental applications. This study focuses on the land cover classification and change detection with multitemporal and multispectral Sentinel-2 satellite data. To address the challenging land cover change detection task, we rely on two different deep learning architectures and selected pre-processing steps. For example, we define an excluded class and deal with temporal water shoreline changes in the pre-processing. We employ a fully convolutional neural network (FCN), and we combine the FCN with long short-term memory (LSTM) networks. The FCN can only handle monotemporal input data, while the FCN combined with LSTM can use sequential information (multitemporal). Besides, we provided fixed and variable sequences as training sequences for the combined FCN and LSTM approach. The former refers to using six defined satellite images, while the latter consists of image sequences from an extended training pool of ten images. Further, we propose measures for the robustness concerning the selection of Sentinel-2 image data as evaluation metrics. We can distinguish between actual land cover changes and misclassifications of the deep learning approaches with these metrics. According to the provided metrics, both multitemporal LSTM approaches outperform the monotemporal FCN approach, about 3 to 5 percentage points (p.p.). The LSTM approach trained on the variable sequences detects 3 p.p. more land cover changes than the LSTM approach trained on the fixed sequences. Besides, applying our selected pre-processing improves the water classification and avoids reducing the dataset effectively by 17.6%. The presented LSTM approaches can be modified to provide applicability for a variable number of image sequences since we published the code of the deep learning models. The Sentinel-2 data and the ground truth are also freely available.<\/jats:p>","DOI":"10.3390\/rs13010078","type":"journal-article","created":{"date-parts":[[2020,12,28]],"date-time":"2020-12-28T10:33:56Z","timestamp":1609151636000},"page":"78","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":122,"title":["Deep Learning for Land Cover Change Detection"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1111-7787","authenticated-orcid":false,"given":"Oliver","family":"Sefrin","sequence":"first","affiliation":[{"name":"Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0596-9585","authenticated-orcid":false,"given":"Felix M.","family":"Riese","sequence":"additional","affiliation":[{"name":"Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7710-5316","authenticated-orcid":false,"given":"Sina","family":"Keller","sequence":"additional","affiliation":[{"name":"Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2020,12,28]]},"reference":[{"key":"ref_1","first-page":"331","article-title":"Using remote sensing to detect and monitor land-cover and land-use change","volume":"60","author":"Green","year":"1994","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_2","first-page":"1091","article-title":"A Strategy for Estimating the Rates of Recent United States Land-Cover Changes","volume":"68","author":"Loveland","year":"2002","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.rse.2005.08.006","article-title":"Land cover classification and change analysis of the Twin Cities (Minnesota) Metropolitan Area by multitemporal Landsat remote sensing","volume":"98","author":"Yuan","year":"2005","journal-title":"Remote Sens. Environ."},{"key":"ref_4","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_5","unstructured":"Prasad, S., and Chanussot, J. (2020). Supervised, Semi-Supervised, and Unsupervised Learning for Hyperspectral Regression. Hyperspectral Image Analysis: Advances in Machine Learning and Signal Processing, Springer International Publishing. Chapter 7."},{"key":"ref_6","unstructured":"Riese, F.M. (2020). Development and Applications of Machine Learning Methods for Hyperspectral Data. [Ph.D. Thesis, Karlsruhe Institute of Technology (KIT)]."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Foody, G.M., Pal, M., Rocchini, D., Garzon-Lopez, C.X., and Bastin, L. (2016). The sensitivity of mapping methods to reference data quality: Training supervised image classifications with imperfect reference data. ISPRS Int. J. Geo-Inf., 5.","DOI":"10.3390\/ijgi5110199"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.rse.2012.08.013","article-title":"Land change for all municipalities in Latin America and the Caribbean assessed from 250-m MODIS imagery (2001\u20132010)","volume":"126","author":"Clark","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Riese, F.M., Keller, S., and Hinz, S. (2020). Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data. Remote Sens., 12.","DOI":"10.3390\/rs12010007"},{"key":"ref_10","unstructured":"Staatsbetrieb Geobasisinformation und Vermessung Sachsen (GeoSN) (2017, June 28). Digitales Basis-Landschaftsmodell. Available online: http:\/\/www.landesvermessung.sachsen.de\/fachliche-details-basis-dlm-4100.html."},{"key":"ref_11","first-page":"551","article-title":"Multi-temporal land cover classification with long short-term memory neural networks","volume":"42","year":"2017","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ru\u00dfwurm, M., and K\u00f6rner, M. (2018). Multi-temporal land cover classification with sequential recurrent encoders. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7040129"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-031-02247-0","article-title":"Remote sensing image processing","volume":"5","author":"Tuia","year":"2011","journal-title":"Synth. Lect. Image, Video, Multimed. Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.chemolab.2012.05.009","article-title":"Pre-processing of hyperspectral images","volume":"117","author":"Vidal","year":"2012","journal-title":"Essential steps before image analysis. Chemom. Intell. Lab. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"615","DOI":"10.5194\/isprs-annals-IV-2-W5-615-2019","article-title":"Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data","volume":"IV-2\/W5","author":"Riese","year":"2019","journal-title":"ISPRS Ann. Photogramm. Remote. Sens. Spat. Inf. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sefrin, O., Riese, F.M., and Keller, S. (2020). Code for Deep Learning for Land Cover Change Detection, Zenodo.","DOI":"10.3390\/rs13010078"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.patrec.2005.08.011","article-title":"Random forests for land cover classification","volume":"27","author":"Gislason","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Keller, S., Braun, A.C., Hinz, S., and Weinmann, M. (2016, January 21\u201324). Investigation of the impact of dimensionality reduction and feature selection on the classification of hyperspectral EnMAP data. Proceedings of the 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Los Angeles, CA, USA.","DOI":"10.1109\/WHISPERS.2016.8071759"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1778","DOI":"10.1109\/TGRS.2004.831865","article-title":"Classification of hyperspectral remote sensing images with support vector machines","volume":"42","author":"Melgani","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","article-title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification","volume":"12","author":"Helber","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_21","unstructured":"Leitloff, J., and Riese, F.M. (2018). Examples for CNN Training and Classification on Sentinel-2 Data, Zenodo."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lyu, H., Lu, H., and Mou, L. (2016). Learning a transferable change rule from a recurrent neural network for land cover change detection. Remote Sens., 8.","DOI":"10.3390\/rs8060506"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.isprsjprs.2019.01.011","article-title":"DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn","volume":"149","author":"Interdonato","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mazzia, V., Khaliq, A., and Chiaberge, M. (2020). Improvement in Land Cover and Crop Classification based on Temporal Features Learning from Sentinel-2 Data Using Recurrent-Convolutional Neural Network (R-CNN). Appl. Sci., 10.","DOI":"10.3390\/app10010238"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.isprsjprs.2019.05.004","article-title":"Local climate zone-based urban land cover classification from multi-seasonal Sentinel-2 images with a recurrent residual network","volume":"154","author":"Qiu","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1787","DOI":"10.1109\/LGRS.2019.2953497","article-title":"Fusing Multiseasonal Sentinel-2 Imagery for Urban Land Cover Classification With Multibranch Residual Convolutional Neural Networks","volume":"17","author":"Qiu","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"van Duynhoven, A., and Dragi\u0107evi\u0107, S. (2019). Analyzing the Effects of Temporal Resolution and Classification Confidence for Modeling Land Cover Change with Long Short-Term Memory Networks. Remote Sens., 11.","DOI":"10.3390\/rs11232784"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ren, T., Liu, Z., Zhang, L., Liu, D., Xi, X., Kang, Y., Zhao, Y., Zhang, C., Li, S., and Zhang, X. (2020). Early Identification of Seed Maize and Common Maize Production Fields Using Sentinel-2 Images. Remote Sens., 12.","DOI":"10.3390\/rs12132140"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1109\/JSTARS.2020.2973602","article-title":"Generalization of Convolutional LSTM Models for Crop Area Estimation","volume":"13","author":"Mattos","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.isprsjprs.2019.01.015","article-title":"Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classification","volume":"149","author":"Hua","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"You, J., Li, X., Low, M., Lobell, D., and Ermon, S. (2017, January 4\u20139). Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.11172"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Song, A., Choi, J., Han, Y., and Kim, Y. (2018). Change detection in hyperspectral images using recurrent 3D fully convolutional networks. Remote Sens., 10.","DOI":"10.3390\/rs10111827"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Pelletier, C., Webb, G.I., and Petitjean, F. (2019). Temporal convolutional neural network for the classification of satellite image time series. Remote Sens., 11.","DOI":"10.3390\/rs11050523"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1109\/TNNLS.2016.2636227","article-title":"A deep convolutional coupling network for change detection based on heterogeneous optical and radar images","volume":"29","author":"Liu","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_35","unstructured":"Daudt, R.C., Le Saux, B., and Boulch, A. (2018, January 7\u201310). Fully convolutional siamese networks for change detection. Proceedings of the 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1016\/j.isprsjprs.2020.06.006","article-title":"Self-attention for raw optical Satellite Time Series Classification","volume":"169","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1080\/01431160110075802","article-title":"Using a time series of satellite imagery to detect land use and land cover changes in the Atlanta, Georgia metropolitan area","volume":"23","author":"Yang","year":"2002","journal-title":"Int. J. Remote Sens."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.14358\/PERS.69.9.1003","article-title":"Urban land-cover change detection through sub-pixel imperviousness mapping using remotely sensed data","volume":"69","author":"Yang","year":"2003","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/S0034-4257(96)00067-3","article-title":"NDWI\u2014A normalized difference water index for remote sensing of vegetation liquid water from space","volume":"58","author":"Gao","year":"1996","journal-title":"Remote Sens. Environ."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Joshi, A.V. (2020). Machine Learning and Artificial Intelligence, Springer.","DOI":"10.1007\/978-3-030-26622-6"},{"key":"ref_41","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 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_42","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_43","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_44","unstructured":"Sefrin, O. (2020). Building Footprint Extraction from Satellite Images with Fully Convolutional Networks. [Master\u2019s Thesis, Karlsruhe Institute of Technology (KIT)]."},{"key":"ref_45","unstructured":"Yakubovskiy, P. (2019, November 11). Segmentation Models. Available online: https:\/\/github.com\/qubvel\/segmentation_models."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Liu, S., Shi, Q., and Zhang, L. Few-Shot Hyperspectral Image Classification With Unknown Classes Using Multitask Deep Learning. IEEE Trans. Geosci. Remote. Sens., 2020.","DOI":"10.1109\/TGRS.2020.3018879"},{"key":"ref_47","unstructured":"Baghbaderani, R.K., Qu, Y., Qi, H., and Stutts, C. (2020, January 23\u201328). Representative-Discriminative Learning for Open-set Land Cover Classification of Satellite Imagery. Proceedings of the European Conference on Computer Vision, Glasgow, UK."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/1\/78\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:46:55Z","timestamp":1760179615000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/1\/78"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,28]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["rs13010078"],"URL":"https:\/\/doi.org\/10.3390\/rs13010078","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,28]]}}}