{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:07:14Z","timestamp":1782576434795,"version":"3.54.5"},"reference-count":41,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"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 availability of remote-sensing multisource data from optical-based satellite sensors has created new opportunities and challenges for forest monitoring in the Amazon Biome. In particular, change-detection analysis has emerged in recent decades to monitor forest-change dynamics, supporting some Brazilian governmental initiatives such as PRODES and DETER projects for biodiversity preservation in threatened areas. In recent years fully convolutional network architectures have witnessed numerous proposals adapted for the change-detection task. This paper comprehensively explores state-of-the-art fully convolutional networks such as U-Net, ResU-Net, SegNet, FC-DenseNet, and two DeepLabv3+ variants on monitoring deforestation in the Brazilian Amazon. The networks\u2019 performance is evaluated experimentally in terms of Precision, Recall, F1-score, and computational load using satellite images with different spatial and spectral resolution: Landsat-8 and Sentinel-2. We also include the results of an unprecedented auditing process performed by senior specialists to visually evaluate each deforestation polygon derived from the network with the highest accuracy results for both satellites. This assessment allowed estimation of the accuracy of these networks simulating a process \u201cin nature\u201d and faithful to the PRODES methodology. We conclude that the high resolution of Sentinel-2 images improves the segmentation of deforestation polygons both quantitatively (in terms of F1-score) and qualitatively. Moreover, the study also points to the potential of the operational use of Deep Learning (DL) mapping as products to be consumed in PRODES.<\/jats:p>","DOI":"10.3390\/rs13245084","type":"journal-article","created":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T22:06:10Z","timestamp":1639519570000},"page":"5084","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":62,"title":["Deforestation Detection with Fully Convolutional Networks in the Amazon Forest from Landsat-8 and Sentinel-2 Images"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7916-9463","authenticated-orcid":false,"given":"Daliana Lobo","family":"Torres","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22451-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9573-2228","authenticated-orcid":false,"given":"Javier Noa","family":"Turnes","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22451-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5396-8531","authenticated-orcid":false,"given":"Pedro Juan","family":"Soto Vega","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22451-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8344-5096","authenticated-orcid":false,"given":"Raul Queiroz","family":"Feitosa","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22451-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4892-2584","authenticated-orcid":false,"given":"Daniel E.","family":"Silva","sequence":"additional","affiliation":[{"name":"Instituto Nacional de Pesquisas Espaciais\u2014INPE, S\u00e3o Jos\u00e9 dos Campos 12227-010, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9096-6866","authenticated-orcid":false,"given":"Jose","family":"Marcato Junior","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1032-6966","authenticated-orcid":false,"given":"Claudio","family":"Almeida","sequence":"additional","affiliation":[{"name":"Instituto Nacional de Pesquisas Espaciais\u2014INPE, S\u00e3o Jos\u00e9 dos Campos 12227-010, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,12,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1038\/nature10717","article-title":"The Amazon basin in transition","volume":"481","author":"Davidson","year":"2012","journal-title":"Nature"},{"key":"ref_2","unstructured":"De Almeida, C.A. (2021, July 18). Estimativa da Area e do Tempo de Perman\u00eancia da Vegeta\u00e7\u00e3o Secundaria na Amaz\u00f4nia Legal por Meio de Imagens Landsat\/TM. Available online: http:\/\/mtc-m16c.sid.inpe.br\/col\/sid.inpe.br\/mtc-m18@80\/2008\/11.04.18.45\/doc\/publicacao.pdf."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1968","DOI":"10.1016\/j.foreco.2009.07.042","article-title":"Biomass and greenhouse-gas emissions from land-use change in Brazil\u2019s Amazonian \u201carc of deforestation\u201d: The states of Mato Grosso and Rond\u00f4nia","volume":"258","author":"Fearnside","year":"2009","journal-title":"For. Ecol. Manag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1038\/s41559-020-01368-x","article-title":"The Brazilian Amazon deforestation rate in 2020 is the greatest of the decade","volume":"5","author":"Junior","year":"2021","journal-title":"Nat. Ecol. Evol."},{"key":"ref_5","unstructured":"Almeida, C.A., and Maurano, L.E.P. (2021). Methodology for Forest Monitoring used in PRODES and DETER Projects, INPE."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3619","DOI":"10.1109\/JSTARS.2015.2437075","article-title":"DETER-B: The new Amazon near real-time deforestation detection system","volume":"8","author":"Diniz","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Rogan, J., Miller, J., Wulder, M., and Franklin, S. (2006). Integrating GIS and remotely sensed data for mapping forest disturbance and change. Underst. For. Disturb. Spat. Pattern Remote Sens. GIS Approaches, 133\u2013172.","DOI":"10.1201\/9781420005189.ch6"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"75","DOI":"10.3832\/ifor0909-007","article-title":"Landsat TM imagery and NDVI differencing to detect vegetation change: Assessing natural forest expansion in Basilicata, southern Italy","volume":"7","author":"Mancino","year":"2014","journal-title":"Ifor.-Biogeosci. For."},{"key":"ref_9","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_10","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1080\/014311698216053","article-title":"Land-use mapping and change detection in a coal mining area-a case study in the Jharia coalfield, India","volume":"19","author":"Prakash","year":"1998","journal-title":"Int. J. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1016\/S0034-4257(01)00326-1","article-title":"Remote sensing of selective logging in Amazonia: Assessing limitations based on detailed field observations, Landsat ETM+, and textural analysis","volume":"80","author":"Asner","year":"2002","journal-title":"Remote Sens. Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.1080\/0143116031000139863","article-title":"Change detection techniques","volume":"25","author":"Lu","year":"2004","journal-title":"Int. J. Remote Sens."},{"key":"ref_13","first-page":"1303","article-title":"Detecting forest canopy change due to insect activity using Landsat MSS","volume":"49","author":"Nelson","year":"1983","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.rse.2014.01.011","article-title":"Continuous change detection and classification of land cover using all available Landsat data","volume":"144","author":"Zhu","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.rse.2005.09.008","article-title":"A change detection model based on neighborhood correlation image analysis and decision tree classification","volume":"99","author":"Im","year":"2005","journal-title":"Remote Sens. Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1016\/j.rse.2012.06.006","article-title":"Monitoring land cover change in urban and peri-urban areas using dense time stacks of Landsat satellite data and a data mining approach","volume":"124","author":"Schneider","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1016\/j.rse.2007.07.023","article-title":"Use of a dark object concept and support vector machines to automate forest cover change analysis","volume":"112","author":"Huang","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1080\/014311600210641","article-title":"Beware of per-pixel characterization of land cover","volume":"21","author":"Townshend","year":"2000","journal-title":"Int. J. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5407","DOI":"10.1109\/TGRS.2017.2707528","article-title":"Forest change detection in incomplete satellite images with deep neural networks","volume":"55","author":"Khan","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1109\/TGRS.2018.2863224","article-title":"Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery","volume":"57","author":"Mou","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.inffus.2017.10.007","article-title":"Deep learning for pixel-level image fusion: Recent advances and future prospects","volume":"42","author":"Liu","year":"2018","journal-title":"Inf. Fusion"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Daudt, R.C., Le Saux, B., Boulch, A., and Gousseau, Y. (2018, January 22\u201327). Urban change detection for multispectral earth observation using convolutional neural networks. Proceedings of the IGARSS 2018\u20142018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8518015"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ortega Adarme, M., Queiroz Feitosa, R., Nigri Happ, P., Aparecido De Almeida, C., and Rodrigues Gomes, A. (2020). Evaluation of deep learning techniques for deforestation detection in the Brazilian Amazon and cerrado biomes from remote sensing imagery. Remote Sens., 12.","DOI":"10.3390\/rs12060910"},{"key":"ref_24","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2021, July 18). Fully Convolutional Networks for Semantic Segmentation. CoRR 2014 . Available online: https:\/\/arxiv.org\/pdf\/1411.4038.pdf."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Caye Daudt, R., 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.","DOI":"10.1109\/ICIP.2018.8451652"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"De Bem, P.P., de Carvalho Junior, O.A., Fontes Guimar\u00e3es, R., and Trancoso Gomes, R.A. (2020). Change Detection of Deforestation in the Brazilian Amazon Using Landsat Data and Convolutional Neural Networks. Remote Sens., 12.","DOI":"10.3390\/rs12060901"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.isprsjprs.2020.06.003","article-title":"A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images","volume":"166","author":"Zhang","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_28","unstructured":"Badrinarayanan, V., Handa, A., and Cipolla, R. (2021, July 18). SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling. CoRR 2015. Available online: https:\/\/arxiv.org\/pdf\/1511.00561.pdf."},{"key":"ref_29","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2021, July 18). U-Net: Convolutional Networks for Biomedical Image Segmentation. CoRR 2015. Available online: https:\/\/arxiv.org\/pdf\/1505.04597.pdf."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","article-title":"Road extraction by deep residual u-net","volume":"15","author":"Zhang","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_31","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, S., Drozdzal, M., V\u00e1zquez, D., Romero, A., and Bengio, Y. (2017, January 21\u201326). The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.156"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201327). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Lobo Torres, D., Queiroz Feitosa, R., Nigri Happ, P., Elena Cu\u00e9 La Rosa, L., Marcato Junior, J., Martins, J., Ol\u00e3 Bressan, P., Gon\u00e7alves, W.N., and Liesenberg, V. (2020). Applying fully convolutional architectures for semantic segmentation of a single tree species in urban environment on high resolution UAV optical imagery. Sensors, 20.","DOI":"10.3390\/s20020563"},{"key":"ref_35","unstructured":"Chen, L., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2021, July 18). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. CoRR 2018. Available online: https:\/\/arxiv.org\/pdf\/1802.02611.pdf."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2021, July 18). Xception: Deep Learning with Depthwise Separable Convolutions. CoRR 2016. Available online: https:\/\/openaccess.thecvf.com\/content_cvpr_2017\/papers\/Chollet_Xception_Deep_Learning_CVPR_2017_paper.pdf.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_37","unstructured":"Chen, L., Papandreou, G., Schroff, F., and Adam, H. (2021, July 18). Rethinking Atrous Convolution for Semantic Image Segmentation. CoRR 2017. Available online: https:\/\/arxiv.org\/pdf\/1706.05587.pdf."},{"key":"ref_38","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., and Chen, L. (2021, July 18). Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. CoRR 2018. Available online: https:\/\/arxiv.org\/pdf\/1801.04381.pdf."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.5902\/1980509834380","article-title":"Spatial deforestation patterns and the accuracy of deforestation mapping for the Brazilian Legal Amazon","volume":"29","author":"Maurano","year":"2019","journal-title":"Ci\u00eancia Florest."},{"key":"ref_40","unstructured":"(2021, July 18). Keras. Available online: https:\/\/keras.io\/getting_started\/."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Sokolova, M., Japkowicz, N., and Szpakowicz, S. (2006, January 4\u20138). Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation. Proceedings of the Australasian Joint Conference on Artificial Intelligence, Hobart, Australia.","DOI":"10.1007\/11941439_114"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/24\/5084\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:48:00Z","timestamp":1760168880000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/24\/5084"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":41,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["rs13245084"],"URL":"https:\/\/doi.org\/10.3390\/rs13245084","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,14]]}}}