{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T21:27:17Z","timestamp":1772054837371,"version":"3.50.1"},"reference-count":62,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T00:00:00Z","timestamp":1663632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CAPES (Brazillian Coordination for the Improvement of Higher Education Personnel)"},{"name":"FAPERJ (Rio de Janeiro State Research Funding Agency)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The Amazon rainforest spreads across nine countries and covers nearly one-third of South America, being 69% inside Brazilian borders. It represents more than half of the remaining tropical forest on Earth and covers the catchment basin of the Amazon river on which 20% of the surface fresh water on the planet flows. Such an ecosystem produces large quantities of water vapor, helping regulate rainfall regimes in most of South America, with strong economic implications: for instance, by irrigating crops and pastures, and supplying water for the main hydroelectric plants in the continent. Being the natural habitat of one-tenth of the currently known species, the Amazon also has enormous biotechnological potential. Among the major menaces to the Amazon is the extension of agricultural and cattle farming, forest fires, illegal mining and logging, all directly associated with deforestation. Preserving the Amazon is obviously essential, and it is well-known that remote sensing provides effective tools for environmental monitoring. This work presents a deforestation detection approach based on the DeepLabv3+, a fully convolutional deep learning model devised for semantic segmentation. The proposed method extends the original DeepLabv3+ model, aiming at properly dealing with a strong class imbalanced problem and improving the delineation quality of deforestation polygons. Experiments were devised to evaluate the proposed method in terms of the sensitivity to the weighted focal loss hyperparameters\u2014through an extensive grid search\u2014and the amount of training data, and compared its performance to previous deep learning methods proposed for deforestation detection. Landsat OLI-8 images of a specific region in the Amazon were used in such evaluation. The results indicate that the variants of the proposed method outperformed previous works in terms of the F1-score and Precision metrics. Additionally, more substantial performance gains were observed in the context of smaller volumes of training data. When the evaluated methods were trained using four image tiles, the proposed method outperformed its counterparts by approximately +10% in terms of F1-score (from 63% to 73%); when the methods were trained with only one image tile, the performance difference in terms of F1-score achieved approximately +18% (from 49% to 67%).<\/jats:p>","DOI":"10.3390\/rs14194694","type":"journal-article","created":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T00:08:09Z","timestamp":1663718889000},"page":"4694","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Deforestation Detection in the Amazon Using DeepLabv3+ Semantic Segmentation Model Variants"],"prefix":"10.3390","volume":"14","author":[{"given":"Renan Bides","family":"de Andrade","sequence":"first","affiliation":[{"name":"Post-Graduation Program in Computational Sciences, Rio de Janeiro State University (UERJ), Rio de Janeiro 20550-013, RJ, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2336-6024","authenticated-orcid":false,"given":"Guilherme Lucio Abelha","family":"Mota","sequence":"additional","affiliation":[{"name":"Post-Graduation Program in Computational Sciences, Rio de Janeiro State University (UERJ), Rio de Janeiro 20550-013, RJ, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7341-9118","authenticated-orcid":false,"given":"Gilson Alexandre Ostwald Pedro","family":"da Costa","sequence":"additional","affiliation":[{"name":"Post-Graduation Program in Computational Sciences, Rio de Janeiro State University (UERJ), Rio de Janeiro 20550-013, RJ, Brazil"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,20]]},"reference":[{"key":"ref_1","unstructured":"World Wildlife Fund (2020, February 20). Places: Amazon. Available online: https:\/\/www.worldwildlife.org\/places\/amazon."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"124004","DOI":"10.1088\/1748-9326\/10\/12\/124004","article-title":"Land use patterns and related carbon losses following deforestation in south america","volume":"10","author":"Herold","year":"2015","journal-title":"Environ. Res. Lett."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1145\/3416957","article-title":"Estimating Amazon Carbon Stock Using AI-Based Remote Sensing","volume":"63","author":"Cavalcanti","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1017\/S1355770X18000499","article-title":"Getting greener by going black: The effect of blacklisting municipalities on Amazon deforestation","volume":"24","author":"Rocha","year":"2019","journal-title":"Environ. Dev. Econ."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lovejoy, T.E., and Nobre, C. (2018). Amazon Tipping Point. Sci. Adv., 4.","DOI":"10.1126\/sciadv.aat2340"},{"key":"ref_6","unstructured":"The Worldwatch Institute (2015). Vital Signs Volume 22\u2014The Trends That Are Shaping Our Future, Island Press."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.foreco.2019.02.037","article-title":"Carbon emissions and potential emissions reductions from low-intensity selective logging in southwestern Amazonia","volume":"439","author":"Goodman","year":"2019","journal-title":"For. Ecol. Manag."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s13280-011-0196-7","article-title":"Brazilian Amazon: A significant five year drop in deforestation rates but figures are on the rise again","volume":"41","author":"Malingreau","year":"2012","journal-title":"Ambio"},{"key":"ref_9","unstructured":"Nogueron, R., Barreto, P., Souza, C., Anderson, A., and Salom\u00e3o, R. (2006). Human Pressure on the Brazilian Amazon Forests, World Resources Institute."},{"key":"ref_10","unstructured":"Miller, M.E. (The Washington Post, 2015). Why are Brazil\u2019s environmentalists being murdered?, The Washington Post."},{"key":"ref_11","unstructured":"Evans, K. (2013). Martyr of the Amazon: The legacy of Chico Mendes, Reuters."},{"key":"ref_12","unstructured":"Boadle, A. (2021). Gold Miners Attack Indigenous Village in Amazon, Clash with Police, Reuters."},{"key":"ref_13","unstructured":"Lewis, J. (2017). Brazil\u2019s Criminal Logging Gangs Kill With Relative Impunity, Human Rights Watch Says. Wall Str. J., Available online: https:\/\/www.wsj.com\/articles\/brazils-criminal-logging-gangs-kill-with-relative-impunity-human-rights-watch-says-11568752021,."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"30","DOI":"10.5751\/ES-10062-230230","article-title":"Deforestation and local sustainable development in Brazilian Legal Amazonia: An exploratory analysis","volume":"23","author":"Sathler","year":"2018","journal-title":"Ecol. Soc."},{"key":"ref_15","unstructured":"Archard, F., and Hansen, M. (2013). The Brazilian amazon monitoring program: PRODES and DETER projects. Global Forest Monitoring from Earth Observation, CRC Press. Chapter 9."},{"key":"ref_16","unstructured":"Goodman, J., and Giles, C. (2020). Amazon Fires: Are They Worse This Year than Before?, BBC News."},{"key":"ref_17","unstructured":"Spring, J. (2021). Scientists Warn of Bad Year for Fires in Brazil\u2019s Amazon and Wetlands, Reuters."},{"key":"ref_18","unstructured":"World Wildlife Fund (2020, February 20). Amazon Deforestation. Available online: https:\/\/wwf.panda.org\/our_work\/forests\/deforestation_fronts2\/deforestation_in_the_amazon,."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1038\/s41558-021-01026-5","article-title":"Carbon loss from forest degradation exceeds that from deforestation in the Brazilian Amazon","volume":"11","author":"Qin","year":"2021","journal-title":"Nat. Clim. Chang."},{"key":"ref_20","first-page":"272","article-title":"Monitoring tropical forest from space: The PRODES digital project","volume":"35","author":"Valeriano","year":"2004","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"37","DOI":"10.4136\/ambi-agua.4","article-title":"Near real time detection of deforestation in the Brazilian Amazon using MODIS imagery","volume":"1","author":"Shimabukuro","year":"2006","journal-title":"Ambiente Agua Interdiscip. J. Appl. Sci."},{"key":"ref_22","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_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2022.3163575","article-title":"Domain-Adversarial Neural Networks for Deforestation Detection in Tropical Forests","volume":"19","author":"Soto","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. arXiv.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.5194\/isprs-archives-XLIII-B3-2020-1497-2020","article-title":"Evaluation of semantic segmentation methods for deforestation detection in the amazon","volume":"XLIII-B3-2020","author":"Andrade","year":"2020","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R.B., He, K., and Doll\u00e1r, P. (2017). Focal Loss for Dense Object Detection. arXiv.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"121","DOI":"10.5194\/isprs-annals-IV-2-W7-121-2019","article-title":"Evaluation of Deep Learning Techniques for Deforestation Detection in the Amazon Forest","volume":"42W7","author":"Ortega","year":"2019","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_28","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_29","doi-asserted-by":"crossref","unstructured":"You, Y., Cao, J., and Zhou, W. (2020). A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios. Remote Sens., 12.","DOI":"10.3390\/rs12152460"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"024518","DOI":"10.1117\/1.JRS.15.024518","article-title":"AI-ForestWatch: Semantic segmentation based end-to-end framework for forest estimation and change detection using multi-spectral remote sensing imagery","volume":"15","author":"Zulfiqar","year":"2021","journal-title":"J. Appl. Remote Sens."},{"key":"ref_31","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_32","doi-asserted-by":"crossref","first-page":"112600","DOI":"10.1016\/j.rse.2021.112600","article-title":"Spatial and temporal deep learning methods for deriving land-use following deforestation: A pan-tropical case study using Landsat time series","volume":"264","author":"Masolele","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Shumilo, L., Yailymov, B., Lavreniuk, M., and Bilokonska, Y. (2020, January 17\u201318). Remote Sensing Approaches for Deforestation Identification in Ukraine. Proceedings of the 2020 IEEE 5th International Symposium on Smart and Wireless Systems within the Conferences on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS-SWS), Dortmund, Germany.","DOI":"10.1109\/IDAACS-SWS50031.2020.9297054"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Lee, S.H., Han, K.J., Lee, K., Lee, K.J., Oh, K.Y., and Lee, M.J. (2020). Classification of Landscape Affected by Deforestation Using High-Resolution Remote Sensing Data and Deep-Learning Techniques. Remote Sens., 12.","DOI":"10.3390\/rs12203372"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1109\/JSTARS.2020.3034186","article-title":"Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2","volume":"14","author":"Isaienkov","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_36","unstructured":"Jia, S., Jiang, S., Zhang, S., Xu, M., and Jia, X. (2022). Graph-in-Graph Convolutional Network for Hyperspectral Image Classification. IEEE Trans. Neural Netw. Learn. Syst., 1\u201315."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.isprsjprs.2013.09.014","article-title":"Geographic Object-Based Image Analysis \u2013 Towards a new paradigm","volume":"87","author":"Blaschke","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3948","DOI":"10.1109\/JSTARS.2022.3171586","article-title":"Hybrid Dense Network With Attention Mechanism for Hyperspectral Image Classification","volume":"15","author":"Ahmad","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"4340","DOI":"10.1109\/TGRS.2020.3016820","article-title":"More Diverse Means Better: Multimodal Deep Learning Meets Remote-Sensing Imagery Classification","volume":"59","author":"Hong","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","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_41","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1109\/LGRS.2020.2986407","article-title":"Spatio-Temporal Deep Learning Approach to Map Deforestation in Amazon Rainforest","volume":"18","author":"Maretto","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"851","DOI":"10.5194\/isprs-archives-XLIII-B3-2021-851-2021","article-title":"Deforestation detection in the amazon rainforest with spatial and channel attention mechanisms","volume":"XLIII-B3-2021","author":"Tovar","year":"2021","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Watanabe, M., Koyama, C., Hayashi, M., Nagatani, I., Tadono, T., and Shimada, M. (2021, January 11\u201316). Trial of Detection Accuracies Improvement for JJ-FAST Deforestation Detection Algorithm Using Deep Learning. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.","DOI":"10.1109\/IGARSS47720.2021.9553211"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Taquary, E.C., Fonseca, L.G.M., Maretto, R.V., Bendini, H.N., Matosak, B.M., Sant\u00c1nna, S.J., and Mura, J.C. (2021, January 11\u201316). Detecting Clearcut Deforestation Employing Deep Learning Methods and SAR Time Series. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.","DOI":"10.1109\/IGARSS47720.2021.9554383"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Shumilo, L., Lavreniuk, M., Kussul, N., and Shevchuk, B. (2021, January 22\u201325). Automatic Deforestation Detection based on the Deep Learning in Ukraine. Proceedings of the 2021 11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Cracow, Poland.","DOI":"10.1109\/IDAACS53288.2021.9661008"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Torres, D.L., Turnes, J.N., Soto Vega, P.J., Feitosa, R.Q., Silva, D.E., Marcato Junior, J., and Almeida, C. (2021). Deforestation Detection with Fully Convolutional Networks in the Amazon Forest from Landsat-8 and Sentinel-2 Images. Remote Sens., 13.","DOI":"10.3390\/rs13245084"},{"key":"ref_47","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_48","first-page":"1","article-title":"Domain-Adversarial Training of Neural Networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_49","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2016). Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs. arXiv."},{"key":"ref_50","unstructured":"Mallat, S. (2018). A Wavelet Tour of Signal Processing, Academic Press. [3rd ed.]."},{"key":"ref_51","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_55","first-page":"109","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","volume":"24","author":"Koltun","year":"2011","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_56","unstructured":"Chen, L., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv."},{"key":"ref_57","unstructured":"Liu, W., Rabinovich, A., and Berg, A.C. (2015). ParseNet: Looking Wider to See Better. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2016). Xception: Deep Learning with Depthwise Separable Convolutions. arXiv.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y. (2017, January 22\u201329). Deformable Convolutional Networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref_60","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv."},{"key":"ref_61","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0034-4257(97)00104-1","article-title":"On the relation between NDVI, fractional vegetation cover, and leaf area index","volume":"62","author":"Carlson","year":"1997","journal-title":"Remote Sens. Environ."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/19\/4694\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:35:48Z","timestamp":1760142948000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/19\/4694"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,20]]},"references-count":62,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["rs14194694"],"URL":"https:\/\/doi.org\/10.3390\/rs14194694","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,20]]}}}