Next Article in Journal
Impact of Fire Emissions on U.S. Air Quality from 1997 to 2016–A Modeling Study in the Satellite Era
Next Article in Special Issue
Comparison of Cloud Cover Detection Algorithms on Sentinel–2 Images of the Amazon Tropical Forest
Previous Article in Journal
Semi-Automatic Methodology for Fire Break Maintenance Operations Detection with Sentinel-2 Imagery and Artificial Neural Network
Previous Article in Special Issue
Change Detection of Deforestation in the Brazilian Amazon Using Landsat Data and Convolutional Neural Networks
Open AccessArticle

Evaluation of Deep Learning Techniques for Deforestation Detection in the Brazilian Amazon and Cerrado Biomes From Remote Sensing Imagery

1
Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, 22451-900 Rio de Janeiro, Brazil
2
National Institute for Space Research (INPE), São Jose dos Campos 12227-010, São Paulo, Brazil
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(6), 910; https://doi.org/10.3390/rs12060910
Received: 5 February 2020 / Revised: 3 March 2020 / Accepted: 6 March 2020 / Published: 12 March 2020
(This article belongs to the Special Issue Assessing Changes in the Amazon and Cerrado Biomes by Remote Sensing)
Deforestation is one of the major threats to natural ecosystems. This process has a substantial contribution to climate change and biodiversity reduction. Therefore, the monitoring and early detection of deforestation is an essential process for preservation. Techniques based on satellite images are among the most attractive options for this application. However, many approaches involve some human intervention or are dependent on a manually selected threshold to identify regions that suffer deforestation. Motivated by this scenario, the present work evaluates Deep Learning-based strategies for automatic deforestation detection, namely, Early Fusion (EF), Siamese Network (SN), and Convolutional Support Vector Machine (CSVM) as well as Support Vector Machine (SVM), used as the baseline. The target areas are two regions with different deforestation patterns: the Amazon and Cerrado biomes in Brazil. The experiments used two co-registered Landsat 8 images acquired at different dates. The strategies based on Deep Learning achieved the best performance in our analysis in comparison with the baseline, with SN and EF superior to CSVM and SVM. In the same way, a reduction of the salt-and-pepper effect in the generated probabilistic change maps was noticed as the number of training samples increased. Finally, the work assesses how the methods can reduce the time invested in the visual inspection of deforested areas. View Full-Text
Keywords: deforestation detection; Brazilian biomes; deep learning; optical imagery deforestation detection; Brazilian biomes; deep learning; optical imagery
Show Figures

Graphical abstract

MDPI and ACS Style

Ortega Adarme, M.; Queiroz Feitosa, R.; Nigri Happ, P.; Aparecido De Almeida, C.; Rodrigues Gomes, A. Evaluation of Deep Learning Techniques for Deforestation Detection in the Brazilian Amazon and Cerrado Biomes From Remote Sensing Imagery. Remote Sens. 2020, 12, 910. https://doi.org/10.3390/rs12060910

AMA Style

Ortega Adarme M, Queiroz Feitosa R, Nigri Happ P, Aparecido De Almeida C, Rodrigues Gomes A. Evaluation of Deep Learning Techniques for Deforestation Detection in the Brazilian Amazon and Cerrado Biomes From Remote Sensing Imagery. Remote Sensing. 2020; 12(6):910. https://doi.org/10.3390/rs12060910

Chicago/Turabian Style

Ortega Adarme, Mabel; Queiroz Feitosa, Raul; Nigri Happ, Patrick; Aparecido De Almeida, Claudio; Rodrigues Gomes, Alessandra. 2020. "Evaluation of Deep Learning Techniques for Deforestation Detection in the Brazilian Amazon and Cerrado Biomes From Remote Sensing Imagery" Remote Sens. 12, no. 6: 910. https://doi.org/10.3390/rs12060910

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop