Detecting clearcut deforestation employing deep learning methods and SAR time series

Evandro C.  Taquary; L.M.G. Fonseca; R.V. Maretto; Hugo N. Bendini; Bruno M.  Matosak; Sidnei J. S.  Sant'Anna; José C.  Mura

doi:10.1109/igarss47720.2021.9554383

Detecting clearcut deforestation employing deep learning methods and SAR time series

Evandro C. Taquary, L.M.G. Fonseca, R.V. Maretto, Hugo N. Bendini, Bruno M. Matosak, Sidnei J. S. Sant'Anna, José C. Mura

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

20 Downloads (Pure)

Abstract

Automating the systematic monitoring of deforestation in the Brazilian biomes has become imperative. In this sense, a promising research field lies upon the exploitation of orbital imaging based on Synthetic Aperture Radar (SAR) sensors, since this technology is less affected by cloud cover, allowing systematic data acquisitions. In addition, the growing availability of with no charge SAR data products enables investigations on the use of time series extracted from this category of instruments, paving the way for more sophisticated temporal analyzes. This work presents the results of a SAR time series classification model designed to identify clearcut deforestation patterns in time, through an Artificial Intelligence approach known as Recurrent Neural Networks. The classification was performed using 5216 samples of Sentinel-1 time series within the Amazon basin, reaching an overall accuracy of 96.74%.

Original language	English
Title of host publication	2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS
Publisher	IEEE
Pages	4520-4523
Number of pages	4
ISBN (Electronic)	978-1-6654-0369-6
ISBN (Print)	978-1-6654-4762-1
DOIs	https://doi.org/10.1109/igarss47720.2021.9554383
Publication status	Published - 12 Oct 2021
Event	IEEE- International Geoscience and Remote Sensing Symposium- IGARSS 2021 - Brussels, Virtual Conference, Belgium Duration: 12 Jul 2021 → 16 Jul 2021 https://igarss2021.com

Conference

Conference	IEEE- International Geoscience and Remote Sensing Symposium- IGARSS 2021
Abbreviated title	IGARSS 2021
Country/Territory	Belgium
City	Virtual Conference
Period	12/07/21 → 16/07/21
Internet address	https://igarss2021.com

Access to Document

10.1109/igarss47720.2021.9554383

Detecting_Clearcut_Deforestation_Employing_Deep_Learning_Methods_and_SAR_Time_SeriesFinal published version, 193 KBLicence: Taverne

Cite this

@inproceedings{9dc500c78c2349c48eb6014721cd4395,

title = "Detecting clearcut deforestation employing deep learning methods and SAR time series",

abstract = "Automating the systematic monitoring of deforestation in the Brazilian biomes has become imperative. In this sense, a promising research field lies upon the exploitation of orbital imaging based on Synthetic Aperture Radar (SAR) sensors, since this technology is less affected by cloud cover, allowing systematic data acquisitions. In addition, the growing availability of with no charge SAR data products enables investigations on the use of time series extracted from this category of instruments, paving the way for more sophisticated temporal analyzes. This work presents the results of a SAR time series classification model designed to identify clearcut deforestation patterns in time, through an Artificial Intelligence approach known as Recurrent Neural Networks. The classification was performed using 5216 samples of Sentinel-1 time series within the Amazon basin, reaching an overall accuracy of 96.74%.",

author = "Taquary, {Evandro C.} and L.M.G. Fonseca and R.V. Maretto and Bendini, {Hugo N.} and Matosak, {Bruno M.} and Sant'Anna, {Sidnei J. S.} and Mura, {Jos{\'e} C.}",

year = "2021",

month = oct,

day = "12",

doi = "10.1109/igarss47720.2021.9554383",

language = "English",

isbn = "978-1-6654-4762-1",

pages = "4520--4523",

booktitle = "2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS",

publisher = "IEEE",

note = "IEEE- International Geoscience and Remote Sensing Symposium- IGARSS 2021, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

url = "https://igarss2021.com",

}

Taquary, EC, Fonseca, LMG, Maretto, RV, Bendini, HN, Matosak, BM, Sant'Anna, SJS & Mura, JC 2021, Detecting clearcut deforestation employing deep learning methods and SAR time series. in 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, pp. 4520-4523, IEEE- International Geoscience and Remote Sensing Symposium- IGARSS 2021, Virtual Conference, Belgium, 12/07/21. https://doi.org/10.1109/igarss47720.2021.9554383

TY - GEN

T1 - Detecting clearcut deforestation employing deep learning methods and SAR time series

AU - Taquary, Evandro C.

AU - Fonseca, L.M.G.

AU - Maretto, R.V.

AU - Bendini, Hugo N.

AU - Matosak, Bruno M.

AU - Sant'Anna, Sidnei J. S.

AU - Mura, José C.

PY - 2021/10/12

Y1 - 2021/10/12

N2 - Automating the systematic monitoring of deforestation in the Brazilian biomes has become imperative. In this sense, a promising research field lies upon the exploitation of orbital imaging based on Synthetic Aperture Radar (SAR) sensors, since this technology is less affected by cloud cover, allowing systematic data acquisitions. In addition, the growing availability of with no charge SAR data products enables investigations on the use of time series extracted from this category of instruments, paving the way for more sophisticated temporal analyzes. This work presents the results of a SAR time series classification model designed to identify clearcut deforestation patterns in time, through an Artificial Intelligence approach known as Recurrent Neural Networks. The classification was performed using 5216 samples of Sentinel-1 time series within the Amazon basin, reaching an overall accuracy of 96.74%.

AB - Automating the systematic monitoring of deforestation in the Brazilian biomes has become imperative. In this sense, a promising research field lies upon the exploitation of orbital imaging based on Synthetic Aperture Radar (SAR) sensors, since this technology is less affected by cloud cover, allowing systematic data acquisitions. In addition, the growing availability of with no charge SAR data products enables investigations on the use of time series extracted from this category of instruments, paving the way for more sophisticated temporal analyzes. This work presents the results of a SAR time series classification model designed to identify clearcut deforestation patterns in time, through an Artificial Intelligence approach known as Recurrent Neural Networks. The classification was performed using 5216 samples of Sentinel-1 time series within the Amazon basin, reaching an overall accuracy of 96.74%.

UR - https://ezproxy2.utwente.nl/login?url=https://doi.org/10.1109/IGARSS47720.2021.9554383

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2021/chap/maretto_det.pdf

U2 - 10.1109/igarss47720.2021.9554383

DO - 10.1109/igarss47720.2021.9554383

M3 - Conference contribution

SN - 978-1-6654-4762-1

SP - 4520

EP - 4523

BT - 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

PB - IEEE

T2 - IEEE- International Geoscience and Remote Sensing Symposium- IGARSS 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

Detecting clearcut deforestation employing deep learning methods and SAR time series

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this