Temporal difference and density-based learning method applied for deforestation detection using ALOS-2/PALSAR-2

Irene Erlyn Wina Rachmawan, Takeo Tadono, Masato Hayashi, Yasushi Kiyoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Remote sensing has established as key technology for monitoring of environmental degradation such as forest clearing. One of the state-of-the-art microwave EO systems for forest monitoring is Japan's L-band ALOS-2/PALSAR-2 which provides outstanding means for observing tropical forests due its cloud and canopy penetration capability. However, the complexity of the physical backscattering properties of forests and the associated spatial and temporal variabilities, render straightforward change detection methods based on simple thresholding rather inaccurate with high false alarm rates. In this paper, we develop a framework to alleviate problems caused by forest backscatter variability. We define three essential elements, namely "structures of density", "speed of change", and "expansion patterns" which are obtained by differential computing between two repeat-pass PALSAR-2 images. To improve both the detection and assessing of deforestation, a "deforestation behavior pattern" is sought through temporal machine learning mechanism of the three proposed elements. Our results indicate that the use of "structure of density" can introduce a more robust performance for detecting deforestation. Meanwhile, "speed of change" and "expansion pattern" are capable to provide additional information with respect to the drivers of deforestation and the land-use change.

Original languageEnglish
Title of host publication2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4905-4908
Number of pages4
ISBN (Electronic)9781538671504
DOIs
Publication statusPublished - 2018 Oct 31
Event38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Valencia, Spain
Duration: 2018 Jul 222018 Jul 27

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2018-July

Conference

Conference38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018
CountrySpain
CityValencia
Period18/7/2218/7/27

Fingerprint

Deforestation
PALSAR
ALOS
deforestation
learning
Monitoring
Backscattering
monitoring
Weathering
environmental degradation
detection method
Land use
backscatter
tropical forest
land use change
Learning systems
Remote sensing
penetration
physical property
Microwaves

Keywords

  • Density-based
  • Synthetic Aperture Radar (SAR)
  • Temporal difference learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Rachmawan, I. E. W., Tadono, T., Hayashi, M., & Kiyoki, Y. (2018). Temporal difference and density-based learning method applied for deforestation detection using ALOS-2/PALSAR-2. In 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings (pp. 4905-4908). [8518412] (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2018-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2018.8518412

Temporal difference and density-based learning method applied for deforestation detection using ALOS-2/PALSAR-2. / Rachmawan, Irene Erlyn Wina; Tadono, Takeo; Hayashi, Masato; Kiyoki, Yasushi.

2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 4905-4908 8518412 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2018-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rachmawan, IEW, Tadono, T, Hayashi, M & Kiyoki, Y 2018, Temporal difference and density-based learning method applied for deforestation detection using ALOS-2/PALSAR-2. in 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings., 8518412, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2018-July, Institute of Electrical and Electronics Engineers Inc., pp. 4905-4908, 38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018, Valencia, Spain, 18/7/22. https://doi.org/10.1109/IGARSS.2018.8518412
Rachmawan IEW, Tadono T, Hayashi M, Kiyoki Y. Temporal difference and density-based learning method applied for deforestation detection using ALOS-2/PALSAR-2. In 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 4905-4908. 8518412. (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.2018.8518412
Rachmawan, Irene Erlyn Wina ; Tadono, Takeo ; Hayashi, Masato ; Kiyoki, Yasushi. / Temporal difference and density-based learning method applied for deforestation detection using ALOS-2/PALSAR-2. 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 4905-4908 (International Geoscience and Remote Sensing Symposium (IGARSS)).
@inproceedings{d6a29bb2fff344d98d8143dfb6c93334,
title = "Temporal difference and density-based learning method applied for deforestation detection using ALOS-2/PALSAR-2",
abstract = "Remote sensing has established as key technology for monitoring of environmental degradation such as forest clearing. One of the state-of-the-art microwave EO systems for forest monitoring is Japan's L-band ALOS-2/PALSAR-2 which provides outstanding means for observing tropical forests due its cloud and canopy penetration capability. However, the complexity of the physical backscattering properties of forests and the associated spatial and temporal variabilities, render straightforward change detection methods based on simple thresholding rather inaccurate with high false alarm rates. In this paper, we develop a framework to alleviate problems caused by forest backscatter variability. We define three essential elements, namely {"}structures of density{"}, {"}speed of change{"}, and {"}expansion patterns{"} which are obtained by differential computing between two repeat-pass PALSAR-2 images. To improve both the detection and assessing of deforestation, a {"}deforestation behavior pattern{"} is sought through temporal machine learning mechanism of the three proposed elements. Our results indicate that the use of {"}structure of density{"} can introduce a more robust performance for detecting deforestation. Meanwhile, {"}speed of change{"} and {"}expansion pattern{"} are capable to provide additional information with respect to the drivers of deforestation and the land-use change.",
keywords = "Density-based, Synthetic Aperture Radar (SAR), Temporal difference learning",
author = "Rachmawan, {Irene Erlyn Wina} and Takeo Tadono and Masato Hayashi and Yasushi Kiyoki",
year = "2018",
month = "10",
day = "31",
doi = "10.1109/IGARSS.2018.8518412",
language = "English",
series = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4905--4908",
booktitle = "2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings",

}

TY - GEN

T1 - Temporal difference and density-based learning method applied for deforestation detection using ALOS-2/PALSAR-2

AU - Rachmawan, Irene Erlyn Wina

AU - Tadono, Takeo

AU - Hayashi, Masato

AU - Kiyoki, Yasushi

PY - 2018/10/31

Y1 - 2018/10/31

N2 - Remote sensing has established as key technology for monitoring of environmental degradation such as forest clearing. One of the state-of-the-art microwave EO systems for forest monitoring is Japan's L-band ALOS-2/PALSAR-2 which provides outstanding means for observing tropical forests due its cloud and canopy penetration capability. However, the complexity of the physical backscattering properties of forests and the associated spatial and temporal variabilities, render straightforward change detection methods based on simple thresholding rather inaccurate with high false alarm rates. In this paper, we develop a framework to alleviate problems caused by forest backscatter variability. We define three essential elements, namely "structures of density", "speed of change", and "expansion patterns" which are obtained by differential computing between two repeat-pass PALSAR-2 images. To improve both the detection and assessing of deforestation, a "deforestation behavior pattern" is sought through temporal machine learning mechanism of the three proposed elements. Our results indicate that the use of "structure of density" can introduce a more robust performance for detecting deforestation. Meanwhile, "speed of change" and "expansion pattern" are capable to provide additional information with respect to the drivers of deforestation and the land-use change.

AB - Remote sensing has established as key technology for monitoring of environmental degradation such as forest clearing. One of the state-of-the-art microwave EO systems for forest monitoring is Japan's L-band ALOS-2/PALSAR-2 which provides outstanding means for observing tropical forests due its cloud and canopy penetration capability. However, the complexity of the physical backscattering properties of forests and the associated spatial and temporal variabilities, render straightforward change detection methods based on simple thresholding rather inaccurate with high false alarm rates. In this paper, we develop a framework to alleviate problems caused by forest backscatter variability. We define three essential elements, namely "structures of density", "speed of change", and "expansion patterns" which are obtained by differential computing between two repeat-pass PALSAR-2 images. To improve both the detection and assessing of deforestation, a "deforestation behavior pattern" is sought through temporal machine learning mechanism of the three proposed elements. Our results indicate that the use of "structure of density" can introduce a more robust performance for detecting deforestation. Meanwhile, "speed of change" and "expansion pattern" are capable to provide additional information with respect to the drivers of deforestation and the land-use change.

KW - Density-based

KW - Synthetic Aperture Radar (SAR)

KW - Temporal difference learning

UR - http://www.scopus.com/inward/record.url?scp=85063129681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063129681&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2018.8518412

DO - 10.1109/IGARSS.2018.8518412

M3 - Conference contribution

AN - SCOPUS:85063129681

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 4905

EP - 4908

BT - 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -