A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia

Research output: Contribution to journalArticle

Standard

A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia. / Crowson, Merry; Warren-Thomas, Eleanor May; Hill, Jane Katharine; Hariyadi, Bambang; Agus, Fahmuddin; Saad, Asmadi; Hamer, Keith C.; Hodgson, Jenny A.; Kartika, Winda D.; Lucey, Jennifer Marie; McClean, Colin John; Nurida, Neneng Laela; Pratiwi, Etty; Stringer, Lindsay C.; Ward, Caroline; Pettorelli, Nathalie.

In: Remote Sensing in Ecology and Conservation, 10.12.2018.

Research output: Contribution to journalArticle

Harvard

Crowson, M, Warren-Thomas, EM, Hill, JK, Hariyadi, B, Agus, F, Saad, A, Hamer, KC, Hodgson, JA, Kartika, WD, Lucey, JM, McClean, CJ, Nurida, NL, Pratiwi, E, Stringer, LC, Ward, C & Pettorelli, N 2018, 'A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia', Remote Sensing in Ecology and Conservation. https://doi.org/10.1002/rse2.102

APA

Crowson, M., Warren-Thomas, E. M., Hill, J. K., Hariyadi, B., Agus, F., Saad, A., ... Pettorelli, N. (2018). A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia. Remote Sensing in Ecology and Conservation. https://doi.org/10.1002/rse2.102

Vancouver

Crowson M, Warren-Thomas EM, Hill JK, Hariyadi B, Agus F, Saad A et al. A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia. Remote Sensing in Ecology and Conservation. 2018 Dec 10. https://doi.org/10.1002/rse2.102

Author

Crowson, Merry ; Warren-Thomas, Eleanor May ; Hill, Jane Katharine ; Hariyadi, Bambang ; Agus, Fahmuddin ; Saad, Asmadi ; Hamer, Keith C. ; Hodgson, Jenny A. ; Kartika, Winda D. ; Lucey, Jennifer Marie ; McClean, Colin John ; Nurida, Neneng Laela ; Pratiwi, Etty ; Stringer, Lindsay C. ; Ward, Caroline ; Pettorelli, Nathalie. / A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia. In: Remote Sensing in Ecology and Conservation. 2018.

Bibtex - Download

@article{a9fc91053fb44e1b8e08ed15a8fe0f0b,
title = "A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia",
abstract = "The loss of huge areas of peat swamp forest in Southeast Asia and the resulting negative environmental effects, both local and global, have led to an increasing interest in peat restoration in the region. Satellite remote sensing offers the potential to provide up-to-date information on peat swamp forest loss across large areas, and support spatially explicit conservation and restoration planning. Fusion of optical and radar remote sensing data may be particularly valuable in this context, as most peat swamp forests are in areas with high cloud cover, which limits the use of optical data. Radar data can “see through” cloud, but experience so far has shown that it doesn’t discriminate well between certain types of land cover. Various approaches to fusion exist, but there is little information on how they compare. To assess this untapped potential, we compare three different classification methods with Sentinel-1 and Sentinel-2 images to map the remnant distribution of peat swamp forest in the area surrounding Sungai Buluh Protection Forest, Sumatra, Indonesia. Results show that data fusion increases overall accuracy in one of the three methods, compared to the use of optical data only. When data fusion was used with the pixel-based classification using the original pixel values, overall accuracy increased by a small, but statistically significant amount. Data fusion was not beneficial in the case of object-based classification or pixelbased classification using principal components. This indicates optical data are still the main source of information for land cover mapping in the region. Based on our findings, we provide methodological recommendations to help those involved in peatland restoration capitalise on the potential of big data.",
author = "Merry Crowson and Warren-Thomas, {Eleanor May} and Hill, {Jane Katharine} and Bambang Hariyadi and Fahmuddin Agus and Asmadi Saad and Hamer, {Keith C.} and Hodgson, {Jenny A.} and Kartika, {Winda D.} and Lucey, {Jennifer Marie} and McClean, {Colin John} and Nurida, {Neneng Laela} and Etty Pratiwi and Stringer, {Lindsay C.} and Caroline Ward and Nathalie Pettorelli",
year = "2018",
month = "12",
day = "10",
doi = "10.1002/rse2.102",
language = "English",
journal = "Remote Sensing in Ecology and Conservation",
issn = "2056-3485",
publisher = "Wiley-Blackwell Publishing Ltd",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia

AU - Crowson, Merry

AU - Warren-Thomas, Eleanor May

AU - Hill, Jane Katharine

AU - Hariyadi, Bambang

AU - Agus, Fahmuddin

AU - Saad, Asmadi

AU - Hamer, Keith C.

AU - Hodgson, Jenny A.

AU - Kartika, Winda D.

AU - Lucey, Jennifer Marie

AU - McClean, Colin John

AU - Nurida, Neneng Laela

AU - Pratiwi, Etty

AU - Stringer, Lindsay C.

AU - Ward, Caroline

AU - Pettorelli, Nathalie

PY - 2018/12/10

Y1 - 2018/12/10

N2 - The loss of huge areas of peat swamp forest in Southeast Asia and the resulting negative environmental effects, both local and global, have led to an increasing interest in peat restoration in the region. Satellite remote sensing offers the potential to provide up-to-date information on peat swamp forest loss across large areas, and support spatially explicit conservation and restoration planning. Fusion of optical and radar remote sensing data may be particularly valuable in this context, as most peat swamp forests are in areas with high cloud cover, which limits the use of optical data. Radar data can “see through” cloud, but experience so far has shown that it doesn’t discriminate well between certain types of land cover. Various approaches to fusion exist, but there is little information on how they compare. To assess this untapped potential, we compare three different classification methods with Sentinel-1 and Sentinel-2 images to map the remnant distribution of peat swamp forest in the area surrounding Sungai Buluh Protection Forest, Sumatra, Indonesia. Results show that data fusion increases overall accuracy in one of the three methods, compared to the use of optical data only. When data fusion was used with the pixel-based classification using the original pixel values, overall accuracy increased by a small, but statistically significant amount. Data fusion was not beneficial in the case of object-based classification or pixelbased classification using principal components. This indicates optical data are still the main source of information for land cover mapping in the region. Based on our findings, we provide methodological recommendations to help those involved in peatland restoration capitalise on the potential of big data.

AB - The loss of huge areas of peat swamp forest in Southeast Asia and the resulting negative environmental effects, both local and global, have led to an increasing interest in peat restoration in the region. Satellite remote sensing offers the potential to provide up-to-date information on peat swamp forest loss across large areas, and support spatially explicit conservation and restoration planning. Fusion of optical and radar remote sensing data may be particularly valuable in this context, as most peat swamp forests are in areas with high cloud cover, which limits the use of optical data. Radar data can “see through” cloud, but experience so far has shown that it doesn’t discriminate well between certain types of land cover. Various approaches to fusion exist, but there is little information on how they compare. To assess this untapped potential, we compare three different classification methods with Sentinel-1 and Sentinel-2 images to map the remnant distribution of peat swamp forest in the area surrounding Sungai Buluh Protection Forest, Sumatra, Indonesia. Results show that data fusion increases overall accuracy in one of the three methods, compared to the use of optical data only. When data fusion was used with the pixel-based classification using the original pixel values, overall accuracy increased by a small, but statistically significant amount. Data fusion was not beneficial in the case of object-based classification or pixelbased classification using principal components. This indicates optical data are still the main source of information for land cover mapping in the region. Based on our findings, we provide methodological recommendations to help those involved in peatland restoration capitalise on the potential of big data.

U2 - 10.1002/rse2.102

DO - 10.1002/rse2.102

M3 - Article

JO - Remote Sensing in Ecology and Conservation

T2 - Remote Sensing in Ecology and Conservation

JF - Remote Sensing in Ecology and Conservation

SN - 2056-3485

ER -