MAPPING OF BURNED AREA USING PRESENCE AND BACKGROUND LEARNING FRAMEWORK ON THE GOOGLE EARTH ENGINE PLATFORM
<p>Mapping of burned areas caused by forest fires was always a main concern to researchers in the field of remote sensing. Thus, various spectral indices and classification techniques have been proposed in the literature. In such a problem, only one specific class is of real interest and cou...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2019-08-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3-W8/37/2019/isprs-archives-XLII-3-W8-37-2019.pdf |
| _version_ | 1819121105009377280 |
|---|---|
| author | D. Attaf D. Attaf K. Djerriri D. Mansour D. Hamdadou |
| author_facet | D. Attaf D. Attaf K. Djerriri D. Mansour D. Hamdadou |
| author_sort | D. Attaf |
| collection | DOAJ |
| description | <p>Mapping of burned areas caused by forest fires was always a main concern to researchers in the field of remote sensing. Thus,
various spectral indices and classification techniques have been proposed in the literature. In such a problem, only one specific class
is of real interest and could be referred to as a one-class classification problem. One-class classification methods are highly desirable
for quick mapping of classes of interest. A common used solution to deal with One-Class classification problem is based on oneclass
support vector machine (OC-SVM). This method has proved useful in classification of remote sensing images. However, overfitting
problem and difficulty in tuning parameters have become the major obstacles for this method. The new Presence and
Background Learning (PBL) framework does not require complicated model selection and can generate very high accuracy results.
On the other hand the Google Earth Engine (GEE) portal provides access to satellite and other ancillary data, cloud computing, and
algorithms for processing large amounts of data with relative ease. Therefore, this study mainly aims to investigate the possibility of
using the PBL framework within the GEE platform to extract burned areas from freely available Landsat archive in the year 2015.
The quality of the results obtained using PBL framework was assessed using ground truth digitized by qualified technicians and
compared to other classification techniques: Thresholding burned area spectral Index (BAI) and OC-SVM classifiers. Experimental
results demonstrate that PBL framework for mapping the burned areas shows the higher classification accuracy than the other
classifiers, and it highlights the suitability for the cases with few positive labelled samples available, which facilitates the tedious
work of manual digitizing.</p> |
| first_indexed | 2024-12-22T06:31:16Z |
| format | Article |
| id | doaj.art-f6754e3f2ef9436c9fef832e972d35b3 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-22T06:31:16Z |
| publishDate | 2019-08-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-f6754e3f2ef9436c9fef832e972d35b32022-12-21T18:35:43ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342019-08-01XLII-3-W8374110.5194/isprs-archives-XLII-3-W8-37-2019MAPPING OF BURNED AREA USING PRESENCE AND BACKGROUND LEARNING FRAMEWORK ON THE GOOGLE EARTH ENGINE PLATFORMD. Attaf0D. Attaf1K. Djerriri2D. Mansour3D. Hamdadou4Department of Earth Observation, Centre des Techniques Spatiales, Arzew, AlgeriaDepartment of Computer Sciences, University of Oran 1 Ahmed Benbella, Laboratory LIO, AlgeriaDepartment of Earth Observation, Centre des Techniques Spatiales, Arzew, AlgeriaDepartment of Earth Observation, Centre des Techniques Spatiales, Arzew, AlgeriaDepartment of Computer Sciences, University of Oran 1 Ahmed Benbella, Laboratory LIO, Algeria<p>Mapping of burned areas caused by forest fires was always a main concern to researchers in the field of remote sensing. Thus, various spectral indices and classification techniques have been proposed in the literature. In such a problem, only one specific class is of real interest and could be referred to as a one-class classification problem. One-class classification methods are highly desirable for quick mapping of classes of interest. A common used solution to deal with One-Class classification problem is based on oneclass support vector machine (OC-SVM). This method has proved useful in classification of remote sensing images. However, overfitting problem and difficulty in tuning parameters have become the major obstacles for this method. The new Presence and Background Learning (PBL) framework does not require complicated model selection and can generate very high accuracy results. On the other hand the Google Earth Engine (GEE) portal provides access to satellite and other ancillary data, cloud computing, and algorithms for processing large amounts of data with relative ease. Therefore, this study mainly aims to investigate the possibility of using the PBL framework within the GEE platform to extract burned areas from freely available Landsat archive in the year 2015. The quality of the results obtained using PBL framework was assessed using ground truth digitized by qualified technicians and compared to other classification techniques: Thresholding burned area spectral Index (BAI) and OC-SVM classifiers. Experimental results demonstrate that PBL framework for mapping the burned areas shows the higher classification accuracy than the other classifiers, and it highlights the suitability for the cases with few positive labelled samples available, which facilitates the tedious work of manual digitizing.</p>https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3-W8/37/2019/isprs-archives-XLII-3-W8-37-2019.pdf |
| spellingShingle | D. Attaf D. Attaf K. Djerriri D. Mansour D. Hamdadou MAPPING OF BURNED AREA USING PRESENCE AND BACKGROUND LEARNING FRAMEWORK ON THE GOOGLE EARTH ENGINE PLATFORM The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | MAPPING OF BURNED AREA USING PRESENCE AND BACKGROUND LEARNING
FRAMEWORK ON THE GOOGLE EARTH ENGINE PLATFORM |
| title_full | MAPPING OF BURNED AREA USING PRESENCE AND BACKGROUND LEARNING
FRAMEWORK ON THE GOOGLE EARTH ENGINE PLATFORM |
| title_fullStr | MAPPING OF BURNED AREA USING PRESENCE AND BACKGROUND LEARNING
FRAMEWORK ON THE GOOGLE EARTH ENGINE PLATFORM |
| title_full_unstemmed | MAPPING OF BURNED AREA USING PRESENCE AND BACKGROUND LEARNING
FRAMEWORK ON THE GOOGLE EARTH ENGINE PLATFORM |
| title_short | MAPPING OF BURNED AREA USING PRESENCE AND BACKGROUND LEARNING
FRAMEWORK ON THE GOOGLE EARTH ENGINE PLATFORM |
| title_sort | mapping of burned area using presence and background learning framework on the google earth engine platform |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3-W8/37/2019/isprs-archives-XLII-3-W8-37-2019.pdf |
| work_keys_str_mv | AT dattaf mappingofburnedareausingpresenceandbackgroundlearningframeworkonthegoogleearthengineplatform AT dattaf mappingofburnedareausingpresenceandbackgroundlearningframeworkonthegoogleearthengineplatform AT kdjerriri mappingofburnedareausingpresenceandbackgroundlearningframeworkonthegoogleearthengineplatform AT dmansour mappingofburnedareausingpresenceandbackgroundlearningframeworkonthegoogleearthengineplatform AT dhamdadou mappingofburnedareausingpresenceandbackgroundlearningframeworkonthegoogleearthengineplatform |