Cover Image

Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia

Accurate land use information is the basis for scientific research related to carbon cycle analysis, hydro-climatic modelling, soil degradation assessment, etc. It is also an indispensable basic information for local land management departments in land use planning and management. With development i...

Full description

Saved in:
Bibliographic Details
Main Authors: Ju, Zeng, Tan, Mou Leong, Narimah Samat,, Chang, Chun Kiat
Format: Article
Language:English
Published: Penerbit Universiti Kebangsaan Malaysia 2021
Online Access:http://journalarticle.ukm.my/18101/1/47689-164856-1-PB.pdf
http://journalarticle.ukm.my/18101/
https://ejournal.ukm.my/gmjss/issue/view/1418
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-ukm.journal.18101
record_format eprints
spelling my-ukm.journal.181012022-02-21T01:14:12Z http://journalarticle.ukm.my/18101/ Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia Ju, Zeng Tan, Mou Leong Narimah Samat, Chang, Chun Kiat Accurate land use information is the basis for scientific research related to carbon cycle analysis, hydro-climatic modelling, soil degradation assessment, etc. It is also an indispensable basic information for local land management departments in land use planning and management. With development in big data and internet network, Google Earth Engine (GEE), a cloud-based computing platform allows users to perform satellite images processing more efficiently. This study aims to improve the land use mapping in a tropical region based on the GEE platform. Seven satellite images and indices combinations include Landsat 8 (C1), Sentinel-2 (C2), Landsat 8+Sentinel-2 (C3), Landsat 8+Indices (C4), Sentinel-2+Indices (C5), Landsat 8+Sentinel-2+Indices (C6), Normalized Difference Vegetation Index (NDVI)+Normalized Difference Water Index (NDWI)+Enhanced Vegetation Index (EVI)+Elevation (C7) were developed to evaluate the best combination for land use mapping in the Johor River Basin (JRB), Malaysia. The Random Forest (RF) algorithm was used to classify the land use land cover (LULC) with 222 training samples and 78 verification samples obtained through the Google Earth Pro higher resolution satellite images and field samplings. The results show that the overall accuracies of all the seven combinations are mostly more than 75%, ranging from 72% (C1) to 86% (C6). The findings show that adding of additional indices information before the land use classification helps to increase the overall accuracy significantly. For instance, the overall accuracy of the C6 combination is 14% higher than that of the Landsat 8 image solely. This study can act as a reference to effectively improve the land use mapping in cloud-prone tropical regions. Penerbit Universiti Kebangsaan Malaysia 2021 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/18101/1/47689-164856-1-PB.pdf Ju, Zeng and Tan, Mou Leong and Narimah Samat, and Chang, Chun Kiat (2021) Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia. Geografia : Malaysian Journal of Society and Space, 17 (3). pp. 30-46. ISSN 2180-2491 https://ejournal.ukm.my/gmjss/issue/view/1418
institution Universiti Kebangsaan Malaysia
building Tun Sri Lanang Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Kebangsaan Malaysia
content_source UKM Journal Article Repository
url_provider http://journalarticle.ukm.my/
language English
description Accurate land use information is the basis for scientific research related to carbon cycle analysis, hydro-climatic modelling, soil degradation assessment, etc. It is also an indispensable basic information for local land management departments in land use planning and management. With development in big data and internet network, Google Earth Engine (GEE), a cloud-based computing platform allows users to perform satellite images processing more efficiently. This study aims to improve the land use mapping in a tropical region based on the GEE platform. Seven satellite images and indices combinations include Landsat 8 (C1), Sentinel-2 (C2), Landsat 8+Sentinel-2 (C3), Landsat 8+Indices (C4), Sentinel-2+Indices (C5), Landsat 8+Sentinel-2+Indices (C6), Normalized Difference Vegetation Index (NDVI)+Normalized Difference Water Index (NDWI)+Enhanced Vegetation Index (EVI)+Elevation (C7) were developed to evaluate the best combination for land use mapping in the Johor River Basin (JRB), Malaysia. The Random Forest (RF) algorithm was used to classify the land use land cover (LULC) with 222 training samples and 78 verification samples obtained through the Google Earth Pro higher resolution satellite images and field samplings. The results show that the overall accuracies of all the seven combinations are mostly more than 75%, ranging from 72% (C1) to 86% (C6). The findings show that adding of additional indices information before the land use classification helps to increase the overall accuracy significantly. For instance, the overall accuracy of the C6 combination is 14% higher than that of the Landsat 8 image solely. This study can act as a reference to effectively improve the land use mapping in cloud-prone tropical regions.
format Article
author Ju, Zeng
Tan, Mou Leong
Narimah Samat,
Chang, Chun Kiat
spellingShingle Ju, Zeng
Tan, Mou Leong
Narimah Samat,
Chang, Chun Kiat
Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia
author_facet Ju, Zeng
Tan, Mou Leong
Narimah Samat,
Chang, Chun Kiat
author_sort Ju, Zeng
title Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia
title_short Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia
title_full Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia
title_fullStr Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia
title_full_unstemmed Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia
title_sort comparison of landsat 8, sentinel-2 and spectral indices combinations for google earth engine-based land use mapping in the johor river basin, malaysia
publisher Penerbit Universiti Kebangsaan Malaysia
publishDate 2021
url http://journalarticle.ukm.my/18101/1/47689-164856-1-PB.pdf
http://journalarticle.ukm.my/18101/
https://ejournal.ukm.my/gmjss/issue/view/1418
_version_ 1725973510850871296
score 13.211869

Similar Items