No Cover Image

Journal article 56 views 3 downloads

Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq

Akram Al-Qaraghuli, Peter North Orcid Logo, Iain Bye, Jacqueline Rosette Orcid Logo, Sietse Los

International Journal of Remote Sensing, Pages: 1 - 30

Swansea University Authors: Akram Al-Qaraghuli, Peter North Orcid Logo, Jacqueline Rosette Orcid Logo, Sietse Los

  • 71928.VOR.pdf

    PDF | Version of Record

    © 2026 The Author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License.

    Download (6.16MB)

Check full text

DOI (Published version): 10.1080/01431161.2026.2676245

Abstract

Using the Google Earth Engine platform, this study compares three datasets from the Planet, Sentinel-2A, and Landsat 8 satellites for the study of Najaf Province, Iraq, at spatial resolutions of 3.7 m, 10 m, and 30 m, respectively. Seven algorithms (smileCART, Random Forest, Gradient Tree Boost, Sup...

Full description

Published in: International Journal of Remote Sensing
ISSN: 0143-1161 1366-5901
Published: Informa UK Limited 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71928
first_indexed 2026-05-18T09:37:04Z
last_indexed 2026-06-17T04:33:57Z
id cronfa71928
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-06-16T14:00:19.3824897</datestamp><bib-version>v2</bib-version><id>71928</id><entry>2026-05-18</entry><title>Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq</title><swanseaauthors><author><sid>b05c3a23e1b8c1a60a84924b9d93ad98</sid><ORCID/><firstname>Akram</firstname><surname>Al-Qaraghuli</surname><name>Akram Al-Qaraghuli</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>fc45a0cb36c24d6cf35313a8c808652f</sid><ORCID>0000-0001-9933-6935</ORCID><firstname>Peter</firstname><surname>North</surname><name>Peter North</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>0307f116e8f87a83cf4080c493fb7590</sid><ORCID>0000-0002-2589-0244</ORCID><firstname>Jacqueline</firstname><surname>Rosette</surname><name>Jacqueline Rosette</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>6d529d947d3b37d7597b36956983cf16</sid><ORCID/><firstname>Sietse</firstname><surname>Los</surname><name>Sietse Los</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-05-18</date><abstract>Using the Google Earth Engine platform, this study compares three datasets from the Planet, Sentinel-2A, and Landsat 8 satellites for the study of Najaf Province, Iraq, at spatial resolutions of 3.7&#x2009;m, 10&#x2009;m, and 30&#x2009;m, respectively. Seven algorithms (smileCART, Random Forest, Gradient Tree Boost, Support Vector Machine, Minimum Distance, Naive Bayes, and k-Nearest Neighbour) are tested. The primary objectives were to evaluate Land Use and Land Cover (LULC) mapping, and to select a suitable algorithm and dataset. Achieving accurate mapping of LULC categories remains a major challenge, particularly within semi-arid regions characterized by complex farming systems. Supervised classification techniques, specifically the seven algorithms, were applied, and ten classes were successfully identified, namely Irrigated Cropland, Watercourses, Water Bodies, Sandy Areas and Dunes, Arable Land, Bare Areas, Wetland, Urban and Industrial Areas, Palm, and Shrubland. The overall accuracy was computed for each classifier algorithm after the collection of 28&#x2013;55 samples representing the ground truth for each identified class. Among the classifiers, Planet reached the highest overall accuracy of 92% with the smileCART algorithm, followed by 88% with Gradient Tree Boost and 86% with Random Forest. On the other side, Sentinel-2A achieved a maximum accuracy of 81% (Gradient Tree Boost and Random Forest), while Landsat 8 presented an overall accuracy of 78% using Random Forest. A test using only common bands across all sensors showed that spatial resolution contributes approximately three times more to classification accuracy than spectral richness in this semi-arid environment. It is noteworthy that the Planet satellite demonstrated an ability to distinguish Shrubland from other land cover classes compared to Sentinel-2A and Landsat 8. Since the grassland/shrubland transition is critical in the ecology and degradation of arid and semi-arid regions, the study suggests a role for recently available high-resolution satellite imagery to improve monitoring of such regions.</abstract><type>Journal Article</type><journal>International Journal of Remote Sensing</journal><volume>0</volume><journalNumber/><paginationStart>1</paginationStart><paginationEnd>30</paginationEnd><publisher>Informa UK Limited</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0143-1161</issnPrint><issnElectronic>1366-5901</issnElectronic><keywords/><publishedDay>29</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-05-29</publishedDate><doi>10.1080/01431161.2026.2676245</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>National Centre for Earth Observation</funders><projectreference/><lastEdited>2026-06-16T14:00:19.3824897</lastEdited><Created>2026-05-18T10:33:36.5364825</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering</level></path><authors><author><firstname>Akram</firstname><surname>Al-Qaraghuli</surname><orcid/><order>1</order></author><author><firstname>Peter</firstname><surname>North</surname><orcid>0000-0001-9933-6935</orcid><order>2</order></author><author><firstname>Iain</firstname><surname>Bye</surname><order>3</order></author><author><firstname>Jacqueline</firstname><surname>Rosette</surname><orcid>0000-0002-2589-0244</orcid><order>4</order></author><author><firstname>Sietse</firstname><surname>Los</surname><orcid/><order>5</order></author></authors><documents><document><filename>71928__36978__37ce837645864d80b808ef9ec557323a.pdf</filename><originalFilename>71928.VOR.pdf</originalFilename><uploaded>2026-06-16T13:56:43.7931910</uploaded><type>Output</type><contentLength>6454979</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2026 The Author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-06-16T14:00:19.3824897 v2 71928 2026-05-18 Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq b05c3a23e1b8c1a60a84924b9d93ad98 Akram Al-Qaraghuli Akram Al-Qaraghuli true false fc45a0cb36c24d6cf35313a8c808652f 0000-0001-9933-6935 Peter North Peter North true false 0307f116e8f87a83cf4080c493fb7590 0000-0002-2589-0244 Jacqueline Rosette Jacqueline Rosette true false 6d529d947d3b37d7597b36956983cf16 Sietse Los Sietse Los true false 2026-05-18 Using the Google Earth Engine platform, this study compares three datasets from the Planet, Sentinel-2A, and Landsat 8 satellites for the study of Najaf Province, Iraq, at spatial resolutions of 3.7 m, 10 m, and 30 m, respectively. Seven algorithms (smileCART, Random Forest, Gradient Tree Boost, Support Vector Machine, Minimum Distance, Naive Bayes, and k-Nearest Neighbour) are tested. The primary objectives were to evaluate Land Use and Land Cover (LULC) mapping, and to select a suitable algorithm and dataset. Achieving accurate mapping of LULC categories remains a major challenge, particularly within semi-arid regions characterized by complex farming systems. Supervised classification techniques, specifically the seven algorithms, were applied, and ten classes were successfully identified, namely Irrigated Cropland, Watercourses, Water Bodies, Sandy Areas and Dunes, Arable Land, Bare Areas, Wetland, Urban and Industrial Areas, Palm, and Shrubland. The overall accuracy was computed for each classifier algorithm after the collection of 28–55 samples representing the ground truth for each identified class. Among the classifiers, Planet reached the highest overall accuracy of 92% with the smileCART algorithm, followed by 88% with Gradient Tree Boost and 86% with Random Forest. On the other side, Sentinel-2A achieved a maximum accuracy of 81% (Gradient Tree Boost and Random Forest), while Landsat 8 presented an overall accuracy of 78% using Random Forest. A test using only common bands across all sensors showed that spatial resolution contributes approximately three times more to classification accuracy than spectral richness in this semi-arid environment. It is noteworthy that the Planet satellite demonstrated an ability to distinguish Shrubland from other land cover classes compared to Sentinel-2A and Landsat 8. Since the grassland/shrubland transition is critical in the ecology and degradation of arid and semi-arid regions, the study suggests a role for recently available high-resolution satellite imagery to improve monitoring of such regions. Journal Article International Journal of Remote Sensing 0 1 30 Informa UK Limited 0143-1161 1366-5901 29 5 2026 2026-05-29 10.1080/01431161.2026.2676245 COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) National Centre for Earth Observation 2026-06-16T14:00:19.3824897 2026-05-18T10:33:36.5364825 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Akram Al-Qaraghuli 1 Peter North 0000-0001-9933-6935 2 Iain Bye 3 Jacqueline Rosette 0000-0002-2589-0244 4 Sietse Los 5 71928__36978__37ce837645864d80b808ef9ec557323a.pdf 71928.VOR.pdf 2026-06-16T13:56:43.7931910 Output 6454979 application/pdf Version of Record true © 2026 The Author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License. true eng https://creativecommons.org/licenses/by-nc-nd/4.0/
title Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq
spellingShingle Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq
Akram Al-Qaraghuli
Peter North
Jacqueline Rosette
Sietse Los
title_short Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq
title_full Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq
title_fullStr Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq
title_full_unstemmed Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq
title_sort Comparative assessment of land use and land cover classification from Planet, Landsat 8, and Sentinel-2A data in the semi-arid region of Najaf, Iraq
author_id_str_mv b05c3a23e1b8c1a60a84924b9d93ad98
fc45a0cb36c24d6cf35313a8c808652f
0307f116e8f87a83cf4080c493fb7590
6d529d947d3b37d7597b36956983cf16
author_id_fullname_str_mv b05c3a23e1b8c1a60a84924b9d93ad98_***_Akram Al-Qaraghuli
fc45a0cb36c24d6cf35313a8c808652f_***_Peter North
0307f116e8f87a83cf4080c493fb7590_***_Jacqueline Rosette
6d529d947d3b37d7597b36956983cf16_***_Sietse Los
author Akram Al-Qaraghuli
Peter North
Jacqueline Rosette
Sietse Los
author2 Akram Al-Qaraghuli
Peter North
Iain Bye
Jacqueline Rosette
Sietse Los
format Journal article
container_title International Journal of Remote Sensing
container_volume 0
container_start_page 1
publishDate 2026
institution Swansea University
issn 0143-1161
1366-5901
doi_str_mv 10.1080/01431161.2026.2676245
publisher Informa UK Limited
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering
document_store_str 1
active_str 0
description Using the Google Earth Engine platform, this study compares three datasets from the Planet, Sentinel-2A, and Landsat 8 satellites for the study of Najaf Province, Iraq, at spatial resolutions of 3.7 m, 10 m, and 30 m, respectively. Seven algorithms (smileCART, Random Forest, Gradient Tree Boost, Support Vector Machine, Minimum Distance, Naive Bayes, and k-Nearest Neighbour) are tested. The primary objectives were to evaluate Land Use and Land Cover (LULC) mapping, and to select a suitable algorithm and dataset. Achieving accurate mapping of LULC categories remains a major challenge, particularly within semi-arid regions characterized by complex farming systems. Supervised classification techniques, specifically the seven algorithms, were applied, and ten classes were successfully identified, namely Irrigated Cropland, Watercourses, Water Bodies, Sandy Areas and Dunes, Arable Land, Bare Areas, Wetland, Urban and Industrial Areas, Palm, and Shrubland. The overall accuracy was computed for each classifier algorithm after the collection of 28–55 samples representing the ground truth for each identified class. Among the classifiers, Planet reached the highest overall accuracy of 92% with the smileCART algorithm, followed by 88% with Gradient Tree Boost and 86% with Random Forest. On the other side, Sentinel-2A achieved a maximum accuracy of 81% (Gradient Tree Boost and Random Forest), while Landsat 8 presented an overall accuracy of 78% using Random Forest. A test using only common bands across all sensors showed that spatial resolution contributes approximately three times more to classification accuracy than spectral richness in this semi-arid environment. It is noteworthy that the Planet satellite demonstrated an ability to distinguish Shrubland from other land cover classes compared to Sentinel-2A and Landsat 8. Since the grassland/shrubland transition is critical in the ecology and degradation of arid and semi-arid regions, the study suggests a role for recently available high-resolution satellite imagery to improve monitoring of such regions.
published_date 2026-05-29T06:02:32Z
_version_ 1868490868920418304
score 11.109323

Similar Items