Analysis of Machine Learning Techniques for Sentinel-2A Satellite Images

This article presents the comparative analysis of classification techniques to assign land use and land cover classes from different strategies (pixel-based, object-based, rule-based, distance-based, and neural-based) with a Sentinel-2A satellite image for 2016. The study area is the Sana’a city of...

Full description

Saved in:
Bibliographic Details
Main Authors: Eman A. Alshari, Bharti W. Gawali
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/2022/9092299
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850232267041931264
author Eman A. Alshari
Bharti W. Gawali
author_facet Eman A. Alshari
Bharti W. Gawali
author_sort Eman A. Alshari
collection DOAJ
description This article presents the comparative analysis of classification techniques to assign land use and land cover classes from different strategies (pixel-based, object-based, rule-based, distance-based, and neural-based) with a Sentinel-2A satellite image for 2016. The study area is the Sana’a city of Yemen which covers about 18,796.88 km2 land area. This research aims to present the fundamentals of supervised machine learning approaches, including their limitations and strengths and experimentation for twelve classifiers. The outcome of experimentation showed that the Random Forest could be a good choice as a classifier for object-based strategy. In contrast, DTC and SVM were efficient in rule-based and pixel-based strategies. Results also showed that the highest accuracy was with object-based strategy, followed by rule-based and then pixel-based and distance-based strategies.
format Article
id doaj-art-09c97c810370483483dab18a8d4a9aff
institution OA Journals
issn 2090-0155
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series Journal of Electrical and Computer Engineering
spelling doaj-art-09c97c810370483483dab18a8d4a9aff2025-08-20T02:03:15ZengWileyJournal of Electrical and Computer Engineering2090-01552022-01-01202210.1155/2022/9092299Analysis of Machine Learning Techniques for Sentinel-2A Satellite ImagesEman A. Alshari0Bharti W. Gawali1Thamar UniversityDr. Babasaheb Ambedkar Marathwada UniversityThis article presents the comparative analysis of classification techniques to assign land use and land cover classes from different strategies (pixel-based, object-based, rule-based, distance-based, and neural-based) with a Sentinel-2A satellite image for 2016. The study area is the Sana’a city of Yemen which covers about 18,796.88 km2 land area. This research aims to present the fundamentals of supervised machine learning approaches, including their limitations and strengths and experimentation for twelve classifiers. The outcome of experimentation showed that the Random Forest could be a good choice as a classifier for object-based strategy. In contrast, DTC and SVM were efficient in rule-based and pixel-based strategies. Results also showed that the highest accuracy was with object-based strategy, followed by rule-based and then pixel-based and distance-based strategies.http://dx.doi.org/10.1155/2022/9092299
spellingShingle Eman A. Alshari
Bharti W. Gawali
Analysis of Machine Learning Techniques for Sentinel-2A Satellite Images
Journal of Electrical and Computer Engineering
title Analysis of Machine Learning Techniques for Sentinel-2A Satellite Images
title_full Analysis of Machine Learning Techniques for Sentinel-2A Satellite Images
title_fullStr Analysis of Machine Learning Techniques for Sentinel-2A Satellite Images
title_full_unstemmed Analysis of Machine Learning Techniques for Sentinel-2A Satellite Images
title_short Analysis of Machine Learning Techniques for Sentinel-2A Satellite Images
title_sort analysis of machine learning techniques for sentinel 2a satellite images
url http://dx.doi.org/10.1155/2022/9092299
work_keys_str_mv AT emanaalshari analysisofmachinelearningtechniquesforsentinel2asatelliteimages
AT bhartiwgawali analysisofmachinelearningtechniquesforsentinel2asatelliteimages