Comparison of Machine Learning Methods for Satellite Image Classification: A Case Study of Casablanca Using Landsat Imagery and Google Earth Engine

IF 0.9 4区 环境科学与生态学 Q4 ENVIRONMENTAL SCIENCES Carpathian Journal of Earth and Environmental Sciences Pub Date : 2023-11-14 DOI:10.30564/jees.v5i2.5928
Hafsa Ouchra, Abdessamad Belangour, Allae Erraissi
{"title":"Comparison of Machine Learning Methods for Satellite Image Classification: A Case Study of Casablanca Using Landsat Imagery and Google Earth Engine","authors":"Hafsa Ouchra, Abdessamad Belangour, Allae Erraissi","doi":"10.30564/jees.v5i2.5928","DOIUrl":null,"url":null,"abstract":"Satellite image classification is crucial in various applications such as urban planning, environmental monitoring, and land use analysis. In this study, the authors present a comparative analysis of different supervised and unsupervised learning methods for satellite image classification, focusing on a case study in Casablanca using Landsat 8 imagery. This research aims to identify the most effective machine-learning approach for accurately classifying land cover in an urban environment. The methodology used consists of the pre-processing of Landsat imagery data from Casablanca city, the authors extract relevant features and partition them into training and test sets, and then use random forest (RF), SVM (support vector machine), classification, and regression tree (CART), gradient tree boost (GTB), decision tree (DT), and minimum distance (MD) algorithms. Through a series of experiments, the authors evaluate the performance of each machine learning method in terms of accuracy, and Kappa coefficient. This work shows that random forest is the best-performing algorithm, with an accuracy of 95.42% and 0.94 Kappa coefficient. The authors discuss the factors of their performance, including data characteristics, accurate selection, and model influencing.","PeriodicalId":55272,"journal":{"name":"Carpathian Journal of Earth and Environmental Sciences","volume":"6 10","pages":"0"},"PeriodicalIF":0.9000,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Carpathian Journal of Earth and Environmental Sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.30564/jees.v5i2.5928","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Satellite image classification is crucial in various applications such as urban planning, environmental monitoring, and land use analysis. In this study, the authors present a comparative analysis of different supervised and unsupervised learning methods for satellite image classification, focusing on a case study in Casablanca using Landsat 8 imagery. This research aims to identify the most effective machine-learning approach for accurately classifying land cover in an urban environment. The methodology used consists of the pre-processing of Landsat imagery data from Casablanca city, the authors extract relevant features and partition them into training and test sets, and then use random forest (RF), SVM (support vector machine), classification, and regression tree (CART), gradient tree boost (GTB), decision tree (DT), and minimum distance (MD) algorithms. Through a series of experiments, the authors evaluate the performance of each machine learning method in terms of accuracy, and Kappa coefficient. This work shows that random forest is the best-performing algorithm, with an accuracy of 95.42% and 0.94 Kappa coefficient. The authors discuss the factors of their performance, including data characteristics, accurate selection, and model influencing.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
卫星图像分类的机器学习方法比较:以卡萨布兰卡Landsat图像和Google Earth引擎为例
卫星图像分类在城市规划、环境监测和土地利用分析等各种应用中至关重要。在本研究中,作者比较分析了不同的有监督和无监督学习方法用于卫星图像分类,并以卡萨布兰卡使用Landsat 8图像为例进行了研究。本研究旨在确定最有效的机器学习方法,以准确分类城市环境中的土地覆盖。采用的方法是对卡萨布兰卡市Landsat图像数据进行预处理,提取相关特征并将其划分为训练集和测试集,然后使用随机森林(RF)、支持向量机(SVM)、分类回归树(CART)、梯度树增强(GTB)、决策树(DT)和最小距离(MD)算法。通过一系列的实验,作者从准确性和Kappa系数方面评估了每种机器学习方法的性能。研究表明,随机森林算法的准确率为95.42%,Kappa系数为0.94,是性能最好的算法。作者讨论了影响其性能的因素,包括数据特征、准确选择和模型影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
2.30
自引率
25.00%
发文量
42
审稿时长
12-24 weeks
期刊介绍: The publishing of CARPATHIAN JOURNAL of EARTH and ENVIRONMENTAL SCIENCES has started in 2006. The regularity of this magazine is biannual. The magazine will publish scientific works, in international purposes, in different areas of research, such as : geology, geography, environmental sciences, the environmental pollution and protection, environmental chemistry and physic, environmental biodegradation, climatic exchanges, fighting against natural disasters, protected areas, soil degradation, water quality, water supplies, sustainable development.
期刊最新文献
Hydrogeological Investigations of Groundwater and Surface Water Interactions in the Berg River Catchment, Western Cape, South Africa Comparison of Machine Learning Methods for Satellite Image Classification: A Case Study of Casablanca Using Landsat Imagery and Google Earth Engine SAR Change Detection Algorithm Combined with FFDNet Spatial Denoising Hyperspectral Inversion and Analysis of Zinc Concentration in Urban Soil in the Urumqi City of China Maximizing Oil Palm Yield: Innovative Replanting Strategies for Sustainable Productivity
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1