Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review
Several machine-learning algorithms have been proposed for remote sensing image classification during the past two decades. Among these machine learning algorithms, Random Forest (RF) and Support Vector Machines (SVM) have drawn attention to image classification in several remote sensing application...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9206124/ |
| _version_ | 1818740466587271168 |
|---|---|
| author | Mohammadreza Sheykhmousa Masoud Mahdianpari Hamid Ghanbari Fariba Mohammadimanesh Pedram Ghamisi Saeid Homayouni |
| author_facet | Mohammadreza Sheykhmousa Masoud Mahdianpari Hamid Ghanbari Fariba Mohammadimanesh Pedram Ghamisi Saeid Homayouni |
| author_sort | Mohammadreza Sheykhmousa |
| collection | DOAJ |
| description | Several machine-learning algorithms have been proposed for remote sensing image classification during the past two decades. Among these machine learning algorithms, Random Forest (RF) and Support Vector Machines (SVM) have drawn attention to image classification in several remote sensing applications. This article reviews RF and SVM concepts relevant to remote sensing image classification and applies a meta-analysis of 251 peer-reviewed journal papers. A database with more than 40 quantitative and qualitative fields was constructed from these reviewed papers. The meta-analysis mainly focuses on 1) the analysis regarding the general characteristics of the studies, such as geographical distribution, frequency of the papers considering time, journals, application domains, and remote sensing software packages used in the case studies, and 2) a comparative analysis regarding the performances of RF and SVM classification against various parameters, such as data type, RS applications, spatial resolution, and the number of extracted features in the feature engineering step. The challenges, recommendations, and potential directions for future research are also discussed in detail. Moreover, a summary of the results is provided to aid researchers to customize their efforts in order to achieve the most accurate results based on their thematic applications. |
| first_indexed | 2024-12-18T01:41:11Z |
| format | Article |
| id | doaj.art-8cfa189466d14ab4a2b9ae18db871f80 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-18T01:41:11Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-8cfa189466d14ab4a2b9ae18db871f802022-12-21T21:25:19ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01136308632510.1109/JSTARS.2020.30267249206124Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic ReviewMohammadreza Sheykhmousa0https://orcid.org/0000-0002-3673-7544Masoud Mahdianpari1https://orcid.org/0000-0002-7234-959XHamid Ghanbari2https://orcid.org/0000-0002-9557-495XFariba Mohammadimanesh3Pedram Ghamisi4https://orcid.org/0000-0003-1203-741XSaeid Homayouni5https://orcid.org/0000-0002-0214-5356OpenGeoHub, Wageningen, The NetherlandsC-CORE, St. John's, NL, CanadaDepartment of Geography, Université Laval, Québec, QC, CanadaC-CORE, St. John's, NL, CanadaDivision of “Exploration Technology,” Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg for Resource Technology, Freiberg, GermanyCentre Eau Terre Environnement, Institut National de la Recherche Scientifique, Quebec City, QC, CanadaSeveral machine-learning algorithms have been proposed for remote sensing image classification during the past two decades. Among these machine learning algorithms, Random Forest (RF) and Support Vector Machines (SVM) have drawn attention to image classification in several remote sensing applications. This article reviews RF and SVM concepts relevant to remote sensing image classification and applies a meta-analysis of 251 peer-reviewed journal papers. A database with more than 40 quantitative and qualitative fields was constructed from these reviewed papers. The meta-analysis mainly focuses on 1) the analysis regarding the general characteristics of the studies, such as geographical distribution, frequency of the papers considering time, journals, application domains, and remote sensing software packages used in the case studies, and 2) a comparative analysis regarding the performances of RF and SVM classification against various parameters, such as data type, RS applications, spatial resolution, and the number of extracted features in the feature engineering step. The challenges, recommendations, and potential directions for future research are also discussed in detail. Moreover, a summary of the results is provided to aid researchers to customize their efforts in order to achieve the most accurate results based on their thematic applications.https://ieeexplore.ieee.org/document/9206124/Image classificationmeta-analysisrandom forest (RF)remote sensing (RS)support vector machine (SVM) |
| spellingShingle | Mohammadreza Sheykhmousa Masoud Mahdianpari Hamid Ghanbari Fariba Mohammadimanesh Pedram Ghamisi Saeid Homayouni Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Image classification meta-analysis random forest (RF) remote sensing (RS) support vector machine (SVM) |
| title | Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review |
| title_full | Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review |
| title_fullStr | Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review |
| title_full_unstemmed | Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review |
| title_short | Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review |
| title_sort | support vector machine versus random forest for remote sensing image classification a meta analysis and systematic review |
| topic | Image classification meta-analysis random forest (RF) remote sensing (RS) support vector machine (SVM) |
| url | https://ieeexplore.ieee.org/document/9206124/ |
| work_keys_str_mv | AT mohammadrezasheykhmousa supportvectormachineversusrandomforestforremotesensingimageclassificationametaanalysisandsystematicreview AT masoudmahdianpari supportvectormachineversusrandomforestforremotesensingimageclassificationametaanalysisandsystematicreview AT hamidghanbari supportvectormachineversusrandomforestforremotesensingimageclassificationametaanalysisandsystematicreview AT faribamohammadimanesh supportvectormachineversusrandomforestforremotesensingimageclassificationametaanalysisandsystematicreview AT pedramghamisi supportvectormachineversusrandomforestforremotesensingimageclassificationametaanalysisandsystematicreview AT saeidhomayouni supportvectormachineversusrandomforestforremotesensingimageclassificationametaanalysisandsystematicreview |