Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020-09-25T00:00:00.000000Z)

TL;DR

A meta-analysis of 251 peer-reviewed journal papers relevant to remote sensing image classification and a comparative analysis regarding the performances of RF and SVM classification against various parameters is applied.

Abstract

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.

Authors

Pedram Ghamisi

7 papers

M. Sheykhmousa

1 papers

M. Mahdianpari

1 papers

References158 items

Multi-task convolutional neural networks outperformed random forest for mapping soil particle size fractions in central Iran

The Second Generation Canadian Wetland Inventory Map at 10 Meters Resolution Using Google Earth Engine

Big Data for a Big Country: The First Generation of Canadian Wetland Inventory Map at a Spatial Resolution of 10-m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform

TL;DR

Abstract

Authors

References158 items

Multi-task convolutional neural networks outperformed random forest for mapping soil particle size fractions in central Iran

The Second Generation Canadian Wetland Inventory Map at 10 Meters Resolution Using Google Earth Engine

Big Data for a Big Country: The First Generation of Canadian Wetland Inventory Map at a Spatial Resolution of 10-m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform

Comparing Deep Learning and Shallow Learning for Large-Scale Wetland Classification in Alberta, Canada

mlr3: A modern object-oriented machine learning framework in R

Welcome to the Tidyverse

Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark

Comparing Deep Neural Networks, Ensemble Classifiers, and Support Vector Machine Algorithms for Object-Based Urban Land Use/Land Cover Classification

A Comparative Assessment of Machine-Learning Techniques for Land Use and Land Cover Classification of the Brazilian Tropical Savanna Using ALOS-2/PALSAR-2 Polarimetric Images

Coral Reef Change Detection in Remote Pacific Islands Using Support Vector Machine Classifiers

Using Multi-Temporal Landsat Images and Support Vector Machine to Assess the Changes in Agricultural Irrigated Areas in the Mogtedo Region, Burkina Faso

Comparing Thresholding with Machine Learning Classifiers for Mapping Complex Water

Meta-analysis of deep neural networks in remote sensing: A comparative study of mono-temporal classification to support vector machines

Deep learning in remote sensing applications: A meta-analysis and review

Post-Disaster Recovery Assessment with Machine Learning-Derived Land Cover and Land Use Information

A new fully convolutional neural network for semantic segmentation of polarimetric SAR imagery in complex land cover ecosystem

Deep Learning for Hyperspectral Image Classification: An Overview

Optimization Performance Comparison of Three Different Group Intelligence Algorithms on a SVM for Hyperspectral Imagery Classification

Wetland Classification with Multi-Angle/Temporal SAR Using Random Forests

Support Vector Machine Accuracy Assessment for Extracting Green Urban Areas in Towns

The First Wetland Inventory Map of Newfoundland at a Spatial Resolution of 10 m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform

Effects of pre-processing methods on Landsat OLI-8 land cover classification using OBIA and random forests classifier

New Frontiers in Spectral-Spatial Hyperspectral Image Classification: The Latest Advances Based on Mathematical Morphology, Markov Random Fields, Segmentation, Sparse Representation, and Deep Learning

Spatial-temporal patterns of features selected using random forests: a case study of corn and soybeans mapping in the US

Deep Convolutional Neural Network for Complex Wetland Classification Using Optical Remote Sensing Imagery

Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery

Multi-scale hierarchical sampling change detection using Random Forest for high-resolution satellite imagery

Complete Analysis of a Random Forest Model

Hyperparameters and tuning strategies for random forest

Decision-Tree, Rule-Based, and Random Forest Classification of High-Resolution Multispectral Imagery for Wetland Mapping and Inventory

Mapping Urban Areas in China Using Multisource Data With a Novel Ensemble SVM Method

Development of a support vector machine based cloud detection method for MODIS with the adjustability to various conditions

An effective implementation and assessment of a random forest classifier as a soil spatial predictive model

Improving accuracy of long-term land-use change in coal mining areas using wavelets and Support Vector Machines

Developing a Random Forest Algorithm for MODIS Global Burned Area Classification

Tree-Species Classification in Subtropical Forests Using Airborne Hyperspectral and LiDAR Data

Generation of Radiometric, Phenological Normalized Image Based on Random Forest Regression for Change Detection

Detection of Informal Settlements from VHR Images Using Convolutional Neural Networks

A Systematic Approach for Variable Selection With Random Forests: Achieving Stable Variable Importance Values

A review of supervised object-based land-cover image classification

Random forest wetland classification using ALOS-2 L-band, RADARSAT-2 C-band, and TerraSAR-X imagery

Hyperspectral and LiDAR Fusion Using Extinction Profiles and Total Variation Component Analysis

Advanced Spectral Classifiers for Hyperspectral Images: A review

LiDAR Data Classification Using Extinction Profiles and a Composite Kernel Support Vector Machine

Review of studies on tree species classification from remotely sensed data

Random Forest Classification of Wetland Landcovers from Multi-Sensor Data in the Arid Region of Xinjiang, China

Rapid Land Cover Map Updates Using Change Detection and Robust Random Forest Classifiers

Learning Change from Synthetic Aperture Radar Images: Performance Evaluation of a Support Vector Machine to Detect Earthquake and Tsunami-Induced Changes

SVM or deep learning? A comparative study on remote sensing image classification

Land cover classification using random forest with genetic algorithm-based parameter optimization

Approximate Computing of Remotely Sensed Data: SVM Hyperspectral Image Classification as a Case Study

Remote sensing platforms and sensors: A survey

Random forest in remote sensing: A review of applications and future directions

Hyperspectral image preprocessing with bilateral filter for improving the classification accuracy of support vector machines

Hyperspectral Image Classification via JCR and SVM Models With Decision Fusion

Mapping CORINE Land Cover from Sentinel-1A SAR and SRTM Digital Elevation Model Data using Random Forests

Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting

ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R

On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping

Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features

Exploring issues of training data imbalance and mislabelling on random forest performance for large area land cover classification using the ensemble margin

caret: Classification and Regression Training

Characterizing stand-level forest canopy cover and height using Landsat time series, samples of airborne LiDAR, and the Random Forest algorithm

Urban land cover classification using airborne LiDAR data: A review

Comparison of support vector machine, artificial neural network, and spectral angle mapper algorithms for crop classification using LISS IV data

Integrating multiple texture methods and NDVI to the Random Forest classification algorithm to detect tea and hazelnut plantation areas in northeast Turkey

Random forests: from early developments to recent advancements

Automatic change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine classification

Meta-discoveries from a synthesis of satellite-based land-cover mapping research

A comparative investigation of modern feature selection and classification approaches for the analysis of mass spectrometry data.

Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers

Optimizing Subspace SVM Ensemble for Hyperspectral Imagery Classification

Improving the accuracy of rainfall rates from optical satellite sensors with machine learning — A random forests-based approach applied to MSG SEVIRI

Predictive soil parent material mapping at a regional-scale: a Random Forest approach.

Detecting Sirex noctilio grey-attacked and lightning-struck pine trees using airborne hyperspectral data, random forest and support vector machines classifiers

Remote sensing of tea plantations using an SVM classifier and pattern-based accuracy assessment technique