PreprintArticleVersion 1Preserved in Portico This version is not peer-reviewed
Using Different Algorithms and Multi-Seasonal, Textural and Ancillary Information to Increase Classification Accuracy during the Period 2000–2015 in a Mediterranean Semiarid Area
Gomariz-Castillo, F.; Alonso-Sarría, F.; Cánovas-García, F. Improving Classification Accuracy of Multi-Temporal Landsat Images by Assessing the Use of Different Algorithms, Textural and Ancillary Information for a Mediterranean Semiarid Area from 2000 to 2015. Remote Sens.2017, 9, 1058.
Gomariz-Castillo, F.; Alonso-Sarría, F.; Cánovas-García, F. Improving Classification Accuracy of Multi-Temporal Landsat Images by Assessing the Use of Different Algorithms, Textural and Ancillary Information for a Mediterranean Semiarid Area from 2000 to 2015. Remote Sens. 2017, 9, 1058.
Gomariz-Castillo, F.; Alonso-Sarría, F.; Cánovas-García, F. Improving Classification Accuracy of Multi-Temporal Landsat Images by Assessing the Use of Different Algorithms, Textural and Ancillary Information for a Mediterranean Semiarid Area from 2000 to 2015. Remote Sens.2017, 9, 1058.
Gomariz-Castillo, F.; Alonso-Sarría, F.; Cánovas-García, F. Improving Classification Accuracy of Multi-Temporal Landsat Images by Assessing the Use of Different Algorithms, Textural and Ancillary Information for a Mediterranean Semiarid Area from 2000 to 2015. Remote Sens. 2017, 9, 1058.
Abstract
The aim of this study is to evaluate three different strategies to improve classification accuracy in a highly fragmented semiarid area. i) Using different classification algorithms: Maximum Likelihood, Random Forest, Support Vector Machines and Sequential Maximum a Posteriori, with parameter optimisation in the second and third cases; ii) using different feature sets: spectral features, spectral and textural features, and spectral, textural and terrain features; and iii) using different image-sets: winter, spring, summer, autumn, winter+summer, winter+ spring+summer; and a four seasons combination. A 3-way ANOVA is used to discern which of these approaches and their interactions significantly increases accuracy. Tukey-Kramer contrast using a heteroscedasticity-consistent estimation of the kappa covariances matrix was used to check for significant differences in accuracy. The experiment was carried out with Landsat TM, ETM, and OLI images corresponding to the period 2000-2015. A combination of four images was the best way to improve accuracy. Maximum Likelihood, Random Forest and Support Vector Machines do not significantly increase accuracy when textural information is added, but do so when terrain features are taken into account. On the other hand, Sequential Maximum a Posteriori increases accuracy when textural features are used, but reduces accuracy substantially when terrain features are included. Random Forest using the three feature subsets and Sequential Maximum a Posteriori with spectral and textural features had the largest kappa values, around 0.9.
Keywords
machine learning; sequential maximum a posteriori; random forest; support vector machines; land use classification; textural information; contextual information
Subject
Environmental and Earth Sciences, Remote Sensing
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.