Original scientific paper

Evaluating Different Machine Learning Methods on RapidEye and PlanetScope Satellite Imagery

Nikola Kranjčić orcid.org/0000-0001-7219-9440 ; Faculty of Geotechnical Engineering, University of Zagreb, Varaždin, Croatia
Damir Medak orcid.org/0000-0003-3660-0051 ; Faculty of Geodesy, University of Zagreb, Zagreb, Croatia

Abstract

Since the first satellite imagery of RapidEye and PlanetScope became available, numerous studies have been conducted. However, only a few authors have focused on evaluating the accuracy of more than two machine learning methods in land cover classification. This paper evaluates the accuracy of four different machine learning methods, namely: support vector machine, artificial neural network, naive Bayes, and random forest. All analysis was conducted on cities in Croatia, Varaždin and Osijek. On Varaždin area on RapidEye satellite imagery support vector machine achieved overall kappa value 0.80, artificial neural network 0.37, naive Bayes 0.84 and random forest 0.76. On Varaždin area on PlanetScope satellite imagery support vector machine achieved overall kappa value 0.77, artificial neural network 0.38, naive Bayes 0.76 and random forest 0.75. On Osijek area on RapidEye satellite imagery support vector machine achieved overall kappa value 0.75, artificial neural network 0.36, naive Bayes 0.85 and random forest 0.76. On Osijek area on PlanetScope satellite imagery support vector machine achieved overall kappa value 0.64, artificial neural network 0.23, naive Bayes 0.72 and random forest 0.63. Performance time of each method is also evaluated. Naive Bayes and random forest have best performance time in every scenario.

Keywords

support vector machines; artificial neural network; naive Bayes; random forest; RapidEye; PlanetScope

Hrčak ID:

237682

URI

https://hrcak.srce.hr/237682

Publication date:

30.3.2020.

Article data in other languages: croatian

Visits: 2.336 *