hrcak mascot   Srce   HID

Izvorni znanstveni članak

Evaluating Different Machine Learning Methods on RapidEye and PlanetScope Satellite Imagery

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

Puni tekst: engleski, pdf (6 MB) str. 1-18 preuzimanja: 79* citiraj
APA 6th Edition
Kranjčić, N. i Medak, D. (2020). Evaluating Different Machine Learning Methods on RapidEye and PlanetScope Satellite Imagery. Geodetski list, 74 (97) (1), 1-18. Preuzeto s https://hrcak.srce.hr/237682
MLA 8th Edition
Kranjčić, Nikola i Damir Medak. "Evaluating Different Machine Learning Methods on RapidEye and PlanetScope Satellite Imagery." Geodetski list, vol. 74 (97), br. 1, 2020, str. 1-18. https://hrcak.srce.hr/237682. Citirano 12.07.2020.
Chicago 17th Edition
Kranjčić, Nikola i Damir Medak. "Evaluating Different Machine Learning Methods on RapidEye and PlanetScope Satellite Imagery." Geodetski list 74 (97), br. 1 (2020): 1-18. https://hrcak.srce.hr/237682
Harvard
Kranjčić, N., i Medak, D. (2020). 'Evaluating Different Machine Learning Methods on RapidEye and PlanetScope Satellite Imagery', Geodetski list, 74 (97)(1), str. 1-18. Preuzeto s: https://hrcak.srce.hr/237682 (Datum pristupa: 12.07.2020.)
Vancouver
Kranjčić N, Medak D. Evaluating Different Machine Learning Methods on RapidEye and PlanetScope Satellite Imagery. Geodetski list [Internet]. 2020 [pristupljeno 12.07.2020.];74 (97)(1):1-18. Dostupno na: https://hrcak.srce.hr/237682
IEEE
N. Kranjčić i D. Medak, "Evaluating Different Machine Learning Methods on RapidEye and PlanetScope Satellite Imagery", Geodetski list, vol.74 (97), br. 1, str. 1-18, 2020. [Online]. Dostupno na: https://hrcak.srce.hr/237682. [Citirano: 12.07.2020.]

Sažetak
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.

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

Hrčak ID: 237682

URI
https://hrcak.srce.hr/237682

[hrvatski]

Posjeta: 151 *