Automatic determination of different soil types via several machine learning algorithms employing radarsat-2 SAR image polarization coefficients
[ X ]
Tarih
2022
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Synthetic aperture radar (SAR), which is one of the most popular remote sensing technologies, has been extensively employed for classification of various soil types, soil texture description, and its mapping. Determining the soil type is useful for rural and urban management. In the current study, several machine learning algorithms, which consist of the K-Nearest Neighbor (K-NN), Extreme Learning Machine (ELM), and Naive Bayes (NB), have been recommended by utilizing Radarsat-2 SAR data. A pilot region in the city of Diyarbakir, Turkey that spreads among 370 46’- 380 04’ N latitudes and 400 04’- 400 26’E longitudes was employed, and nearly, 156 soil samples were collected for classification of two soil types (Clayey and Clayey+Loamy). After that, four different Radarsat-2 SAR image polarization coefficients were computed for each soil sample, and these coefficients were utilized as inputs in the classification stage. Finally, the results showed that an overall accuracy of 91.1% with K-NN, 82.0% with ELM, and 85.2% with NB algorithm was computed for the classification of two soil types.
Açıklama
Anahtar Kelimeler
Kaynak
Springer Optimization and Its Applications
WoS Q Değeri
Scopus Q Değeri
Q4
Cilt
199
Sayı
Künye
Acar, E. ve Özerdem, M. S. (2022). Automatic determination of different soil types via several machine learning algorithms employing radarsat-2 SAR image polarization coefficients. Springer Optimization and Its Applications, 199, 219-233.
