Identification of Characteristics of Land Cover in Mangkauk Catchment Area Using Support Vector Machine (SVM) And Artificial Neural Network (ANN)

American journal of applied sciences

Ridwan, Ichsan¹ 

关键词: ANN;    Mangkauk Catchment Area;    Land Cover;    SVM;   

DOI  :  10.3844/ajassp.2017.726.736

学科分类：自然科学（综合）

来源: Science Publications

【 摘 要 】

Land cover is anything that includes any types of appearance on the surface of the earth on a particular land. Information related to land cover can be used as at the parameter to determine the amount of runoff in a catchment area. This study was conducted in the Catchment Area (CA) of Mangkauk using Landsat 8 OLI/TIRS 2014 scene path/row 117/62 with the methods of Support Vector Machine (SVM) and Artificial Neural Network (ANN). The classification of land cover in Mangkauk catchment area included forests, plantations, shrubs, reeds/grasses, rice fields, open lands, settlements and water body. Based on the accuracy test of land cover classification using SVM, the value of the overall accuracy was 97.22% with Kappa Coefficient 0.96, while using ANN 86.33% with Kappa Coefficient 0.79.

【 授权许可】

CC BY