 This study presents a hybrid object-based approach for Arctic coastal tundra mapping using very high resolution optical satellite imagery that combines results from semi-automatic water, land separation, texture analysis based on local binary pattern, LBP, and image classification via random forests, RF. The method achieved an overall accuracy of 88% for nine classes and successfully identified unique land cover types such as icewedge polygons and wetland with both producers and users accuracy over 91%. This article was authored by Jaohua Cheng, John Paha, Jason Duff, and others.