Impervious Surface Mapping Using Robust Depth Minimum Vector Variance Regression

Abstract

This paper proposes a reliable minimum vector variance regression algorithm for robust supervised impervious mapping. The mapping is done with a conventional two phase process; training and mapping process. The outcome of training process is the robust regression models useful for the knowledge base of mapping land cover. The robust regression model is built from the existing
robust depth minimum vector variance subsample. The case of research is a metropolitan area consisting of megacities surrounding Jakarta, Jabodetabek. The urban population in the Jabodetabek area is very high. The urbanization is closely related to the percentage of impervious area and indicates the quality of the environment. The evaluation mapping provides that the robust depth
minimum vector variance regression is an effective method for the impervious land cover mapping of Jabodetabek.

Keywords: depth function, impervious, minimum vector variance, robust