Using remote sensing data and cluster algorithms to structure cities

The increasing urban population and the resulting lack of reliable water, energy and food supply is a big challenge for cities especially in informal settlements (slums). In order to plan new, better supply structures for cities, it is useful to subdivide the cities into sub structures. This subdivision can be performed by using cluster algorithms. In this paper we subdivide the slums in Dhaka using three different cluster methods and evaluate them with different indicators regarding their suitability for infrastructure planning.