Using OpenStreetMap (OSM) to enhance the classification of local climate zones in the framework of WUDAPT

Abstract

The World Urban Database and Access Portal Tools (WUDAPT) project has adopted the Local Climate Zone (LCZ) scheme as a basic and consistent description of form and function of cities at neighbourhood scale. LCZs are classified using crowdsourced training samples, open data and open source software but the quality of the maps still needs improvement. The aim of this paper is to investigate the use of data from OpenStreetMap (OSM) to enhance the development of LCZs, complement the existing data sources, and improve the accuracy of the maps. Various features were derived from the OSM database and combined with seasonal LCZ maps. Therefore a methodology was developed and tested for Hamburg, Germany, using a fuzzy approach and then a weighted combination method was applied to combine the inputs from OSM with each of the seasonal LCZ maps. The results showed that improvements can be achieved for certain classes, either in terms of accuracy, e.g. rectifying the misclassification of agricultural areas as heavy industry, or representation on the map, e.g. a more detailed water network. The approach developed is flexible and allows for knowledge about which data sources are more reliable as inputs to the combination and weighting process.