Predicting Building Types and Functions at Transnational Scale

Abstract:

Building-specific knowledge like building type and function information is important for numerous energy applications. However, comprehensive datasets containing this information for individual households are missing in many regions in Europe. For the first time, we investigate whether it is feasible to predict building types and functional classes for a diverse set of regions based on only open GIS-datasets available across countries. We train a Graph Neural Network (GNN) classifier on OpenStreetMap (OSM) buildings across the EU, Norway, Switzerland, and the UK. A Graph Transformer model achieves a high Cohen’s Kappa coefficient of 0.755 when classifying buildings into 9 classes, and a very high Cohen’s Kappa coefficient of 0.845 when classifying buildings into the residential and non-residential classes. The experimental results imply three core novel contributions to literature. Firstly, we show that building classification across multiple countries is possible by using OSM as a ground truth data source. Secondly, we demonstrate that a multi-source input consisting of information about 2D building shape, land use, degree of urbanization, and countries is suitable for building type/function classification. Thirdly, our results indicate that GNN models that consider contextual information of building neighborhoods improve predictive performance compared to models that only consider individual buildings and ignore the neighborhood.