A Spatial Structural and Statistical Approach to Building Classification of Residential Function for City-Scale Impact Assessment Studies

摘要: In order to implement robust climate change adaption and mitigation strategies in cities fine spatial scale information on building stock is required. However, for many such rarely available. response, we present a methodology that allows topographic footprints be classified the level of residential topological-building types corresponding period construction. The approach developed employs structure topology first recognise topological Detached , Semi-Detached or Terrace . Thereafter, morphological metrics are employed with multinomial logistic regression assign buildings particular periods construction use within city-scale impact assessment studies. Overall system performs well classification exemplars city Manchester UK, an overall accuracy 83.4%, although less satisfactory results (76.6%) but excellent accuracies (93.0%).