Spatial factors influencing building age prediction and implications for urban residential energy modelling

摘要: Abstract Urban energy consumption is expected to continuously increase alongside rapid urbanization. The building sector represents a key area for curbing the trend and reducing energy-related emissions by adopting efficiency strategies. Building age acts as proxy insulation properties an important parameter models that facilitate decision making. present study explores potential of predicting residential at large geographical scale from open spatial data sources in eight municipalities German federal state North-Rhine Westphalia. proposed framework combines attributes with street block metrics classification features Random Forest model. Results show addition urban fabric improves accuracy prediction specific training scenarios. Furthermore, findings highlight way which disposition test samples influences accuracy. Additionally, paper investigates impact misclassification on heat demand estimation. model leads reasonable errors estimates, various scenarios training, suggests method promising modelling toolkit.