Using artificial intelligence models and degree-days method to estimate the heat consumption evolution of a building stock until 2050: A case study in a temperate climate of the Northern part of Europe

The energy use in buildings is highly influenced by outdoor temperature changes. In the contest of nowadays climate change, its impact on sector important and needs to be assessed. This study investigates how heat consumption (HC) existing regional building stock, located a temperate Northern part Europe (Belgium), will future First, Seasonal Auto-Regressive Integrated Moving Average (SARIMA), Long Short-Term Memory (LSTM) Gated Recurrent Unit (GRU) models are used predict until 2050 from historical data. Second, UK Met Office equations applied for computing heating degree-days (HDD) considering base 15°C. Finally, HC this stock projected using (DD) method. decrease HDD about −11.76% 2012 2050. reduction, calculated at scale, reaching −8.82 %, −10.00%, −11.26% respectively residential, tertiary, industrial buildings. mapped municipality, urban region, province scales. produced maps help decision-makers set up efficient management strategies. methods can replicated other regions with same kind