A Machine Learning-Based Prediction Model of LCCO2 for Building Envelope Renovation in Taiwan

In 2015, Taiwan’s government announced the “Greenhouse Gas Reduction and Management Act”, the goal of which was a 50% reduction in carbon emissions by 2050, compared with 2005. The residential and commercial sectors produce approximately one third of all carbon emissions in Taiwan, and the number of construction renovation projects is much larger than that of new construction projects. In this paper, we considered the life-cycle CO2 (LCCO2) of a building envelope renovation project in Tainan and focused on local construction methods for typical row houses. The LCCO2 of 744 cases with various climate zones, orientations, and insulation and glazing types was calculated via EnergyPlus, SimaPro, and a local database (LCBA database), and the results were then used to develop a machine learning model. Our findings showed that the machine learning model was capable of predicting annual energy consumption and LCCO2. With regard to annual energy consumption, the RMSE was 227.09 kW·h (per year) and the R2 was 0.992. For LCCO2, the RMSE was 2792.47 kgCO2eq and the R2 was 0.989, which indicates a high-confidence process for decision making in the early stages of building design and renovation.