Deciphering exterior: building energy efficiency prediction with emerging urban big data

Abstract In the UK, 28 million households consume 25% of the total energy and contribute to 25% of the carbon emissions. It is vital to focus on sustainability and energy efficiency within the building sector for decarbonizing purposes. However, traditional methods such as simulations or on-site inspections are time-consuming and labor-intensive. In this research, we propose a novel methodology framework for estimating building energy efficiency using only external and widely existing data. We have designed and trained an end-to-end multi-channel deep learning model utilizing high-resolution thermal infrared and optical remotely sensed images, street view images, socio-economic indicators, and building morphological data. Validated in Glasgow and Edinburgh, the model achieved F1 scores of 0.64 and 0.69. Further analyses surprisingly suggest that more deprived neighborhoods tend to have better building energy efficiency. The study highlights how widely available data and AI can provide scalable, global solutions for advancing the net-zero agenda.