First of its kind AI-model can help policymakers efficiently identify and prioritize houses for retrofitting and other decarbonizing measures
‘Hard-to-decarbonize’ (HtD) houses are responsible for over a quarter of all direct housing emissions – a major obstacle to achieving net zero – but are rarely identified or targeted for improvement.
Now a new ‘deep learning’ model trained by researchers from Cambridge University’s Department of Architecture promises to make it far easier, faster and cheaper to identify these high priority problem properties and develop strategies to improve their green credentials.
Houses can be ‘hard to decarbonize’ for various reasons including their age, structure, location, social-economic barriers and availability of data. Policymakers have tended to focus mostly on generic buildings or specific hard-to-decarbonise technologies but the study, published in the journal Sustainable Cities and Society, could help to change this.1
The model also helps authorities to understand the geographical distribution of HtD houses, enabling them to efficiently target and deploy interventions efficiently.
- 1. Maoran Sun, an urban researcher and data scientist, and his PhD supervisor Dr Ronita Bardhan (Selwyn College), who leads Cambridge’s Sustainable Design Group, show that their AI model can classify HtD houses with 90% precision and expect this to rise as they add more data, work which is already underway. Dr Bardhan said: “This is the first time that AI has been trained to identify hard-to-decarbonize buildings using open source data to achieve this. “Policymakers need to know how many houses they have to decarbonize, but they often lack the resources to perform detail audits on every house. Our model can direct them to high priority houses, saving them precious time and resources.”
Sun, Maoran, and Ronita Bardhan. “Identifying Hard-to-Decarbonize Houses from Multi-Source Data in Cambridge, UK.” Sustainable Cities and Society 100 (2024): 105015. https://doi.org/10.1016/j.scs.2023.105015.
As the urban population continues to expand and is expected to comprise 80% of the total population in 2050, it is crucial to ensure the sustainability and energy efficiency of cities. Among all the homes globally, Hard-to-Decarbonize (HtD) buildings are estimated to be a quarter of them. Identifying the HtD houses and proposing strategies for these houses is important to reach the global net zero target. However, the study of HtD houses has historically been neglected. Previous studies mainly focus on simulating, predicting and understanding attributes that are directly related to energy usage and efficiency. In this research, a methodology for identifying HtD buildings with publicly available data is proposed and tested in Cambridge, UK. A dataset of HtD houses in Cambridge is organized, with criteria derived from the Energy Performance Certificate (EPC), which results from detailed inspections of houses. Street view images (SVI), aeriel view images (AVI), land surface temperature (LST), and building stock data are used together for the prediction with deep learning. The classification precision for HtD buildings is able to achieve 82%. This study also explores the minimal data needed for the high-accuracy prediction of HtD houses. Results show that SVI contributes the most to the prediction.
