.png){kind=icon}
.png){kind=icon}
Return
Identifying residential building energy retrofit priorities across climate zones and end uses using machine learning and explainable AI
.png){kind=icon}
OA
AI
L
A
A
C
A
L
DOI：10.1016/j.enbuild.2026.118037.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Developed a data-driven framework to identify residential retrofit priorities by climate zone and energy end use. • An XAI method is applied to identify and interpret key features affecting cooling and heating EUI. • Warmer and transitional zones (CZ 4–6) should prioritize solar control, mechanical efficiency, and ventilation. • Colder zones (CZ 7 A–8) should prioritize reducing ground and window heat losses and improving airtightness. • Under future climate scenarios, system efficiency and operational controls become increasingly influential across climate zones.
Keywords:
Building energy use
Explainable AI
Climate zones
Energy retrofit
Machine learning
Journal
IF:
7.1
Papers:
1.5W
Citations:
6.8W
Organization
Cited Papers