This AI can tell if your home is wasting energy — just by looking at it

Key Takeaways:

– Researchers from the University of Cambridge have developed a deep-learning algorithm to identify energy-wasting homes.
– The AI was trained on open-source data and achieved a 90% accuracy rate in classifying ‘hard to decarbonise’ houses.
– The model can identify specific areas of a building that are losing the most heat and determine whether a home is old or modern.
– The researchers plan to increase the detail and accuracy of the model over time.
– The UK aims to decarbonise all homes by 2050, but identifying high-priority “problem properties” is crucial to achieving this goal.
– The AI model can save policymakers time and resources by directing them to high-priority houses.
– The researchers are working on an advanced framework that will incorporate additional data layers like energy use, poverty levels, and thermal images.
– Decarbonisation policy decisions have historically been based on limited datasets, but AI has the potential to change this.
– AI is being utilized by various companies outside of academia to address climate change, such as Dryad Networks and 7Analytics.

The Next Web:

Two researchers from the University of Cambridge have developed a deep-learning algorithm that could make it easier, faster, and cheaper to identify energy-wasting homes — a significant source of greenhouse gas emissions. 

Trained on open-source data including energy performance certificates and satellite images, the AI was able to classify so-called ‘hard to decarbonise’ houses with 90% accuracy, according to the study. These homes are hard to electrify or retrofit for a variety of reasons including old age, structure, or location. 

The model can pinpoint specific parts of a building — such as the roof and windows — which are losing the most heat, and whether a home is old or modern. However, the researchers are confident they can significantly increase the detail and accuracy of the model over time.