In the rapidly evolving world of construction and sustainability, a groundbreaking scoping review published in the journal *Buildings* (translated to English as “Buildings”) is shedding light on the untapped potential of artificial intelligence (AI) in assisting surveyors with pre-retrofit and pre-demolition auditing (PRA/PDA). This review, led by Yuan Yin from the Dyson School of Design Engineering at Imperial College London, explores how AI could revolutionize the way we approach building retrofits and demolitions, offering significant commercial impacts for the energy sector.
Traditionally, PRA/PDA processes have been labor-intensive and prone to human error, requiring substantial time and manual effort. However, as the construction industry increasingly emphasizes sustainable practices, the demand for these audits has grown. “The traditional methods are not only time-consuming but also error-prone,” Yin explains. “AI has the potential to streamline these processes, making them more efficient and accurate.”
The review indicates that while AI has the potential to be applied across multiple sub-stages of PRA/PDA, its actual application is still limited. Notably, AI integration has been most prevalent in floor plan recognition and material detection, where deep learning and computer vision models have achieved remarkable accuracies. “We found that AI models, particularly deep learning and computer vision, have shown over 90% accuracy in floor plan recognition and material detection,” Yin notes. “This is a significant step forward, but there’s still a lot of room for growth in other areas.”
Other sub-stages, such as operation and maintenance document analysis, object detection, volume estimation, and automated report generation, remain underexplored. These gaps highlight the uneven distribution of AI adoption, with performance varying greatly depending on data quality, available domain-specific datasets, and the complexity of integration into existing workflows.
The commercial implications for the energy sector are substantial. Efficient PRA/PDA processes can lead to better material reuse, waste reduction, and regulatory compliance, all of which are critical for sustainable construction. “By leveraging AI, we can make the entire process more efficient and cost-effective,” Yin says. “This not only benefits the construction industry but also has a positive impact on the environment and the energy sector.”
The review concludes that while AI demonstrates strong potential in PRA/PDA, particularly for floor plan and material analysis, broader adoption is still in its infancy. Future research should target multimodal AI development, real-time deployment, and standardized benchmarking to improve automation and accuracy across all PRA/PDA stages.
As the construction industry continues to evolve, the integration of AI in PRA/PDA processes could be a game-changer. “The potential is enormous,” Yin concludes. “With further research and development, AI could transform the way we approach building retrofits and demolitions, making the process more sustainable and efficient.”
This research not only highlights the current state of AI in PRA/PDA but also paves the way for future developments. As the industry moves towards more sustainable practices, the role of AI in assisting surveyors will become increasingly important. The findings of this review could shape the future of construction, offering new opportunities for innovation and efficiency in the energy sector.