Machine Learning in Hazardous Building Material Management: Research Status and Applications

Assessment of the presence hazardous materials in buildings is essential for improving material recyclability, increasing working safety, and lowering risk unforeseen cost delay demolition. In light these aspects, machine learning has been viewed as a promising approach to complement environmental investigations quantify finding buildings. view number related studies, this article aims review research status management identify potential applications learning. Our exploratory study consists two-fold approach: science mapping critical literature review. By evaluating references acquired from search complementary materials, we have able pinpoint discuss gaps opportunities. While pilot conducted identification source separation collection, extensive adoption available methods was not found field. findings show that (1) quantification asbestos-cement roofing possible combination remote sensing algorithms, (2) characterization with asbestos-containing progressive by using statistical methods, (3) collection wastes can be addressed hybrid image processing algorithms. Analysis demonstrates method applicability provides an orientation future implementation European Union Construction Demolition Waste Management Protocol. Furthermore, establishing comprehensive inventory database key facilitating transition toward hazard-free circular construction.