Artificial Intelligence is revolutionizing the detection of asbestos-containing material (ACM) roofing, making it cost-effective, efficient, and current. In a recent study, researchers used mask region-based convolution neural networks (Mask R-CNN) to analyze multi-spectral satellite imagery (MSSI) and high-resolution aerial imagery (HRAI) to detect the presence of ACM roofing on residential buildings in Australia.
The study found that AI models can provide additional data to monitor, manage and plan for ACM in situ and its safe removal and disposal, compared with traditional approaches alone. Combining advanced AI techniques and remote sensing imagery, specifically Mask R-CNN with HRAI, can provide efficient methods for the large-scale detection of ACM roofing, improving the coverage and currency of data for the implementation of coordinated management policies for ACM in the built environment.
The researchers used three models to detect ACM roofing using different training sample datasets and confidence thresholds. Model 1, using HRAI and 460 training samples, was found to be the most reliable with a precision of 94%. Model 2, using MSSI and 184 training samples, produced 533 inferences at 63% precision and a 90% confidence threshold. Model 3, using HRAI and 184 training samples, produced 1737 inferences at 62% precision and a 97% confidence threshold. The results confirmed that model 1, using HRAI and a larger training sample dataset with Mask R-CNN, produced the highest number of inferences at the highest precision and confidence threshold.
This breakthrough can save countless lives by detecting and removing asbestos roofing from residential buildings. Asbestos is a naturally occurring mineral that was widely used in construction for its insulation and fire-resistant properties. However, it is also a known carcinogen, causing lung cancer and mesothelioma. Asbestos-containing materials (ACMs) were used in building products until the late 1980s and can still be found in older buildings.
Traditionally, detecting ACM roofing involved in situ inspection and detection methods, which can be time-consuming, costly, and dangerous. With the use of AI, detection methods can be scaled up to cover a larger area and allocate resources for targeted investigations in areas with a high likelihood of asbestos. The study shows that without replacing traditional methods, AI detection methods can be useful in widening the scale of investigation coverage.
The cost-effective techniques described in this paper can be applied by governments and stakeholders for the safe management and disposal of ACM in developed, developing and undeveloped regions worldwide. It can provide a foundation for cost-effective larger-scale detection of asbestos roofing. The results of the study are promising and pave the way for future research in the field.
The combination of advanced AI techniques and remote sensing imagery has proven to be an efficient method for the large-scale detection of ACM roofing, improving the coverage and currency of data for the implementation of coordinated management policies for ACM in the built environment. The study confirms the efficacy of AI, specifically Mask R-CNN, to detect ACM roofing using remote sensing imagery, without replacing traditional in situ inspection and detection methods.
This study was a component of a postgraduate research from Griffith University in Southport, Australia and UACS Consulting Pty Ltd. in Buderim, Australia. The research for this paper began with the backing of two projects, which were commissioned and done in collaboration with the Asbestos Safety and Eradication Agency, a branch of the Australian Federal Government.