Asbestos fibers are well-known carcinogens, and their rapid detection is critical for ensuring safety, protecting public health, and promoting environmental sustainability. In this work, short-wave infrared (SWIR) spectroscopy, combined with machine learning (ML), was evaluated as an environmentally friendly analytical approach for simultaneously distinguishing the asbestos type, asbestos-containing materials in various forms, asbestos-contaminated/-uncontaminated soil, and asbestos-contaminated/-uncontaminated cement, simultaneously. This approach offers a noninvasive and efficient alternative to traditional laboratory methods, aligning with sustainable practices by reducing hazardous waste generation and enabling in situ testing. Different chemometrics techniques were applied to discriminate the material classes. In more detail, partial least squares discriminant analysis (PLS-DA), principal component analysis-based discriminant analysis (PCA-DA), principal component analysis-based K-nearest neighbors classification (PCA-KNN), classification and regression trees (CART), and error-correcting output-coding support vector machine (ECOC SVM) classifiers were tested. The tested classifiers showed different performances in discriminating between the analyzed samples. CART and ECOC SVM performed best (${Recall}_M$ and ${Accuracy}_M$ equal to 1.00), followed by PCA-KNN (${Recall}_M$ of 0.98–1.00 and ${Accuracy}_M$ equal to 1.00). Poorer performances were obtained by PLS-DA (${Recall}_M$ of 0.68–0.72 and ${Accuracy}_M$ equal to 0.95) and PCA-DA (${Recall}_M$ of 0.66–0.70 and ${Accuracy}_M$ equal to 0.95). This research aligns with the United Nations’ Sustainable Development Goals (SDGs), particularly SDG 3 (Good Health and Well-Being), by enhancing human health protection through advanced asbestos detection methods, and SDG 12 (Responsible Consumption and Production), by promoting sustainable, low-waste testing methodologies.

This study focuses on the analysis of serpentinite rocks to detect asbestos minerals, with a particular emphasis at discriminating chrysotile from other minerals and matrices (antigorite, lizardite) in serpentinites. The primary objective of this exploratory study is to lay the groundwork for the development of an innovative system for real-time identification of asbestos on the surface of materials and rocks. In more detail, the study emphasizes the advantages of utilization of rapid and reliable portable instrumentation, aided by machine learning (ML) techniques. Serpentinite rock debris from tunnel excavation activities (i.e. tunnel spoil) were collected at the Cravasco railway tunnelling site (Genoa - Italy) of the TEN-T Rhine-Alps Core Corridor. On-site analysis was conducted using the ASD FieldSpec 4 Standard-Res spectrophotoradiometer (350-2500 nm). A two-class classifier was developed based on acquired reflectance spectra, to discriminate between the "Presence of asbestiform fibers" and the "Absence of asbestiform fibers". The classification model was calibrated through stereomicroscopic inspection and electron microscopy carried on selected sample fractions.

Asbestos is a well-known carcinogenic substance, and it still represents a common problem in many countries. It was widely used during the twentieth century, thanks to its numerous physical and mechanical characteristics. Many governments banned the manufacturing, importation, processing, and distribution of asbestos-containing products and recommended action plans for the mapping and safe removal of such materials. The remote-sensing approach allows to perform analysis on large portions of territories in a relatively short time, providing an innovative tool for managing urban and natural environments. In this chapter, an overview regarding the application of this technology for asbestos cement roofs mapping is presented. Moreover, the different types of sensors, platforms, and data processing architectures are reported and discussed, to give the readers information that we hope will be useful in designing, setting up, and implementing efficient mapping of asbestos cement roofs based on remote sensing strategies.

This technical note describes a protocol for the safe excavation of asbestos-bearing serpentinite and the management of the associated spoil during tunnel construction. Asbestos fibers occur naturally in serpentinites belonging to greenstone formations and may pose serious health risks if released and inhaled. Detailed, site-specific risk assessment is therefore required for tunnelling and earthworks involving these lithologies. Where excavation through greenstones cannot be avoided, as in the construction of major national and international infrastructure networks, dedicated safety and waste-management procedures are necessary to minimize occupational and environmental risks. The protocol was implemented considering Italy’s extensive experience with tunnel construction sites and integrates operational controls, environmental monitoring, personal protective equipment, and procedures for the characterization and management of rocks potentially containing asbestos. Drawing on practical site experience, it provides a structured framework for risk assessment, worker protection, exposure prevention, and appropriate spoil classification and handling. The proposed approach is also consistent with circular-economy principles, as more detailed material characterization can enable greater recovery of excavated material for reuse. The present technical note may therefore serve as a practical reference for comparable tunnelling projects involving naturally occurring asbestos.