The use of multi-sensor array systems has become commonplace in indoor air quality or individual exposure applications. Nevertheless, there is a lack of reliable data, as qualification protocols are sparsely applied by end-users to multi-sensor commercial systems prior to field or lab implementation. This is especially the case with regard to VOC monitoring, although they are ubiquitous species of indoor environment. The aim of the present work is to propose an all-encompassing qualification protocol, suitable for a wide range of multi-sensor systems, able to assess the metrological performance regarding indoor VOCs. Furthermore, it provides data on metrological performance for 45 replicas of 5 types of sensors, 4 metal oxides and 1 electrochemical, embedded in a single system, under controlled conditions. Multi-sensor systems were exposed to 6 single VOCs, with their mixture representative of indoor pollution (formaldehyde, acetaldehyde, acetone, ethanol, limonene) in a 1:1 scale experimental room. Metrological performances were retrieved from the correlation curves established by comparison with the responses of a reference analyzer. The results show that the electrochemical sensor, supposedly dedicated to total VOCs, is acetone-blind and underestimates the effective quantity of TVOCs by a factor of 3. Metal oxide sensors, chosen for their reliability in establishing pollution source fingerprints, indicate effectively differentiated sensitivities by type of VOC, but without homogeneity by chemical family. A pre-processing of the data is required to overcome their non-linear responses depending on the concentration range. These results provide crucial insights for the interpretation of field campaign data retrieved from multi-sensor arrays.
25 February 2025 in International Journal of Environmental Science and Technology
Volatile Organic Compounds (VOCs) are important contributors to indoor and occupational air pollution, such as environments involving the extensive use of paints and solvents. The routine measurement of VOCs is often limited by resource constraints, creating a need for indirect estimation techniques. This work presents the need for a predictive framework that offers a practical, interpretable alternative to a full-spectrum chemical analysis and supports early exposure detection in resource-limited settings, contributing to environmental health monitoring and occupational risk assessment. This study explores the capability of machine learning to simultaneously predict the concentrations of five paint-related VOCs using other co-emitted VOCs along with demographic variables. Three models—Multi-Output Gaussian Process Regression (MOGP), CatBoost Multi-Output Regressor, and Multi-Output Neural Networks—were calibrated and each achieved a high predictive performance. Further, a feature importance analysis is conducted and showed that certain VOCs and some demographic variables consistently influenced the predictions across all models, pointing to common exposure determinants for individuals, regardless of their specific exposure setting. Additionally, a subgroup analysis identified the exposure disparities across demographic groups, supporting targeted risk mitigation efforts.
Volatile organic compounds (VOCs) are considered a major public health concern in industrial location areas. The presence of exposure to (VOCs) has raised concern regarding the health effects caused by chronic human exposure as this will increase cancer diseases in the village. An analytical method has been developed and modified to help us detect 38 VOCs in the blood of 38 volunteers who are related to a carpentry shop at the parts-per-trillion level. To measure and evaluate the potential risk, several devices, such as portable passive monitors and air-collected samples, in addition to blood concentration, were used to study three different occupational groups. Ten of the volunteers are employees at the shop, 10 volunteers live very close to the shop, and 10 of them are students in an elementary school very close to the shop. In this study, we developed an automated analytical method using headspace (HS) together with solid-phase microextraction (SPME) connected to capillary gas chromatography (GC) equipped with quadrupole mass spectrometry (MS). The detection limits for the method used were measured in the range from 0.001 to 0.15 ng/L, using linear calibration curves that have three orders of magnitude. The detected concentrations ranged from 3 ng L−1 for trichloroethene to 91 ng L−1 for toluene and 270 ng L−1 for 2,4-diisocyanate, which was derived from the paint solvents used for the wood in the carpentry shop and the paints on the walls. More than half of all assessed species (80%) had mean concentration values less than 50 ng L−1, which is the maximum allowed for most VOCs. The major chemical types among the compounds quantified will be those we found in our previous study in the surrounding air of a carpentry workshop in Deir Ballout in Palestine, which were toluene diisocyanate and butyl cyanate. Some were found to be highly present air. Most of the measurements were below the guidelines of the World Health Organization (WHO). Despite the fact that this study only involved a small number of smokers, smoking was found to be connected with several blood and breath components. This group includes unsaturated hydrocarbons (1,3-butadiene, 1,3-pentadiene, 2-butene), furans (2,5-dimethylfuran), and acetonitrile. The proposed classification of measured species into systemic (blood-borne) and exogenous volatiles is strictly hypothetical, as some species may have several origins.
(1) Background: Urban traffic micro-environments show strong spatial and temporal variability. Short and intensive campaigns remain a practical approach for understanding exposure patterns in complex environments, but they need clear and interpretable summaries that are not limited to simple site or time segmentation. (2) Methods: We carried out a multi-site campaign across five traffic-affected micro-environments, where measurements covered several pollutants, gases, and meteorological variables. A machine learning framework was introduced to learn interpretable operational regimes as recurring multivariate states using clustering with stability checks, and then we evaluated their added explanatory value and cross-site transfer using a strict site hold-out design to avoid information leakage. (3) Results: Five regimes were identified, representing combinations of emission intensity and ventilation strength. Incorporating regime information increased the explanatory power of simple NO2 models and allowed the imputation of missing H2S day using regime-aware random forest with an near 0.97. Regime labels remained identifiable using reduced sensor sets, while cross-site forecasting transferred well for NO2 but was limited for PM, indicating stronger local effects for particles. (4) Conclusions: Operational-regime learning can transform short multivariate campaigns into practical and interpretable summaries of urban air pollution, while supporting data recovery and cautious model transfer.
21 April 2021 in Communications in Statistics - Theory and Methods
The choice of a bandwidth can affect dramatically the accuracy of classification methods relying on it. Recently, a large number of methods to choose the bandwidth have been developed. This article presents a simple method called KBER to estimate the bandwidth using the average Ricci curvature of graphs. The Radial Basis Function kernel (RBF) has been chosen in our work for its simplicity and its popularity in this kind of research; it is also possible to apply our method to any kernel with the same kind of parameter.