Indoor air quality (IAQ), as determined by the concentrations of indoor air pollutants, can be predicted using either physically based mechanistic models or statistical models that are driven by measured data. In comparison with mechanistic models mostly used in unoccupied or scenario-based environments, statistical models have great potential to explore IAQ captured in large measurement campaigns or in real occupied environments. The present study carried out the first literature review of the use of statistical models to predict IAQ. The most commonly used statistical modeling methods were reviewed and their strengths and weaknesses discussed.Thirty-seven publications, in which statistical models were applied to predict IAQ, were identified. These studies were all published in the past decade, indicating the emergence of the awareness and application of machine learning and statistical modeling in the field of IAQ. The concentrations of indoor particulate matter (PM 2.5 and PM 10 ) were the most frequently studied parameters, followed by carbon dioxide and radon. The most popular statistical models applied to IAQ were artificial neural networks, multiple linear regression, partial least squares, and decision trees. K E Y W O R D Sartificial neural networks, data mining, IAQ, partial least squares, particulate matter, regression | 705 WEI Et al.

The indoor environmental quality in classrooms can largely affect children's daily exposure to indoor chemicals in schools. To date, there has not been a comprehensive study of the concentrations of semivolatile organic compounds (SVOCs) in French schools. Therefore, the French Observatory for Indoor Air Quality (OQAI) performed a field study of SVOCs in 308 nurseries and elementary schools between June 2013 and June 2017. The concentrations of 52 SVOCs, including phthalates, polybrominated diphenyl ethers (PBDEs), polychlorinated biphenyls (PCBs), polycyclic aromatic hydrocarbons (PAHs), synthetic musks, and pesticides, were measured in air and settled dust (40 SVOCs in both air and dust, 12 in either air or dust). The results showed that phthalates had the highest concentrations among the SVOCs in both the air and dust. Other SVOCs, including tributyl phosphate, fluorene, phenanthrene, gamma‐hexachlorocyclohexane (gamma‐HCH, lindane), galaxolide, and tonalide, also showed high concentrations in both the air and dust. Theoretical equations were developed to estimate the SVOC partitioning between the air and settled dust from either the octanol/air partition coefficient or the boiling point of the SVOCs. The regression constants of the equations were determined using the data set of the present study for phthalates and PAHs.

No abstract