Ranking the Environmental Factors of Indoor Air Quality of Metropolitan Independent Coffee Shops by Random Forest Model

Independent coffee shops are the alternative workplaces for people working remotely from traditional offices but are not concerned about their indoor air quality (IAQ). This study aimed to rank the environmental factors in affecting the IAQ by Random Forest models. The indoor environments and human activities of participated independent coffee shops were observed and recorded for 3 consecutive days including weekdays and weekend during the business hours. The multi-sized particulate matter (PM), particle-bound polycyclic aromatic hydrocarbons (p-PAHs), total volatile organic compounds (TVOCs), CO, CO 2 , temperature and relative humidity were monitored. Random Forest models ranked the environmental factors. More than 20% of the 15-minute average concentrations of PM 10 , PM 2.5 , and CO 2 exceeded the World Health Organization guidelines. Occupant density affected TVOCs, p-PAHs and CO 2 concentrations directly. Tobacco smoking dominated PM 10 , PM 2.5 , TVOCs and p-PAHs concentrations mostly. CO concentration was affected by roasting bean first and tobacco smoking secondly. The non-linear relationships between temperature and these pollutants illustrated the relative low concentrations happened at temperature between 22°C and 24°C. Tobacco smoking, roasting beans and occupant density are the observable activities to alert the IAQ change. Monitoring CO 2 and optimizing the room temperature could also be the surrogate parameters to assure the IAQ.