The joint effect of temperature and humidity on airborne bacteria and fungi concentration in indoor environment: a machine learning approach for cost-effective intervention

This study presents a machine learning model that predicts indoor bioaerosol levels. We collected data from 4,048 indoor facilities in Korea between 2021 and 2023, then statistical analyses were conducted to identify the factors that influence bioaerosol levels. Based on these factors, a machine learning-based model was developed to predict cautionary concentration range (fungi: <400 CFU/m³, bacteria: <640 CFU/m³) based on temperature and humidity. This research contributes to our understanding of the relationship between temperature, humidity, and bioaerosol levels, which can aid in developing effective strategies for managing indoor air quality.