Revisiting the joint effect of temperature and relative humidity on airborne mold and bacteria concentration in indoor environment: A machine learning approach

초록

Exposure to airborne bioaerosols, such as bacteria and fungi, presents significant health risks, especially for vulnerable populations like children, the elderly, and those with compromised immune systems. Bioaerosol exposure can aggravate respiratory and allergic conditions, underscoring the need for real-time monitoring in indoor environments. However, continuous monitoring is often hindered by technical and economic challenges. Temperature and relative humidity are known to strongly influence airborne bacteria and mold levels, yet the combined impact of these factors remains insufficiently explored for effective control strategies in diverse indoor settings. This study investigates the joint effects of temperature and humidity on indoor bioaerosol concentrations through a machine learning-based outlier removal. Data were collected from 4,048 samples across 10 different types of multi-use facilities (e.g., daycare center, library) in South Korea, taking seasonal variations into account. A Random Forest model was employed to manage complex nonlinear relationships, identifying and excluding data points heavily influenced by external variables, such as ventilation and occupancy, rather than by temperature and humidity alone. The refined dataset enabled a focused analysis of temperature and humidity's combined impact, revealing specific conditions that correspond with elevated bioaerosol levels. The findings show that temperature and humidity jointly and significantly affect concentrations of bacteria and mold, with variations observed according to season and facility type. This research provides practical guidelines for controlling indoor bioaerosol levels by adjusting temperature and humidity alone, thus supporting safer and healthier indoor environments across a range of facilities.

키워드