New Machine Learning Model Predicts Indoor Ozone Exposure Using Ventilation Behavior

Researchers from Fudan University and the Chinese Academy of Sciences have developed the first large-scale machine learning model capable of predicting hourly indoor ozone concentrations using accessible environmental and behavioral data. The study, published in Eco-Environment & Health on July 9, 2025, addresses a critical gap in air pollution exposure assessment, as people typically spend 70% to 90% of their time indoors where ozone levels differ significantly from outdoor measurements.

Ozone is a key air pollutant formed by chemical reactions between nitrogen oxides and volatile organic compounds under sunlight. In 2021, long-term ozone exposure contributed to nearly 490,000 deaths worldwide. Traditional exposure assessments have relied heavily on outdoor data, but indoor environments are affected by ventilation, indoor sources, and building materials, creating complex exposure scenarios that linear regression models struggle to capture.

The research team collected over 8,200 hours of indoor ozone data using portable electrochemical sensors in 23 households across 18 Chinese cities. They trained random forest algorithms using predictor variables including outdoor ozone levels from high-resolution datasets, meteorological parameters such as temperature and humidity, and crucially, window-opening status recorded manually by volunteers. The full study is available at https://doi.org/10.1016/j.eehl.2025.100170.

By comparing two models—one excluding and one including window-status information—the researchers demonstrated that incorporating ventilation behavior significantly improved prediction accuracy. The model with window data achieved a cross-validation R² of 0.83 compared to 0.80 without window information, while reducing root mean square error from 7.89 to 7.21 parts per billion. The model accurately captured hourly ozone fluctuations and regional differences, performing better in southern than northern China and during cold rather than warm seasons.

Predictor-importance analysis revealed surface pressure, temperature, and ambient ozone as dominant factors, with ventilation emerging as a crucial behavioral determinant. Diurnal comparisons showed indoor ozone concentrations were 40% lower than outdoor levels during the day, highlighting the buffering effect of indoor environments. "Most exposure studies still rely on outdoor ozone data, but that's only half the story," said Prof. Xia Meng, senior author of the study. "Our findings show that ventilation behavior—something as simple as whether a window is open or closed—can change exposure dramatically."

This research introduces a practical, low-cost strategy for predicting indoor ozone exposure in real time across large geographic areas. The model can be integrated into health-risk assessments, smart-home monitoring systems, and public-health surveillance platforms, enabling policymakers and scientists to better understand indoor-outdoor exposure differences. Future work could extend the framework to other pollutants such as fine particulate matter or nitrogen dioxide, incorporate smart sensors for automated window tracking, and expand monitoring to diverse climatic zones.