A new machine learning model developed by researchers from Fudan University and the Chinese Academy of Sciences can predict hourly indoor ozone (O₃) concentrations using easily accessible data, marking a significant advancement in assessing human exposure to this harmful air pollutant. The study, published in Eco-Environment & Health, addresses a critical gap in exposure science: while most people spend 70%–90% of their time indoors, traditional risk assessments rely heavily on outdoor ozone measurements, which do not accurately reflect actual exposure.
Ozone is a key air pollutant formed by chemical reactions under sunlight. In 2021, long-term ozone exposure contributed to nearly 490,000 deaths worldwide. Indoor ozone levels are influenced by outdoor concentrations, building ventilation, and indoor sources. However, traditional models require detailed indoor parameters that are difficult to obtain at scale, while linear regressions fail to capture complex nonlinear relationships. This study introduces a scalable, data-driven approach using random forest algorithms.
The research team collected over 8,200 hours of indoor ozone data using portable electrochemical sensors in 23 households across 18 Chinese cities. Predictor variables included outdoor ozone levels from high-resolution random forest and MERRA-2 datasets, meteorological parameters (temperature, humidity, wind, solar radiation, boundary-layer height, and surface pressure), and window-opening status recorded manually by volunteers. Two models were compared: one excluding and one including window status. Incorporating window behavior raised cross-validation R² from 0.80 to 0.83 and lowered RMSE from 7.89 to 7.21 ppb, demonstrating that ventilation behavior significantly improves prediction accuracy.
The model accurately captured hourly ozone fluctuations and regional differences, performing better in southern China than in the north, and better in the cold season than in the warm season. Predictor-importance analysis showed surface pressure, temperature, and ambient ozone as dominant factors, with ventilation emerging as a crucial behavioral determinant. Diurnal comparisons revealed that indoor ozone concentrations were 40% lower than outdoor levels during the day, underscoring the buffering effect of indoor environments.
"Most exposure studies still rely on outdoor O₃ 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." The 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. This machine-learning approach bridges environmental modeling with daily life, promoting healthier indoor environments in rapidly urbanizing regions.
