Estimating Air Exchange Rates in Thousands of Elementary School Classrooms using Commercial CO2 Sensors and Machine Learning

In this study, the authors introduce a scalable and cost-effective method to estimate classroom air exchange rates (AER) using end-of-day carbon dioxide (CO₂) data from commercial sensors. This method assumes well-mixed conditions and replicates the tracer gas technique, utilizing statistical machine learning and knowledge of classroom operations to automate AER calculations at the end of occupied periods. They analyzed data from 3206 sensors across 125 schools in a large urban school district in the Northeastern United States and identified 648,956 CO₂ decay curves over one school year. After applying data screening criteria, we calculated 323,776 AER values, with an average of 84 values (SD = 40) per classroom. The AER ranged from less than 0.1 to 64 h−1, with an average of 3.0 h−1 (SD = 2.9). The average AER in schools with central mechanical ventilation was 1.8 times higher than in schools without mechanical ventilation. The method is optimized for parallel and high-performance computing resources, allowing daily air exchange rate calculations for an entire classroom over a school year in a few seconds, an entire school in a few minutes, and a district in just a few hours. This represents the largest deployment of commercial CO₂ sensors in schools with publicly shared data. The AER calculation approach is scalable and efficient, automating the cleaning, selection, and processing of CO₂ data from commercial sensors, with methods and code that can be transferred to other schools collecting similar large-scale data.