Machine Learning Prediction of Student Satisfaction on Indoor Air Quality and Thermal Environment in a Norwegian Secondary School

Tidsskrift: ASHRAE Conference Proceedings, 4. august 2025

Doi: doi.org/10.63044/s25pre69

Sammendrag:
Ensuring a healthy and comfortable indoor environment in schools is essential for student well-being and academic performance. The purpose of this study is to investigate the factors influencing students’ satisfaction with indoor air quality (IAQ) and thermal comfort in classrooms. To address this, one year-long measurements were conducted across multiple classrooms in a Norwegian secondary school, collecting data on indoor climate (CO₂, VOC levels, temperature, relative humidity, and air pressure) along with outdoor climate variables (temperature, humidity, and solar radiation). Additional room-specific data, including orientation, floor level, and ventilation system specifications, were also considered. An online feedback system was used to gather 1,473 real-time student responses on satisfaction levels. Supervised machine learning (ML) models were developed to assess the importance of these parameters in predicting perceived indoor comfort: IAQ perceptions and thermal environmental perceptions. Results showed ML models effectively predicted student dissatisfaction, achieving accuracy greater than 80% when environmental and building parameters were considered simultaneously. The findings emphasized that dissatisfaction with indoor conditions is driven by multiple interacting factors of measured variables and building parameters single independent variables. SHAP analysis provided valuable interpretability, revealing how variations in environmental conditions collectively impact students' perceived comfort. This comprehensive approach demonstrates the practical potential of ML-based IEQ monitoring systems, suggesting that schools can proactively improve indoor conditions through targeted interventions informed by real-time predictions.