Prediction of Indoor CO2 Concentration in a University Hospital Using Machine Learning Algorithms

Machine Learning (ML) models effectively capture complex, nonlinear, multimodal, and time-dependent patterns in indoor environments. In thisstudy, the relationship between indoor CO2 concentrations and environmental variables in different areas of a university hospital was investigated using ML methods. The dataset is a total of 114, including 80% train and 20% test. CO2 concentration measured at 16:00 was defined as the target variable, while eight inputs (number of occupants, room volume, room floor area, average relative humidity, average temperature, average CO2 concentration, the change in CO2 concentration, room orientation) were selected as model inputs. Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), Random Forest (RF) and Linear Regression were applied to predict CO2 concentration. Model performance was evaluated based on prediction accuracy criteria, such as Mean Absolute Percentage Error (MAPE), Coefficient of Determination (R2), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), so it enabled a comparative consideration of their effectiveness. When CO2-related variables were included, RF achieved the best performance (R2 = 0.804, MAPE = 8.34%, MAE = 70.65, RMSE = 104.24), followed by XGBoost (R2 = 0.776, MAPE = 9.07%, MAE = 78.10, RMSE = 111.44). In contrast, ANN (R2 = 0.250, MAPE = 19.62%, MAE = 159.81, RMSE = 203.72) and Linear Regression (R2 = 0.175, MAPE = 19.44%, MAE = 169.37, RMSE = 213.77) showed comparatively lower predictive performance. Overall, the results indicate that tree-based ML models can provide promising predictive performance and practical insights for indoor air quality monitoring and management in healthcare facilities, while their applicability and generalizability could be further strengthened through future evaluations involving data from diverse healthcare environments.