Abstract
We designed this study to map environmental noise pollution (ENP) around all elementary schools and kindergartens in Tehran using a land use regression (LUR) approach. Out of 135 spatial predictor variables, seven were identified as significant determinants of ENP. The final model demonstrated strong predictive performance, with an R² of 0.70 and an adjusted R² of 0.65. Additionally, the model had a leave-one-out cross-validation (LOOCV) R² of 0.59 and a root mean squared error (RMSE) of 3.15, indicating acceptable predictive accuracy. Among the significant predictors, green space area, and the distances to the nearest terminals, primary roads, and highways had negative effects on ENP, meaning that increases in these variables reduce noise levels around schools and kindergartens. In contrast, the length of secondary roads, the area of commercial parcels, and the distance to military zones had positive effects, suggesting that increases in these variables contributed to higher ENP. Our findings reveal substantial spatial variation in environmental noise levels across Tehran, with the highest ENP values-ranging from 65.1 dB(A) to 85 dB(A)-concentrated primarily in the central, southern, and southeastern districts of the city. Approximately 36%, 30%, and 13% of educational institutions for children in Tehran are exposed to ENP in the range of 70.1-75 dB(A), 65-70 dB(A), and > 75 dB(A), respectively. Only 4% of these institutions are located in areas with ENP < 60 dB(A). Our findings highlight the importance of infrastructure design changes, such as expanding green spaces around schools and kindergartens, or relocating these educational institutions farther from terminals, primary roads, military zones, and commercial areas.