Comparison of Two National Noise Models: Progress Towards an Integrated Noise Model for Environmental Health Research in the United States

Two sound level maps currently exist for the contiguous United States. One was developed by the National Park Service (NPS) using machine learning methods and sound pressure level monitoring data, and the other by the Bureau of Transportation Statistics (BTS) using transportation noise models of roadway, aviation, and rail sources. Developed for different purposes, each has distinct strengths and weaknesses. This study aimed to compare the two models, develop a hybrid model integrating both, and evaluate its performance against field measurements. Linear regression with data from 378 NPS field sites was used to relate the NPS L50 metric to Leq. A positive association was observed, and the resulting regression equation was used to convert L50 to Leq. Comparing BTS 2018 and 2020 with the converted NPS model, we found strong correlation and small bias between BTS years (Pearson's r = 0.90, Spearman's rho = 0.88, bias = 0.3 dBA), but larger differences between BTS and NPS, with BTS levels on average ~6 dBA higher. A hybrid model was created by filling censored BTS areas with converted NPS Leq values. Evaluation against 708 NPS measurements and 757 metropolitan measurements showed good performance (bias = 0.4 dBA, MAE = 5.0 dBA for NPS; bias = -0.5 dBA, MAE = 3.8 dBA for metropolitan sites). Using the hybrid model, we estimated that ~36.4 million people (11.1% of the U.S. population) are exposed above 55 dB Leq. The hybrid model provides a resource to inform noise-related environmental health research, policy, and planning.