@article {Ajala:2025:0736-2935:927,
title = "Predicting the Impact of Climate Change on Aircraft Noise Propagation in the National Airspace System (NAS)",
journal = "INTER-NOISE and NOISE-CON Congress and Conference Proceedings",
parent_itemid = "infobike://ince/incecp",
publishercode ="ince",
year = "2025",
volume = "271",
number = "2",
publication date ="2025-07-25T00:00:00",
pages = "927-937",
itemtype = "ARTICLE",
issn = "0736-2935",
url = "https://ince.publisher.ingentaconnect.com/content/ince/incecp/2025/00000271/00000002/art00094",
doi = "doi:10.3397/NC_2025_0158",
author = "Ajala, Abiola Olayinka and Owolabi, Oludare Adegbola and Adeyemi, Sarah Halleluyah and Shobowale, Olorunfunmi Samuel and Adeniran, Opeyemi Taiwo and Nyarko, Kofi and Abiodun, Pelumi O.",
abstract = "As climate change continues to alter atmospheric conditions, the propagation of aircraft noise in the National Airspace System (NAS) has become an area of growing concern, particularly for noise-sensitive regions near airports. This study investigated how meteorological factors including
temperature, wind patterns, visibility, humidity, and atmospheric pressure influence aircraft operations and associated noise impacts. Using data from the FAA Aircraft noise disturbance Aircraft report, we developed a predictive framework integrating meteorological data from NOAA which contains
historical weather and climate information. Multiple machine learning approaches were evaluated, including Random Forest, Long Short-Term Memory (LSTM) neural networks, and Gradient Boosting regressors, with Gradient Boosting achieving the strongest performance (R\texttwosuperior = 0.6771, RMSE = 0.6860).
Operational report types and visibility emerged as the most influential predictors, with visibility showing a strong negative correlation (-0.4341) with operations. Climate scenario projections indicated a 4.7% increase in aircraft operations under RCP4.5 and 11.6% under RCP8.5 by 2050, with
substantial seasonal variation showing the highest increase during summer months (12.4%). Analysis of residuals demonstrated that the model performed consistently across most temperature ranges but showed systematic biases at extreme visibility and wind speed values. These findings provide
critical insights for airport noise management planning and highlight the need for climate-adaptive noise mitigation strategies.",
}