![Journal of Aviation/Aerospace Education & Research](/assets/md5images/b12925aa5740d5f2db58f76a8d249794.png)
Volume
33
Issue
4
Key words
hail forecast, severe weather, airport safety, machine learning, ArcGIS, neural network
Abstract
The National Airspace System (NAS) is a sophisticated network of air traffic control, navigation, and communication systems that play a critical role in ensuring the safe and efficient flow of air traffic across the United States. However, the occurrence of severe weather conditions, particularly hailstorms, poses a significant threat to flight safety within the NAS. To mitigate the risks associated with hail, aviation organizations have implemented a range of safety measures. This study utilized Esri’s ArcGIS as a mapping software to conduct a geospatial analysis of the impact of severe weather, particularly hail, on the NAS. The Hail Awareness Spatial Analysis Toolkit (HASAT), developed as part of this research, leveraged Machine Learning (ML) as a forecasting method to predict the occurrence of severe hail events. The results of the analysis revealed that states such as Texas, Oklahoma, Kansas, and Nebraska emerged as the epicenter of these hailstorms. The Hail Awareness Spatial Analysis Toolkit (HASAT) possessed an additional capability to provide localized hail data to pilots, empowering aviation operators with critical information for flight safety. By incorporating this tool into existing systems, pilots can access real-time, location-specific hail data, enabling them to make informed choices regarding flight routes and potential hazards associated with hailstorms.
Scholarly Commons Citation
Fu, H.,
Hupy, J. P.,
Lu, C.,
& Ji, Z.
(2024).
Machine Learning - Hail Awareness Spatial Analysis Toolkit (HASAT).
Journal of Aviation/Aerospace Education & Research, 33(4).
DOI: https://doi.org/10.58940/2329-258X.2041
Included in
Aviation Safety and Security Commons, Management and Operations Commons, Meteorology Commons