Machine Learning for Dynamic Airspace Configuration towards Optimized Mobility in Emergency Situations

Abstract

The objective of this project is to develop a prototype for dynamic airspace configuration (DAC) through the use of machine learning (ML) techniques, to achieve optimized mobility in emergency situations. Disasters, such as hurricanes, tornadoes, and thunderstorms, affect many people and cause severe economic losses every year. When disasters occur, air travel is an efficient mode of transportation for emergency evacuation. With the large volume of travel occurring in a short period of time, the current structured, static airspace cannot accommodate rapid increases in traffic demand during emergency situations. An adaptive and dynamic scheduling program for air travel during the crisis is in demand. The purpose of this study is to enable dynamic airspace configuration (DAC) to optimize air mobility in an emergency evacuation. We propose to identify, apply, and evaluate machine learning (ML) techniques as they relate to DAC. The anticipated outcome is a prototype that would demonstrate the ML-augmented capability supporting DAC.

Note: The title of this project was later changed to "Application of Artificial Intelligence in the Optimization of Mobility in Dynamic Airspace Configurations During Emergency Situations" and Dr. Yongxin Liu assumed the lead role in completing the project.

CATM Research Affiliates: Houbing Song (ERAU: Lead), Dahai Liu (ERAU), Yongxin Liu (ERAU)