Skip to main content

Recommending Strategic Air Traffic Management Initiatives in Convective Weather

Paper ID

ATM-2021-016

Conference

USA/Europe ATM R&D Seminar

Year

2021

Theme

Weather in ATM

Project Name

Keywords:

epsilon-greedy, reinforcement learning, simulation, softmax, traffic management initiatives, weather

Authors

James Jones, Zach Ellenbogen and Yan Glina

DOI

Project Number

Abstract

The presence of uncertainty in weather forecasts poses significant challenges for air traffic managers. These challenges can have major repercussions on stakeholders in terms of their impact on the delay within the system. In this paper, we discuss an approach for recommending Traffic Management Initiative (TMI) parameters during uncertain weather conditions. We propose four methods for TMI selection. The first two favor random exploration of TMI decisions. An epsilon-greedy approach and a softmax algorithm are also evaluated against the two random exploration approaches. A parallel fast-time simulation framework is presented for evaluating the proposed methods over a range of weather forecast scenarios. A set of regional TMIs is applied and tested against a case day in which the airspace capacity in the Northeast United States was compromised by convective weather. Both the softmax and epsilon-greedy approaches demonstrate strong performance relative to the other methods. The results suggest that the approach could potentially aid air traffic stakeholders in understanding how to best deal with weather forecast uncertainty.