Unified Estimation of turbulence eddy dissipation rate of atmospheric Turbulence for effective flight plan management

The aim of the proposed project is to develop a machine learning classification that predicts energy from turbulent flow atmospheric systems. Being able to predict turbulent flows is of great importance since the atmosphere features strongly in the invisible infrastructure of aviation from established navigation waypoints to conduit airways – the highways in the sky. A primary consequence of the onset of turbulence in the atmosphere is the dramatic unpredictability and the challenge in forecasting the phenomenon. More than 100 years after Osborne Reynold’s seminal experiments on the transition of flow through a pipe from a laminar (smooth) to a turbulent state, the exact quantification that drives this phenomenon on a meta-scale level still vexes the aviation and meteorological community. In this project we aim use artificial intelligence and machine learning in order to predict energy from turbulent flow atmospheric systems thus allowing the development of a turbulence prediction model and design flight routes.

Faculty Supervisor:

Reda Alhajj

Student:

Salim Afra

Partner:

Skyplan

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Calgary