Skip to content

Dynamic Pairwise Wake Vortex Separations For Arrivals Using Predictive Machine Learning Models

The potential encounter of wake vortices from a preceding flight is at the origin of the wake separation minima between aircraft on the final approach. Wake separations ensure safety under all conditions, but have been shown to be over-conservative in some meteorological conditions which directly penalises runway performance. This paper describes the Dynamic Pairwise Wake Separation for Arrivals (D-PWS-A) concept which has been developed in order to safely reduce, when possible, wake separation minima between consecutive arrivals on the final approach based on wake risk monitoring. Aircraft wake behaviour and meteorological information is monitored and processed using Machine Learning (ML) algorithms which determine the wake separation minimum reductions that can be safely applied between subsequent arriving aircraft. The use of wake behaviour monitoring combined with ML techniques allows us to maximise the conditions under which wake separations can be reduced. The model is developed and tested based on field data collected in Paris-CDG airport.

Lorenzo Frigerio, Ivan De Visscher, Guillaume Stempfel, Rocio Barragan Montes & Catherine Chalon Morgan, In Proc. of The 33rd Congress of the International Council of the Aeronautical Sciences (ICAS), September 2022.

Click here to access the paper.

Releated Posts

Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings

In this paper, we study graph representation learning and show that data augmentation that preserves semantics can be learned and used to produce interpretations. Our framework, which we named INGENIOUS, creates inherently interpretable embeddings and eliminates the need for costly additional post-hoc analysis.
Read More

SANGEA: Scalable and Attributed Network Generation

In this paper, we present SANGEA, a sizeable synthetic graph generation framework that extends the applicability of any SGG to large graphs. By first splitting the large graph into communities, SANGEA trains one SGG per community, then links the community graphs back together to create a synthetic large graph.
Read More