Skip to main content

Active Learning Metamodelling for R-NEST

Paper ID

SIDs-2022-091

Conference

SESAR Innovation Days

Year

2022

Theme

Modelling and Explainability

Project Name

SESAR 2020 ER4 project NOSTROMO, SESAR 2020 ER4 project SIMBAD

Keywords:

Active Learning, ATM, Gaussian Process, metamodelling, R-NEST

Authors

Raquel Sánchez, Christoffer Riis, Francisco Antunes, David Mocholí, Oliva García Cantú, Francisco Câmara Pereira, Ricardo Herranz and Carlos Lima Azevedo

DOI

Project Number

894241

Project Number

892517

Abstract

The computational cost of realistic air traffic simulations is a barrier for a comprehensive assessment of new ATM concepts and solutions, which, in practice, restricts the simulations to a limited number of scenarios, often insufficient to obtain conclusive results. So, a goal for a comprehensive exploration of the simulation space should be finding its most informative instances. This can be done by means of active learning metamodelling, which can be used to translate a complex simulation model into a metamodel, allowing a more efficient exploration of the simulation input-output space. This work presents two metamodels developed within the SESAR ER4 SIMBAD project for one of the state-of-the-art ATM simulation tools, R-NEST. The metamodels were trained using the active learning technique through the metamodelling framework developed by the SESAR ER4 NOSTROMO project. The training process with this tool is also described in the paper.