Synthetic Flight Data Generation Using Generative Models

TL;DR

This paper explores the use of generative models, specifically TVAE and Gaussian Copula, to produce realistic synthetic flight data that can improve predictive models in aviation while addressing data confidentiality issues.

Contribution

It introduces a comprehensive framework for evaluating synthetic flight data quality and compares two generative models, highlighting their strengths and limitations.

Findings

Gaussian Copula achieves higher statistical similarity and fidelity.

TVAE handles large datasets efficiently and is scalable.

Synthetic data enables flight delay prediction with accuracy comparable to real data.

Abstract

The increasing adoption of synthetic data in aviation research offers a promising solution to data scarcity and confidentiality challenges. This study investigates the potential of generative models to produce realistic synthetic flight data and evaluates their quality through a comprehensive four-stage assessment framework. The need for synthetic flight data arises from their potential to serve as an alternative to confidential real-world records and to augment rare events in historical datasets. These enhanced datasets can then be used to train machine learning models that predict critical events, such as flight delays, cancellations, diversions, and turnaround times. Two generative models, Tabular Variational Autoencoder (TVAE) and Gaussian Copula (GC), are adapted to generate synthetic flight information and compared based on their ability to preserve statistical similarity, fidelity, diversity, and predictive utility. Results indicate that while GC achieves higher statistical similarity and fidelity, its computational cost hinders its applicability to large datasets. In contrast, TVAE efficiently handles large datasets and enables scalable synthetic data generation. The findings demonstrate that synthetic data can support flight delay prediction models with accuracy comparable to those trained on real data. These results pave the way for leveraging synthetic flight data to enhance predictive modeling in air transportation.