# Generative Augmentation of Imbalanced Flight Records for Flight Diversion Prediction: A Multi-objective Optimisation Framework

arXiv: https://arxiv.org/abs/2604.20288 · HTML: https://mlsanity.com/paper/2604.20288/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 16 of 16)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [A Comprehensive Survey on Rare Event Prediction](https://mlsanity.com/paper/2309.11356/) (2023)
- [Systematic Assessment of Tabular Data Synthesis](https://mlsanity.com/paper/2402.06806/) (2024)
- [Robust Variational Autoencoder for Tabular Data with Beta Divergence](https://mlsanity.com/paper/2006.08204/) (2020)
- [Differentially Private Release of High-Dimensional Datasets using the Gaussian Copula](https://mlsanity.com/paper/1902.01499/) (2019)
- [Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class](https://mlsanity.com/paper/2412.15657/) (2024)
- [Robust Bayesian Inference for Discrete Outcomes with the Total Variation Distance](https://mlsanity.com/paper/2010.13456/) (2020)
- [Towards Autonomous Cybersecurity: An Intelligent AutoML Framework for Autonomous Intrusion Detection](https://mlsanity.com/paper/2409.03141/) (2024)
- [A Comparative Study of Sampling Methods with Cross-Validation in the FedHome Framework](https://mlsanity.com/paper/2406.01950/) (2024)
- [Towards a framework on tabular synthetic data generation: a minimalist approach: theory, use cases, and limitations](https://mlsanity.com/paper/2411.10982/) (2024)
- [Synthetic Aircraft Trajectory Generation Using Time-Based VQ-VAE](https://mlsanity.com/paper/2504.09101/) (2025)
- [Deep Learning Aided Packet Routing in Aeronautical Ad-Hoc Networks Relying on Real Flight Data: From Single-Objective to Near-Pareto Multi-Objective Optimization](https://mlsanity.com/paper/2110.15145/) (2021)
- [An Exploratory Assessment of LLM's Potential Toward Flight Trajectory Reconstruction Analysis](https://mlsanity.com/paper/2401.06204/) (2024)
- [Improving Aviation Safety Analysis: Automated HFACS Classification Using Reinforcement Learning with Group Relative Policy Optimization](https://mlsanity.com/paper/2508.21201/) (2025)

## Built on by (most cited first, 1 of 1)

- [TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement](https://mlsanity.com/paper/2608.11951/) (2026)

## Abstract (arXiv)

Flight diversions are rare but high-impact events in aviation, making their reliable prediction vital for both safety and operational efficiency. However, their scarcity in historical records impedes the training of machine learning models used to predict them. This study addresses this challenge by proposing a generative augmentation framework for imbalanced aviation tabular records. The principal contribution lies in the design of a composite optimisation objective specifically tailored to flight data, which integrates four complementary quality dimensions into a single score used to guide automated hyperparameter search via the Tree-structured Parzen Estimator (TPE) algorithm: realism, statistical similarity, fidelity, and predictive utility. These dimensions were selected and defined to reflect the operational and statistical requirements specific to aviation records, and were complemented by two descriptive evaluation dimensions, diversity and operational validity, forming a six-stage assessment framework. The composite objective was then used to tune three deep generative models, namely Tabular Variational Autoencoder (TVAE), Conditional Tabular Generative Adversarial Network (CTGAN), and CopulaGAN, with Gaussian Copula (GC) serving as a statistical baseline. Results show that optimised models substantially outperform their default counterparts across all six assessment dimensions, and that augmentation with the resulting synthetic data improves diversion prediction compared to training on real data alone. These findings demonstrate that domain-adapted multi-objective optimisation is an effective strategy for generative augmentation of rare events in aviation, with applicability to other imbalanced tabular prediction tasks.