Application of Quantum Artificial Intelligence for Airport Potential Analysis and Aerotropolis Development
- Fabiano Rocha
- Giovanna Miceli Ronzani Borille
- Fabio Rocha Barbosa
Federal Institute of Ceará · Aeronautics Institute of Technology · Federal University of Piauí
- Event
- XXII SITRAER – Brasília, DF, Brasil, October 22–24, 2025
- Volume
- Anais do XXII Simpósio de Transporte Aéreo – SITRAER 2025 · ISBN 978-65-272-2024-4 · DOI 10.29327/9786527220244
- Publisher
- Even3 Publicações
- Editors
- Fabiana Serra de Arruda, Camila Lucena, Giovanna Miceli Ronzani Borille, Evandro José da Silva
Abstract
The development of aerotropolises—a strategic urban model where airports serve as economic hubs—requires analyzing multiple interdependent factors, including infrastructure, connectivity, regulations, investments, and regional economic dynamics. These datasets often contain hundreds of variables with nonlinear relationships that traditional methods struggle to capture, risking oversimplified feasibility assessments, especially for predictive modeling. Data Envelopment Analysis (DEA) remains essential for benchmarking efficiency, offering insights into current performance. In this study, DEA provided efficiency benchmarks; however, its static nature limits multidimensional evaluations, reinforcing the need for advanced approaches capable of handling high-dimensional data and uncovering complex patterns. This research investigates Quantum Artificial Intelligence (QAI) as a disruptive method for aerotropolis potential assessment. By combining AI’s pattern-recognition capabilities with quantum computing’s parallelism, QAI can manage large-scale, multidimensional airport datasets. As a proof of concept, we implemented a Quantum Support Vector Machine (QSVM) and compared it to a classical SVM using DEA-based data from Brazilian airports. Although the dataset was intentionally small, results indicate that the quantum kernel offers a more discriminative representation, confirmed by structural metrics such as silhouette score and kernel alignment, despite similar accuracy. The proposed framework demonstrates QAI’s potential to enhance aerotropolis planning through robust analytical tools for multi-criteria decision-making and investment prioritization under uncertainty. Leveraging QAI allows stakeholders to simulate scenarios—such as infrastructure upgrades or regulatory incentives—and predict impacts on feasibility, improving strategic airport development and fostering competitiveness in air transport networks.
Keywords: Aerotropolis Planning; Airport Performance Analysis; High-Dimensional Data; Artificial Intelligence; Quantum Machine Learning