Abstract

Turbulence is a persistent and often unpredictable hazard in aviation, frequently occurring without visual or radar cues. This study presents a machine learning framework for identifying severe and extreme turbulence risk across U.S. airspace using only publicly available flight and weather data. The framework combines over 550,000 pilot reports with ERA5 reanalysis data to construct a large labeled dataset. It integrates anomaly-aware downsampling, synthetic oversampling, dimensionality reduction, and both unsupervised (K-Means) and supervised (XGBoost) modeling. In 10-fold cross-validation, the model achieved strong performance (recall = 0.91, F1 = 0.88) in detecting high-risk events. A real-world case study from February 2025 further illustrates the system’s predictive capability. This work demonstrates the feasibility of operational turbulence identification using open-source data and interpretable learning techniques.

References

• Herv´e Abdi and Lynne J Williams. Principal component analysis. Wiley interdisciplinary reviews: computational statistics, 2(4):433–459, 2010.
• Purnima Bholowalia and Arvind Kumar. Ebk-means: A clustering technique based on elbow method and k-means in wsn. International Journal of Computer Applications, 105(9), 2014.
• Nitesh V Chawla, Kevin W Bowyer, Lawrence O Hall, and W Philip Kegelmeyer. Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357, 2002.
• Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794, 2016.
• Mounir Chrit and Marwa Majdi. Operational wind and turbulence nowcasting capability for advanced air mobility. Neural Computing and Applications, 36(18):10637–10654, 2024.
• Ivan Bitar Fiuza de Mello, Gutemberg Borges Franc¸a, and Haroldo Fraga de Campos Velho. Enhancing clear air turbulence prediction: A comparative analysis of machine learning algorithms using gfs forecast and era-5 reanalysis data. 2024.
• Federal Aviation Administration. Turbulence: Staying safe. https://www.faa.gov/travelers/fly_safe/ turbulence.
• John A Hartigan and Manchek A Wong. Algorithm as 136: A k-means clustering algorithm. Journal of the royal statistical society. series c (applied statistics), 28(1):100–108, 1979.
• Hans Hersbach, Bill Bell, Paul Berrisford, Shoji Hirahara, Andr´as Hor´anyi, Joaqu´ın Mu˜noz-Sabater, Julien Nicolas, Carole Peubey, Raluca Radu, Dinand Schepers, et al. The era5 global reanalysis. Quarterly journal of the royal meteorological society, 146(730):1999–2049, 2020.
• Afaq Khattak, Jianping Zhang, Pak-Wai Chan, Feng Chen, and Abdulrazak H Almaliki. Aviation safety at the brink: Unveiling the hidden dangers of wind-shear-related aircraft-missed approaches. Aerospace, 12(2):126, 2025.
• Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. Isolation forest. In 2008 eighth ieee international conference on data mining, pages 413–422. IEEE, 2008.
• Shinya Mizuno, Haruka Ohba, and Koji Ito. Machine learning-based turbulence-risk prediction method for the safe operation of aircrafts. Journal of Big Data, 9(1):29, 2022.
• Domingo Mu˜noz-Esparza and Robert Sharman. An improved algorithm for low-level turbulence forecasting. Journal of Applied Meteorology and Climatology, 57(6):1249–1263, 2018.
• National Transportation Safety Board. Preventing turbulence-related injuries in air carrier operations conducted under title 14 code of federal regulations part 121. Technical Report SS-21/01, NTSB, 2021. https://www.ntsb.gov/ safety/safety-studies/Documents/SS2101.pdf.
• Robert Sharman, C Tebaldi, G Wiener, and J Wolff. An integrated approach to mid-and upper-level turbulence forecasting. Weather and forecasting, 21(3):268–287, 2006.
• Luke N Storer, Paul D Williams, and Philip G Gill. Aviation turbulence: dynamics, forecasting, and response to climate change. Pure and Applied Geophysics, 176:2081–2095, 2019.
• Paul D Williams. Increased light, moderate, and severe clear-air turbulence in response to climate change. Advances in atmospheric sciences, 34(5):576–586, 2017.