Authors: Ke Liu, Kaijing Ding, Xi Cheng, Jianan Chen, Siyuan Feng, Hui Lin, Jilin Song, Chen Zhu

Published on: May 14, 2024

Impact Score: 7.4

Arxiv code: Arxiv:2405.08293

Summary

• What is new: Application of the novel Temporal Fusion Transformer model to predict numerical airport arrival delays at a more granular quarter hour level.
• Why this is important: Flight delay prediction in previous research is often categorical and highly aggregated.
• What the research proposes: Using the Temporal Fusion Transformer to predict airport arrival delays at U.S. top 30 airports with detailed input factors.
• Results: The model achieved satisfactory performance with small prediction errors and provided insights into important factors for delay prediction.

Technical Details

Technological frameworks used: Temporal Fusion Transformer

Models used: nan

Data used: Airport demand and capacity forecasts, historic airport operation efficiency, airport wind and visibility conditions, enroute weather and traffic conditions

Potential Impact

Airlines, airports, airline logistic services

Want to implement this idea in a business?

We have generated a startup concept here: SkyPredict.