Running summarizing tools on a new article
Check the paper below, then start its synthesis.
Airport Delay Prediction with Temporal Fusion Transformers
Ke Liu (University of California, Berkeley), Kaijing Ding (University of California, Berkeley), Xi Cheng (University of Illinois Chicago), Guanhao Xu (Oak Ridge National Laboratory), Xin Hu (University of Michigan), Tong Liu (University of Illinois Urbana-Champaign), Siyuan Feng (Hong Kong University of Science and Technology), Binze Cai (Georgia Institute of Technology), Jianan Chen (University of British Columbia), Hui Zhi Lin (Northwestern University), Jilin Song (University of Toronto), Chen Zhu (Tsinghua University)
Abstract: Since flight delay hurts passengers, airlines, and airports, its prediction becomes crucial for the decision-making of all stakeholders in the aviation industry and thus has been attempted by various previous research. However, previous delay predictions are often categorical and at a highly aggregated level. To improve that, this study proposes to apply the novel Temporal Fusion Transformer model and predict numerical airport arrival delays at quarter hour level for U.S. top 30 airports. Inputs to our model include airport demand and capacity forecasts, historic airport operation efficiency information, airport wind and visibility conditions, as well as en-route weather and traffic conditions. The results show that our model achieves satisfactory performance measured by small prediction errors on the test set. In addition, the interpretability analysis of the model outputs identifies the important input factors for delay prediction.