Airport Passenger Flow Forecasting via Deformable Temporal-Spectral Transformer Approach

2025-12-04

AI Summary

Airport passenger flow exhibits strong heterogeneity, abrupt fluctuations, and multiple periodicities—posing significant challenges for accurate forecasting. To address this, we propose DTSFormer, a deformable time-frequency Transformer. Methodologically, it introduces a novel window-function-driven multi-scale deformable patching mechanism to dynamically adapt to varying flow rhythms; incorporates a frequency-domain attention module to explicitly model high- and low-frequency components; and fuses multi-frequency temporal features to jointly capture short-term fluctuations and long-term trends. Evaluated on real-world data from Beijing Capital International Airport (2023–2024), DTSFormer consistently outperforms state-of-the-art methods across all prediction horizons, achieving an average 18.7% reduction in MAE. Notably, it demonstrates superior responsiveness to high-frequency abrupt fluctuations. These results establish DTSFormer as a robust, high-precision forecasting framework for intelligent airport operations.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Time-Series/Data Streams
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Accurate forecasting of passenger flows is critical for maintaining the efficiency and resilience of airport operations. Recent advances in patch-based Transformer models have shown strong potential in various time series forecasting tasks. However, most existing methods rely on fixed-size patch embedding, making it difficult to model the complex and heterogeneous patterns of airport passenger flows. To address this issue, this paper proposes a deformable temporal-spectral transformer named DTSFormer that integrates a multiscale deformable partitioning module and a joint temporal-spectral filtering module. Specifically, the input sequence is dynamically partitioned into multiscale temporal patches via a novel window function-based masking, enabling the extraction of heterogeneous trends across different temporal stages. Then, within each scale, a frequency-domain attention mechanism is designed to capture both high- and low-frequency components, thereby emphasizing the volatility and periodicity inherent in airport passenger flows. Finally, the resulting multi-frequency features are subsequently fused in the time domain to jointly model short-term fluctuations and long-term trends. Comprehensive experiments are conducted on real-world passenger flow data collected at Beijing Capital International Airport from January 2023 to March 2024. The results indicate that the proposed method consistently outperforms state-of-the-art forecasting models across different prediction horizons. Further analysis shows that the deformable partitioning module aligns patch lengths with dominant periods and heterogeneous trends, enabling superior capture of sudden high-frequency fluctuations.

Problem

• Forecasting airport passenger flows using a deformable transformer
• Modeling complex and heterogeneous patterns in passenger flow data
• Capturing both short-term fluctuations and long-term trends in flows

Innovation

• Dynamic multiscale patch partitioning for heterogeneous trends
• Frequency-domain attention capturing volatility and periodicity
• Time-domain fusion of multi-frequency features for fluctuations and trends