AI model forecasts airport security throughput using flight schedules

Researchers have developed a novel framework to forecast hourly airport security checkpoint throughput by converting flight schedules into temporally aligned signals. This approach utilizes a Temporal Fusion Transformer, which integrates schedule-derived arrival-intensity signals with historical data and temporal variables. The model achieved a weighted mean absolute percentage error of 9.33% for six-hour forecasts, outperforming recurrent neural network and long short-term memory models, and maintained competitive error rates for longer forecast horizons. AI

IMPACT This framework could improve operational efficiency at airports by enabling better staffing and resource allocation for security checkpoints.

RANK_REASON The cluster contains an academic paper detailing a new forecasting model. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Cirium Diio
• long short-term memory
• recurrent neural network
• Temporal Fusion Transformer
• Transportation Security Administration

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →