Mobile data signals could help airports predict passenger surges

An international study suggests that anonymized cellphone data can significantly improve airport operations by predicting passenger surges. Researchers analyzed over 9 million mobile network signals collected around Lisbon Airport in Portugal to develop a forecasting model that outperformed standard methods, reducing forecast errors by up to 24%.

The research team, which included faculty from Texas A&M University, Molde University College in Norway, and Inov Inesc in Portugal, utilized data from 119 grid cells covering the airport's footprint over a one-year period. To protect privacy, the signals were aggregated and anonymized, with any data slice containing fewer than 10 devices being excluded.

By using a time-series forecasting tool to account for seasonal swings and holidays, the study aims to provide airport managers with actionable insights to reduce congestion, manage capacity, and lower emissions. Lisbon Airport was used as a primary test case due to its high passenger volumes and seasonal fluctuations.