An improved prophet emergency traffic flow prediction model

Emergencies are rare and random, but cause dramatic changes in traffic volumes whenever they occur. It therefore poses a huge challenge to accurately predict emergency traffic volumes. This paper aims to provide a practical methodology for predicting traffic volumes during emergencies, which was built using the Prophet model and improving the event function of the model. The proposed approach isolates the event impacts through time series decomposition techniques, and allows the model to add points in time when traffic flow changes abruptly and to incorporate external factors useful to adapt to the specific background imposed by the emergency. The main data used in the paper was the daily traffic volume dataset published on the Luxembourg Data Open Platform. These data were collected over a span from January 2017 to December 2021. The dataset covers the period of impact of the two emergencies. The proposed method and four comparative models were applied to the second emergency period. The results show that the proposed method can accurately predict unconventional changes caused by emergencies and has better prediction accuracy with real data than the other comparative models under the same attribute conditions through a comparative analysis.