Granger-guided reduced dual attention long short-term memory for travel demand forecasting during coronavirus disease 2019

The spread of Coronavirus disease 2019 (COVID-19) is closely related to residents’ travel. Quantities of studies have explored the spread of the epidemic impacted by the travel patterns. However, the researches of changes in residents' travel demand during the evolution of the epidemic are still insufficient. In particular, the lag effect of the epidemic on residents' travel demand has not been fully studied. This paper proposes a novel model named Granger-guided reduced dual attention long short-term memory (GRDA-LSTM) to predict changes in residents' travel demand under the impact of COVID-19. The contribution to artificial intelligence lies in leveraging Granger causality tests to enhance sensitivity to trend changes, incorporating a dual attention mechanism to improve forecasting performance, and utilizing channel reduction to boost efficiency. Experiments have proved that GRDA-LSTM is superior to existing Granger causality-integrated deep learning models. It effectively handles the abruptness and uncertainty of epidemic data, improves prediction accuracy, and meets rapid prediction requirements. The contribution in practical engineering applications is that the research findings not only provide more scientific guidance for traffic management practices in response to future comparable public health crises, but also broaden the research perspective on the impact of long-term public health events on transportation systems.