Situational-Aware Multi-Graph Convolutional Recurrent Network (SA-MGCRN) for Travel Demand Forecasting During Wildfires
This addresses a critical problem for emergency managers and transportation planners during large-scale wildfire evacuations, representing a novel application rather than an incremental improvement in general travel forecasting.
This study tackles real-time travel demand forecasting during wildfire evacuations by developing the SA-MGCRN deep learning model using GPS data and AI technologies, tested on the 2019 Kincade Fire case where it significantly outperformed state-of-the-art benchmarks.
Real-time forecasting of travel demand during wildfire evacuations is crucial for emergency managers and transportation planners to make timely and better-informed decisions. However, few studies focus on accurate travel demand forecasting in large-scale emergency evacuations. Therefore, this study develops and tests a new methodological framework for modeling trip generation in wildfire evacuations by using (a) large-scale GPS data generated by mobile devices and (b) state-of-the-art AI technologies. The proposed methodology aims at forecasting evacuation trips and other types of trips. Based on the travel demand inferred from the GPS data, we develop a new deep learning model, i.e., Situational-Aware Multi-Graph Convolutional Recurrent Network (SA-MGCRN), along with a model updating scheme to achieve real-time forecasting of travel demand during wildfire evacuations. The proposed methodological framework is tested in this study for a real-world case study: the 2019 Kincade Fire in Sonoma County, CA. The results show that SA-MGCRN significantly outperforms all the selected state-of-the-art benchmarks in terms of prediction performance. Our finding suggests that the most important model components of SA-MGCRN are evacuation order/warning information, proximity to fire, and population change, which are consistent with behavioral theories and empirical findings.