AI Research Catalyst Fund Awardees Virtual Seminar Series

“Real-time Forecasting of Dockless Scooter-Sharing Demand: A Context-Aware Spatio-Temporal Multi-Graph Convolutional Network Approach”

by Yiming Xu
Ph.D. student in the Department of Civil and Coastal Engineering
PI: Dr. Xilei Zhao

Wednesday, September 1, 2021

ABSTRACT:

Real-time demand forecasting for micromobility can greatly enhance its potential benefits and mitigate its adverse effects on urban mobility. The deep learning models provide researchers powerful tools to deal with the real-time dockless scooter-sharing demand prediction problem, but existing studies have not fully incorporated the features that are highly associated with the demand, such as demographic characteristics, zonal functionality, and weather conditions. This paper proposes a novel deep learning model named Context-Aware Spatio-Temporal Multi-Graph Convolutional Network (CA-STMGCN) to forecast the real-time dockless scooter-sharing demand. The proposed model applies a Graph Convolutional Network (CGN) component that uses spatial adjacency graph, functional similarity graph, and demographic similarity graph as input graphs to extract spatial dependency and attach the spatial dependency to historical demand data. Then, we use a Gated Recurrent Unit (GRU) component to process the output of GCN and weather condition data to capture temporal dependency. Lastly, a fully connected neural network layer is used to generate the final prediction. The proposed model is evaluated using the real-world dockless scooter-sharing demand data in Washington, D.C. The results show that the proposed model outperforms all the selected benchmark models. The new deep learning model can help the operators develop optimal vehicle charging and rebalancing schemes and guide cities to regulate the dockless scooter-sharing usage.

Bio:

Yiming Xu is a Ph.D. student in the Department of Civil and Coastal Engineering at the University of Florida. He received his B.E. and M.E. degrees in transportation engineering from Tongji University, China. His research interests include shared mobility, data analytics for transportation systems, and machine learning.

Wednesday, September 1, 2021
12:00PM – 1:00PM
Via Zoom

RSVP below. Instructions to attend talk via Zoom will be emailed to you.