Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
This work addresses a domain-specific problem for urban planners and public safety officials, offering an incremental improvement by combining existing techniques like residual networks with spatio-temporal modeling.
The paper tackles the problem of predicting citywide crowd flows, which is important for traffic management and public safety, by proposing ST-ResNet, a deep-learning approach that models spatio-temporal data using residual neural networks and external factors, achieving performance that exceeds six well-known methods on datasets from Beijing and NYC.
Forecasting the flow of crowds is of great importance to traffic management and public safety, yet a very challenging task affected by many complex factors, such as inter-region traffic, events and weather. In this paper, we propose a deep-learning-based approach, called ST-ResNet, to collectively forecast the in-flow and out-flow of crowds in each and every region through a city. We design an end-to-end structure of ST-ResNet based on unique properties of spatio-temporal data. More specifically, we employ the framework of the residual neural networks to model the temporal closeness, period, and trend properties of the crowd traffic, respectively. For each property, we design a branch of residual convolutional units, each of which models the spatial properties of the crowd traffic. ST-ResNet learns to dynamically aggregate the output of the three residual neural networks based on data, assigning different weights to different branches and regions. The aggregation is further combined with external factors, such as weather and day of the week, to predict the final traffic of crowds in each and every region. We evaluate ST-ResNet based on two types of crowd flows in Beijing and NYC, finding that its performance exceeds six well-know methods.