Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks

By Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, Xiuwen Yi, Tianrui Li. Artificial Intelligence, 2017

492 citations recorded by the source corpus.

Forecasting the flow of crowds is of great importance to traffic management and public safety, and very challenging as it is affected by many complex factors, including spatial dependencies (nearby and distant), temporal dependencies (closeness, period, trend), and external conditions (e.g., weather and events). We propose a deep-learning-based approach, called ST-ResNet, to collectively forecast two types of crowd flows (i.e. inflow and outflow) in each and every region of 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 residual neural network framework to model the temporal closeness, period, and trend properties of crowd traffic. For each property, we design a branch of residual convolutional units, each of which models the spatial properties of 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 have developed a real-time system based on Microsoft Azure Cloud, called UrbanFlow, providing the crowd flow monitoring and forecasting in Guiyang City of China. In addition, we present an extensive experimental evaluation using two types of crowd flows in Beijing and New York City (NYC), where ST-ResNet outperforms nine well-known baselines.

Subfields: Artificial Intelligence, Building and Construction, Transportation

View Paper: https://www.semanticscholar.org/paper/9dbc46768641a975b30d1249e49fb0e0fc0803aa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Qiang Yang
3. Yu Zheng
4. Senzhang Wang
5. Jiannong Cao
6. Jieping Ye
7. Junbo Zhang
8. Tianrui Li

In Building and Construction

1. Philip S. Yu
2. Senzhang Wang
3. Gao Cong
4. Junbo Zhang
5. Shengna Guo
6. Youfang Lin
7. Huaiyu Wan
8. Jiannong Cao

In Transportation

1. Yu Zheng
2. Philip S. Yu
3. Senzhang Wang
4. Junbo Zhang
5. Gao Cong
6. Qiang Yang
7. Jiannong Cao
8. Xiuwen Yi

Citations in the corpus

• Deep Distributed Fusion Network for Air Quality Prediction (2018, background): “proposed a CNN-based network to extract features [13, 15, 16].”
• Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting (2019, methodology): “With convolutional neural network and recurrent neural network, state-of-the-art results are achieved in (Shi et al. 2015; Yu et al. 2017; Shi et al. 2017; Zhang, Zheng, and Qi 2017; Zhang et al. 2018a; Ma et al. 2017; Yao et al. 2018b; 2018a).”
• Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting (2019, background): “Some attempts (Ma et al., 2017; Zhao et al., 2017; Zhang et al., 2018) applied Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for traffic forecasting.”
• Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting (2020, methodology): “Recent years, deep learning methods have shown promising results in dynamic prediction over spatial-temporal traffic flows data [1, 12, 5].”
• Deep Learning for Spatio-Temporal Data Mining: A Survey (2019, methodology): “Application domains Related works Transportation [177], [187], [116], [31], [29], [6], [32], [127], [53], [112], [26], [105], [166], [82], [23], [66], [108], [126], [81], [139], [78], [128], [146], [148], [72], [98], [189], [22], [24], [99], [96], [16], [97], [85], [15], [164], [165], [95], [140], [”
• Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting (2021, background): “In particular, the proposals [21], [22], [23], [26], [32], [33], [34], [35] partition the region into 2D or 3D cells,”