TLab: Second Place Solution Towards Traffic4cast 2020 Competition

The problem of the effective prediction for large-scale spatio-temporal traffic data has long haunted researchers in the field of intelligent transportation. Limited by the quantity of data, citywide traffic state prediction was seldom achieved. Hence the complex urban transportation system of an entire city cannot be truly understood. Thanks to the efforts of organizations like IARAI, the massive open data provided by them has made the research possible. In our 2020 Competition solution, we further design multiple variants based on HR-NET and UNet. Through feature engineering, the hand-crafted features are input into the model in a form of channels. It is worth noting that, to learn the inherent attributes of geographical locations, we proposed a novel method called geo-embedding, which contributes to significant improvement in the accuracy of the model. In addition, we explored the influence of the selection of activation functions and optimizers, as well as tricks during model training on the model performance. In terms of prediction accuracy, our solution has won 2nd place in NeurIPS 2020, Traffic4cast Challenge.

[1]  Jieping Ye,et al.  Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting , 2019, AAAI.

[2]  Jieping Ye,et al.  Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction , 2018, AAAI.

[3]  Yang Liu,et al.  Building Personalized Transportation Model for Online Taxi-Hailing Demand Prediction , 2020, IEEE Transactions on Cybernetics.

[4]  S. Dwivedi,et al.  Obesity May Be Bad: Compressed Convolutional Networks for Biomedical Image Segmentation , 2020 .

[5]  Li Li,et al.  Using LSTM and GRU neural network methods for traffic flow prediction , 2016, 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC).

[6]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[7]  Ridha Soua,et al.  Improving Traffic Flow Prediction With Weather Information in Connected Cars: A Deep Learning Approach , 2016, IEEE Transactions on Vehicular Technology.

[8]  Yang Zhao,et al.  Deep High-Resolution Representation Learning for Visual Recognition , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Junbo Zhang,et al.  Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning , 2019, KDD.

[10]  Cyrus Shahabi,et al.  Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting , 2017, ICLR.

[11]  Xiqun Chen,et al.  Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach , 2017, ArXiv.

[12]  Yike Guo,et al.  Deep Sequence Learning with Auxiliary Information for Traffic Prediction , 2018, KDD.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[15]  Raia Hadsell,et al.  The surprising efficiency of framing geo-spatial time series forecasting as a video prediction task - Insights from the IARAI Traffic4cast Competition at NeurIPS 2019 , 2020, NeurIPS.

[16]  James Demmel,et al.  Large Batch Optimization for Deep Learning: Training BERT in 76 minutes , 2019, ICLR.

[17]  Yang Liu,et al.  DeepPF: A deep learning based architecture for metro passenger flow prediction , 2019, Transportation Research Part C: Emerging Technologies.

[18]  Ripul Ghosh,et al.  A spatio-temporal deep learning approach for human action recognition in infrared videos , 2018, Optical Engineering + Applications.

[19]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.