Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction

Abstract

Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing popularity of taxi requesting services such as Uber and Didi Chuxing (in China), we are able to collect large-scale taxi demand data continuously. How to utilize such big data to improve the demand prediction is an interesting and critical real-world problem. Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations. Recent advances in deep learning have shown superior performance on traditionally challenging tasks such as image classification by learning the complex features and correlations from large-scale data. This breakthrough has inspired researchers to explore deep learning techniques on traffic prediction problems. However, existing methods on traffic prediction have only considered spatial relation (e.g., using CNN) or temporal relation (e.g., using LSTM) independently. We propose a Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations. Specifically, our proposed model consists of three views: temporal view (modeling correlations between future demand values with near time points via LSTM), spatial view (modeling local spatial correlation via local CNN), and semantic view (modeling correlations among regions sharing similar temporal patterns). Experiments on large-scale real taxi demand data demonstrate effectiveness of our approach over state-of-the-art methods.

AAAI 2018 paper

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• XGBoost: A Scalable Tree Boosting System
• LINE: Large-scale Information Network Embedding

Cited by in corpus (76)

• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• Joint predictions of multi-modal ride-hailing demands: a deep multi-task multigraph learning-based approach
• GMAN: A Graph Multi-Attention Network for Traffic Prediction
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Incorporating dynamicity of transportation network with multi-weight traffic graph convolutional network for traffic forecasting
• Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
• Idle Vehicle Relocation Strategy through Deep Learning for Shared Autonomous Electric Vehicle System Optimization
• Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference
• Spatial-temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network
• Auxiliary-task Based Deep Reinforcement Learning for Participant Selection Problem in Mobile Crowdsourcing
• Coupled Layer-wise Graph Convolution for Transportation Demand Prediction
• STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
• Localized convolutional neural networks for geospatial wind forecasting
• HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting
• Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction
• A Trusted and Privacy-preserving Internet of Mobile Energy
• Spatial-Temporal Dynamic Graph Attention Networks for Ride-hailing Demand Prediction
• Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework
• Urban Anomaly Analytics: Description, Detection, and Prediction
• "How do urban incidents affect traffic speed?" A Deep Graph Convolutional Network for Incident-driven Traffic Speed Prediction
• StressNet: Deep Learning to Predict Stress With Fracture Propagation in Brittle Materials
• Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting
• Crowd-sensing Enhanced Parking Patrol using Trajectories of Sharing Bikes
• Spatio-Temporal Hybrid Graph Convolutional Network for Traffic Forecasting in Telecommunication Networks
• Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction
• Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
• Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search Based on Reinforcement Learning and Existing Research Results
• Revisiting Convolutional Neural Networks for Citywide Crowd Flow Analytics
• Knowledge Adaption for Demand Prediction based on Multi-task Memory Neural Network
• Revisiting Flow Information for Traffic Prediction
• Demand Forecasting from Spatiotemporal Data with Graph Networks and Temporal-Guided Embedding
• Deep-MAPS: Machine Learning based Mobile Air Pollution Sensing
• TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning
• EasiCSDeep: A deep learning model for Cervical Spondylosis Identification using surface electromyography signal
• Mapping road safety features from streetview imagery: A deep learning approach
• Data-Driven Short-Term Voltage Stability Assessment Based on Spatial-Temporal Graph Convolutional Network
• Correlative Channel-Aware Fusion for Multi-View Time Series Classification
• GraphTCN: Spatio-Temporal Interaction Modeling for Human Trajectory Prediction
• Building Effective Large-Scale Traffic State Prediction System: Traffic4cast Challenge Solution
• SOUP: Spatial-Temporal Demand Forecasting and Competitive Supply
• Deep Reinforcement Learning with Spatio-temporal Traffic Forecasting for Data-Driven Base Station Sleep Control
• Predicting Urban Dispersal Events: A Two-Stage Framework through Deep Survival Analysis on Mobility Data
• Long-Short Term Spatiotemporal Tensor Prediction for Passenger Flow Profile
• A Survey on Spatial and Spatiotemporal Prediction Methods
• Real-Time Forecasting of Dockless Scooter-Sharing Demand: A Spatio-Temporal Multi-Graph Transformer Approach
• Learning Spatiotemporal Features of Ride-sourcing Services with Fusion Convolutional Network
• Taxi Demand-Supply Forecasting: Impact of Spatial Partitioning on the Performance of Neural Networks
• Urban flows prediction from spatial-temporal data using machine learning: A survey
• How to Eliminate Detour Behaviors in E-hailing? Real-time Detecting and Time-dependent Pricing
• A Comparative Study on Basic Elements of Deep Learning Models for Spatial-Temporal Traffic Forecasting
• An Effective Dynamic Spatio-temporal Framework with Multi-Source Information for Traffic Prediction
• Event Ticket Price Prediction with Deep Neural Network on Spatial-Temporal Sparse Data
• A Comparative Study of Using Spatial-Temporal Graph Convolutional Networks for Predicting Availability in Bike Sharing Schemes
• GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention
• Quantifying Uncertainty in Deep Spatiotemporal Forecasting
• Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction
• TLab: Traffic Map Movie Forecasting Based on HR-NET
• ALCNN: Attention-based Model for Fine-grained Demand Inference of Dock-less Shared Bike in New Cities
• Position-Aware Convolutional Networks for Traffic Prediction
• Graph Deep Factors for Forecasting
• Using NASA Satellite Data Sources and Geometric Deep Learning to Uncover Hidden Patterns in COVID-19 Clinical Severity
• Modeling vehicular mobility patterns using recurrent neural networks
• Mix and Match: Markov Chains & Mixing Times for Matching in Rideshare
• STDI-Net: Spatial-Temporal Network with Dynamic Interval Mapping for Bike Sharing Demand Prediction
• STR-GODEs: Spatial-Temporal-Ridership Graph ODEs for Metro Ridership Prediction
• Demand Prediction for Electric Vehicle Sharing
• Attention-based Supply-Demand Prediction for Autonomous Vehicles
• Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs
• Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
• PPtaxi: Non-stop Package Delivery via Multi-hop Ridesharing
• Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph
• Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics