DeepSTCL: A Deep Spatio-temporal ConvLSTM for Travel Demand Prediction

  title={DeepSTCL: A Deep Spatio-temporal ConvLSTM for Travel Demand Prediction},
  author={Dongjie Wang and Yan Yang and Shangming Ning},
  journal={2018 International Joint Conference on Neural Networks (IJCNN)},
Urban resource scheduling is an important part of the development of a smart city, and transportation resources are the main components of urban resources. [] Key Method In order to improve the performance, deep learning is used to assist prediction. But most of the deep learning methods only utilize temporal dependence or spatial dependence of data in the forecasting process. To address these limitations, a novel deep learning traffic demand forecasting framework which based on Deep Spatio-Temporal ConvLSTM…

Demand Forecasting of Online Car-Hailing with Combining LSTM + Attention Approaches

Compared with other forecasting models, the results show that the short-term demand forecasting model LSTM + Attention outperforms other models and verify that the proposed model can support advanced scheduling and dynamic pricing for online car-hailing.

Short-Term Traffic Prediction With Deep Neural Networks: A Survey

This study surveys recent STTP studies applying deep networks from four perspectives, and summarizes input data representation methods according to the number and type of spatial and temporal dependencies involved.

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Critically analyzing the state of the art in what refers to the use of Deep Learning for Intelligent Transportation Systems reveals that Deep Learning could not be the best modeling technique for every case, which unveils some caveats unconsidered to date.

Examine the Prediction Error of Ride-Hailing Travel Demands with Various Ignored Sparse Demand Effects

It is found that increasing the minimum demand threshold to delete more sparse data improves the overall prediction accuracy to a certain extent, but the spatiotemporal coverage of the data is also significantly reduced.

Ride Hailing Service Demand Forecast by Integrating Convolutional and Recurrent Neural Networks

This study constructs a deep learning based model for ride hailing demand forecast aiming to achieve high accuracies in solving similar problems and demonstrates that the proposed model outperforms the CNN and LSTM models up to 18.41 % in RMSE and 22.65% in R values.

Self-Attention ConvLSTM for Spatiotemporal Forecasting of Short-Term Online Car-Hailing Demand

The experimental results showed that the proposed self-attention mechanism in convolutional long short-term memory performed better than the existing models, and including spatiotemporal information in images would perform better predictions than including spatial information in time-series pixels.

TA-STAN: A Deep Spatial-Temporal Attention Learning Framework for Regional Traffic Accident Risk Prediction

A deep learning framework to predict regional Traffic Accident risk that utilizes a Spatial-Temporal Attention Network (named TA-STAN) that outperforms 6 baseline models in 3 evaluation metrics and can reasonably interpret the actual meaning of attention weights, which plays a crucial role in the model.


This research paper presents approaches to analyse spatial temporal patterns existing in networks and goes on to use a machine learning model that integrates both spatial and temporal dependency in traffic flow prediction, which can accurately predict traffic flow up to 15 minutes in advance and accuracy results obtained outperform other classical traffic prediction methods.



Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction

This work designs an end-to-end structure of ST-ResNet, a deep-learning-based approach to collectively forecast the inflow and outflow of crowds in each and every region of a city, based on unique properties of spatio-temporal data.

Traffic Flow Prediction With Big Data: A Deep Learning Approach

A novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently and is applied for the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction.

DNN-based prediction model for spatio-temporal data

A Deep-learning-based prediction model for Spatio-Temporal data (DeepST), which is comprised of two components: spatio-temporal and global, and built on a real-time crowd flow forecasting system called UrbanFlow1.

DeepTFP: Mobile Time Series Data Analytics based Traffic Flow Prediction

This study proposes a deep learning based prediction algorithm, DeepTFP, to collectively predict the traffic flow on each and every traffic road of a city using three deep residual neural networks to model temporal closeness, period, and trend properties of traffic flow.

Poster: DeepTFP: Mobile Time Series Data Analytics based Traffic Flow Prediction

A deep learning based prediction algorithm, DeepTFP, is proposed to collectively predict the traffic flow on each and every traffic road of a city using three deep residual neural networks to model temporal closeness, period, and trend properties of traffic flow.

DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data

This study introduces a brand-new data-driven precipitation prediction model called DeepRain, which predicts the amount of rainfall from weather radar data, which is three-dimensional and four-channel data, using convolutional LSTM (ConvLSTM).

Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

This paper proposes the convolutional LSTM (ConvLSTM) and uses it to build an end-to-end trainable model for the precipitation nowcasting problem and shows that it captures spatiotemporal correlations better and consistently outperforms FC-L STM and the state-of-the-art operational ROVER algorithm.

Multi-task learning of time series and its application to the travel demand

A support vector regression model is developed for joint learning of mutually dependent time series and it is the regularization-based multi-task learning previously developed for the classification case and extended to time series.

A multi-level clustering approach for forecasting taxi travel demand

This paper uses time-series modeling to forecast taxi travel demand, in the context of a mobile application-based taxi hailing service, and employs a multi-level clustering technique where demand is aggregated over neighboring cells/geohashes to improve the model performance.