01698147

Component

The primary objective of this study is to investigate how the deep learning approach contributes to citywide short-term crash risk prediction by leveraging multi-source datasets. This study uses data collected from Manhattan in New York City to illustrate the procedure. The following multiple datasets are collected: crash data, large-scale taxi GPS data, road network attributes, land use features, population data and weather data. A spatiotemporal convolutional long short-term memory network (STCL-Net) is proposed for predicting the citywide short-term crash risk. A total of nine prediction tasks are conducted and compared, including weekly, daily and hourly models with 8×3, 15×5 and 30×10 grids, respectively. The results suggest that the prediction performance of the proposed model decreases as the spatiotemporal resolution of prediction task increases. Moreover, four commonly-used econometric models (ARIMA, Random-parameter model, Random-effects model and GWR), and four state-of-the-art machine-learning models (CNN, LSTM, ANN, and GBRT) are selected as benchmark methods to compare with the proposed STCL-Net for all the crash risk prediction tasks. The comparative analyses suggest that in general the proposed STCL-Net outperforms the benchmark methods for different crash risk prediction tasks in terms of lower MSE, MAE and MAPE. The results verify that the proposed spatiotemporal deep learning approach performs better at capturing the spatiotemporal characteristics for the citywide short-term crash risk prediction. In addition, the comparative analyses also reveal that econometric models perform better than machine-learning models in weekly crash risk prediction tasks, while they exhibit worse results than machine-learning models in daily crash risk prediction tasks. The results can potentially guide transportation safety engineers to select appropriate methods for different citywide crash risk prediction tasks.

This paper was sponsored by TRB committee ANB20 Standing Committee on Safety Data, Analysis and Evaluation.

19-04439

English

8p

2019

Transportation Research Board 98th Annual Meeting

Digital/other

Figures; References (19) ; Tables

Crash causes; Crash data; Crash risk forecasting; Data analysis; Econometrics; Machine learning; Mathematical prediction; Urban highways

Manhattan (New York, New York)

Data and Information Technology; Highways; Safety and Human Factors

Transportation Research Board Annual Meeting 2019 Paper #19-04439

TRIS, TRB, ATRI

Dec 7 2018 9:47AM