Jiangsu Key Laboratory of Urban ITS, Southeast University, Si Pai Lou #2, Nanjing, 210096, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Si Pai Lou #2, Nanjing, 210096, China; Lyles School of Civil Engineering, Purdue University, 550 Stadium Mall Drive, West Lafayette, 47906 IN, United States.
Jiangsu Key Laboratory of Urban ITS, Southeast University, Si Pai Lou #2, Nanjing, 210096, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Si Pai Lou #2, Nanjing, 210096, China.
Accid Anal Prev. 2019 Jan;122:239-254. doi: 10.1016/j.aap.2018.10.015. Epub 2018 Nov 1.
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, and four state-of-the-art machine-learning models 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 higher prediction accuracy rate and lower false alarm rate. 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 crash risk prediction tasks.
本研究的主要目的是探讨深度学习方法如何利用多源数据集助力城市短期事故风险预测。本研究以纽约市曼哈顿的数据为例说明了该方法的实施过程。收集了以下多个数据集：事故数据、大规模出租车 GPS 数据、道路网络属性、土地利用特征、人口数据和天气数据。提出了一种时空卷积长短时记忆网络（STCL-Net）来预测城市短期事故风险。共进行了 9 项预测任务，并进行了比较，包括每周、每日和每小时模型，分别有 8×3、15×5 和 30×10 个网格。结果表明，随着预测任务时空分辨率的增加，预测模型的性能下降。此外，选择了四个常用的计量经济学模型和四个最先进的机器学习模型作为基准方法，与所提出的 STCL-Net 进行了所有事故风险预测任务的比较。对比分析表明，在不同的事故风险预测任务中，所提出的 STCL-Net 通常优于基准方法，具有更高的预测准确率和更低的误报率。结果验证了所提出的时空深度学习方法在捕捉城市短期事故风险预测的时空特征方面表现更好。此外，对比分析还表明，在每周事故风险预测任务中，计量经济学模型比机器学习模型表现更好，而在每日事故风险预测任务中，它们的表现则不如机器学习模型。研究结果可能有助于交通安全工程师为不同的事故风险预测任务选择合适的方法。
