[1]SUN Yiwen,ZHANG Yichi,CHEN Jiaqi.Traffic accident risk prediction based on causal intervention and dynamic graph learning[J].CAAI Transactions on Intelligent Systems,2026,21(4):1030-1043.[doi:10.11992/tis.202511031]
Copy

Traffic accident risk prediction based on causal intervention and dynamic graph learning

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 4 Page number: 1030-1043 Column: 学术论文—智能系统 Public date: 2026-07-05
Title:
Traffic accident risk prediction based on causal intervention and dynamic graph learning
Author(s):
SUN Yiwen1;  ZHANG Yichi2;  CHEN Jiaqi3
1. Institute for Artificial Intelligence, Peking University, Beijing 100871, China;
2. Baidu Online Network Technology Co., Ltd., Beijing 100193;
3. School of Information Engineering, Minzu University of China, Beijing 100081, China
Keywords:
accident prevention; causal intervention; deep learning; forecasting; risk prediction; graph neural networks; time series; long short-term memory; traffic control; convolutional neural networks
CLC:
TP391.4; U491.31
DOI:
10.11992/tis.202511031
Abstract:
To address the limited generalization ability and inadequate spatiotemporal dependency modeling in urban traffic accident risk prediction, this paper proposes a traffic accident risk forecasting network based on causal intervention and dynamic graph learning. Within an encoder-decoder framework, an input-gating module is designed to fuse multi-period accident signals with external covariates. A dynamic graph learning module is further introduced to adaptively characterize time-varying spatial dependencies among nodes via a channel-attention mechanism, while graph convolution and gated recurrent units are jointly employed to model spatiotemporal evolution patterns. To further improve forecasting stability, a transition-bridge module is incorporated to map historical spatiotemporal states to future states, thereby mitigating error accumulation in multi-step prediction. Meanwhile, a front-door-criterion-based causal intervention mechanism is adopted to sever confounding paths at the feature level, enhancing model robustness and transferability. Experiments on two public datasets, NYC and Chicago, demonstrate that CIDGNet outperforms four baseline models in terms of root mean square error, recall, and mean average precision. Ablation studies further verify the contributions of key components-including the dynamic graph, input gate, and transition bridge-to performance gains, confirming the effectiveness of causal intervention and dynamic graph learning for complex spatiotemporal forecasting tasks.
References:
[1] DOYCHEVA K. Global status report on road safety 2018[M]. [S. l. ]: World Health Organization, 2019.
[2] JOSHUA S C, GARBER N J. Estimating truck accident rate and involvements using linear and Poisson regression models[J]. Transportation planning and technology, 1990, 15(1): 41-58
[3] 陈昭明, 徐文远. 基于负二项分布的高速公路交通事故影响因素分析[J]. 交通信息与安全, 2022, 40(1): 28-35 CHEN Zhaoming, XU Wenyuan. An analysis of factors influencing freeway crashes with a negative binomial model[J]. Journal of transport information and safety, 2022, 40(1): 28-35
[4] IHUEZE C C, ONWURAH U O. Road traffic accidents prediction modelling: an analysis of Anambra State, Nigeria[J]. Accident analysis & prevention, 2018, 112: 21-29
[5] LI Wei, ZHAO Xujian, LIU Shiyu. Traffic accident prediction based on multivariable grey model[J]. Information, 2020, 11(4): 184
[6] 马永杰, 程时升, 马芸婷, 等. 卷积神经网络及其在智能交通系统中的应用综述[J]. 交通运输工程学报, 2021, 21(4): 48-71 MA Yongjie, CHENG Shisheng, MA Yunting, et al. Review of convolutional neural network and its application in intelligent transportation system[J]. Journal of traffic and transportation engineering, 2021, 21(4): 48-71
[7] DONG Ni, HUANG Helai, ZHENG Liang. Support vector machine in crash prediction at the level of traffic analysis zones: Assessing the spatial proximity effects[J]. Accident analysis & prevention, 2015, 82: 192-198
[8] 冯宁, 郭晟楠, 宋超, 等. 面向交通流量预测的多组件时空图卷积网络[J]. 软件学报, 2019, 30(3): 759-769 FENG Ning, GUO Shengnan, SONG Chao, et al. Multi-component spatial-temporal graph convolution networks for traffic flow forecasting[J]. Journal of software, 2019, 30(3): 759-769
[9] PARSA A B, MOVAHEDI A, TAGHIPOUR H, et al. Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis[J]. Accident analysis & prevention, 2020, 136: 105405
[10] LIN Lei, WANG Qian, SADEK A W. A novel variable selection method based on frequent pattern tree for real-time traffic accident risk prediction[J]. Transportation Research Part C: Emerging Technologies, 2015, 55: 444-459
[11] DOYCHEVA K. GPU-enabled real-time pavement distress detection based on computer vision and deep learning[D]. Bochum: Ruhr University Bochum, 2020.
[12] FAISAL M, ALBOGAMY F, ELGIBREEN H, et al. Deep learning and computer vision for estimating date fruits type, maturity level, and weight[J]. IEEE access, 2020, 8: 206770-206782
[13] GUPTA M, VARMA V, DAMANI S, et al. Compression of deep learning models for NLP[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. Virtual Event: ACM, 2020: 3507-3508.
[14] 户佐安, 邓锦程, 韩金丽, 等. 图神经网络在交通预测中的应用综述[J]. 交通运输工程学报, 2023, 23(5): 39-61 HU Zuoan, DENG Jincheng, HAN Jinli, et al. Review on application of graph neural network in traffic prediction[J]. Journal of traffic and transportation engineering, 2023, 23(5): 39-61
[15] 谷振宇, 陈聪, 郑家佳, 等. 基于时空图卷积循环神经网络的交通流预测[J]. 控制与决策, 2022, 37(3): 645-653 GU Zhenyu, CHEN Cong, ZHENG Jiajia, et al. Traffic flow prediction based on STG-CRNN[J]. Control and decision, 2022, 37(3): 645-653
[16] REN Honglei, SONG You, WANG Jingwen, et al. A deep learning approach to the citywide traffic accident risk prediction[C]//2018 21st International Conference on Intelligent Transportation Systems. Maui: IEEE, 2018: 3346-3351.
[17] CHEN Quanjun, SONG Xuan, YAMADA H, et al. Learning deep representation from big and heterogeneous data for traffic accident inference[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Phoenix: ACM, 2016: 338-344.
[18] BAO Jie, LIU Pan, UKKUSURI S V. A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data[J]. Accident analysis & prevention, 2019, 122: 239-254
[19] YUAN Zhuoning, ZHOU Xun, YANG Tianbao. Hetero-ConvLSTM: a deep learning approach to traffic accident prediction on heterogeneous spatio-temporal data[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London: ACM, 2018: 984-992.
[20] 赵文竹, 袁冠, 张艳梅, 等. 多视角融合的时空动态GCN城市交通流量预测[J]. 软件学报, 2024, 35(4): 1751-1773 ZHAO Wenzhu, YUAN Guan, ZHANG Yanmei, et al. Multi-view fused spatial-temporal dynamic GCN for urban traffic flow prediction[J]. Journal of software, 2024, 35(4): 1751-1773
[21] 包银鑫, 曹阳, 施佺. 基于改进时空残差卷积神经网络的城市路网短时交通流预测[J]. 计算机应用, 2022(1): 258-264 BAO Yinxin, CAO Yang, SHI Quan. Improved spatio-temporal residual convolutional neural network for urban road network short-term traffic flow prediction[J]. Journal of computer applications, 2022(1): 258-264
[22] ZHOU Zhengyang, WANG Yang, XIE Xike, et al. RiskOracle: a minute-level citywide traffic accident forecasting framework[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York: AAAI, 2020, 34(1): 1258-1265.
[23] WANG Beibei, LIN Youfang, GUO Shengnan, et al. GSNet: learning spatial-temporal correlations from geographical and semantic aspects for traffic accident risk forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Virtual Event: AAAI, 2021, 35(5): 4402-4409.
[24] BHARDWAJ N, PAL A, BHUMIKA, et al. Adaptive context based road accident risk prediction using spatio-temporal deep learning[J]. IEEE transactions on artificial intelligence, 2024, 5(6): 2872-2883
[25] TRIRAT P, YOON S, LEE J G. MG-TAR: multi-view graph convolutional networks for traffic accident risk prediction[J]. IEEE transactions on intelligent transportation systems, 2023, 24(4): 3779-3794.
[26] ZHANG Jiaxun, GUAN Yanchen, WAGN Chengyue, et al. LATTE: a real-time lightweight attention-based traffic accident anticipation engine[J]. Information fusion, 2025, 122: 103173
[27] HU Junjie, BAI Jun, YANG Jiayu, et al. Crash risk prediction using sparse collision data: Granger causal inference and graph convolutional network approaches[J]. Expert systems with applications, 2025, 259: 125315
[28] CHEN Minxiao, YUAN Haitao, JIANG Nan, et al. S-MGHSTN: towards an effective streaming traffic accident risk prediction framework[J]. IEEE transactions on knowledge and data engineering, 2025, 37(7): 4285-4298
[29] ZOU Guojian, ZHOU Zhiyong, WEIBEL R, et al. Multi-graph spatio-temporal network for traffic accident risk forecasting[J]. Pattern recognition, 2026, 172: 112784
[30] 邹慧琪, 史彬泽, 宋凌云, 等. 基于图神经网络的复杂时空数据挖掘方法综述[J]. 软件学报, 2025, 36(4): 1811-1843 ZOU Huiqi, SHI Binze, SONG Lingyun, et al. Survey on complex spatio-temporal data mining methods based on graph neural network[J]. Journal of software, 2025, 36(4): 1811-1843
[31] 吴永庆, 姜正宇. 基于解耦动态时空卷积循环网络的交通流预测[J]. 计算机工程, 2026, 52(5): 160-171 WU Yongqing, JIANG Zhengyu. Traffic flow prediction based on decoupled dynamic spatio-temporal convolutional recurrent network[J]. Computer engineering, 2026, 52(5): 160-171
[32] LIU Chang, SUN Xinwei, WANG Jindong, et al. Learning causal semantic representation for out-of-distribution prediction[C]//Neural Information Processing Systems. Virtual Event: NeurIPS, 2020.
[33] YAN Haoyang, MA Xiaolei, PU Ziyuan. Learning dynamic and hierarchical traffic spatiotemporal features with transformer[J]. IEEE transactions on intelligent transportation systems, 2022, 23(11): 22386-22399
[34] WANG Yuhu, FANG Shen, ZHANG Chunxia, et al. TVGCN: Time-variant graph convolutional network for traffic forecasting[J]. Neurocomputing, 2022, 471: 118-129
[35] PEARL J. Causality[M]. Cambridge: Cambridge University Press, 2009.
[36] LI Yaguang, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[EB/OL]. (2017-07-06)[2025-11-24]. https://arxiv.org/abs/1707.01926.
[37] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems 30. Long Beach: NeurIPS, 2017: 5998-6008.
[38] LIU Runpeng, SHIN S Y. A review of traffic flow prediction methods in intelligent transportation system construction[J]. Applied sciences, 2025, 15(7): 3866
[39] CHEN Tianqi, GUESTRIN C. XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016: 785-794.
[40] RUMELLHART D E. Learning internal representations by error propagation[J]. Parallel distributed processing: explorations in the microstructure of cognition, 1986, 1: 319-362
[41] CHUNG J, GULCEHRE C, CHO K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL]. (2014-12-11)[2025-11-24]. https://arxiv.org/abs/1412.3555.
[42] SHI Xingjian, CHEN Zhourong, WANG Hao, et al. Convolutional LSTM Network: a machine learning approach for precipitation nowcasting[C]//Proceedings of the 29th International Conference on Neural Information Processing Systems. Cambridge: ACM, 2015: 802-810.
[43] WU Zonghan, PAN Shirui, LONG Guodong, et al. Graph WaveNet for deep spatial-temporal graph modeling[EB/OL]. (2019-06-31)[2025-11-24]. https://arxiv.org/abs/1906.00121.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems