Abstract
In harsh climates, highway icing poses a hazard to traffic safety and increases road maintenance costs. It is of great significance to predict when the highway icing may occur and take a preventive plan. However, there are few studies on highway icing time prediction due to the scarcity and complexity of data. In this study, variables of icing temperature, friction, ice percentage, road surface temperature, water film height, saline concentration, and road condition were collected by road sensors distributed on a highway in China. A large-scale time series highway surface information dataset called HighwayIce is formed. Furthermore, a deep learning approach called IceAlarm, composed of long short-term memory neural network (LSTM), multilayer perceptron (MLP), and residual connection, has been developed to predict when the highway will ice. The LSTM is used to process dynamic variables, the MLP is used to process static variables, and the fully-connected layers with residual connections are used to make a deep fusion. The experimental results show that the average mean absolute error before icing using the IceAlarm model is about 6 min and outperforms all baseline models. The HighwayIce dataset and IceAlarm model can help improve the prediction accuracy and efficiency of forecasting real-world road icing time, therefore reducing the impact of icy road conditions on traffic.
Similar content being viewed by others
References
Xin J, Xu X. The main meteorological disasters in China and the countermeasures. J Catastrophology, 2007, 22: 85–89
Wallman C G, Åström H. Friction measurement methods and the correlation between road friction and traffic safety: A literature review. Swedish National Road and Transport Research Institute (VTI), 2001
Lu T, Zhang Y, Gao J. Research on highway operation safety management system under ice and snow weather. Sci Tech Innovat Herald, 2009, 1: 87–87
Shenton M D, Nichols S J, Bray J P, et al. The effects of road de-icing salts on water quality and macroinvertebrates in australian alpine areas. Arch Environ Contam Toxicol, 2022, 82: 266–280
Bang S S, Johnston D. Environmental effects of sodium acetate/formate deicer, ice shear? Arch Environ Contamination Toxicol, 1998, 35: 580–587
Ma H, Yu H, Li C, et al. Freeze-thaw damage to high-performance concrete with synthetic fibre and fly ash due to ethylene glycol deicer. Construction Building Mater, 2018, 187: 197–204
Li Z X, Shi X L, Cao J D, et al. CPSO-XGBoost segmented regression model for asphalt pavement deflection basin area prediction. Sci China Tech Sci, 2022, 65: 1470–1481
Xiang Y, Sheng J B, Wang L, et al. Research progresses on equipment technologies used in safety inspection, repair, and reinforcement for deepwater dams. Sci China Tech Sci, 2022, 65: 1059–1071
Crevier L P, Delage Y. METRo: A new model for road-condition forecasting in Canada. J Appl Meteor, 2001, 40: 2026–2037
Hu J, Lin Z, Cheng T. Research progress on temperature prediction method for road icing. Sci Tech Eng, 2020, 20: 1–6
Dan H C, He L H, Zou J F, et al. Laboratory study on the adhesive properties of ice to the asphalt pavement of highway. Cold Regions Sci Tech, 2014, 104: 7–13
Matić B, Tepić J, Sremac S, et al. Development and evaluation of the model for the surface pavement temperature prediction. Metalurgija, 2012, 51: 329–332
Christison J, Anderson K. The response of asphalt pavements to low temperature climatic environments. In: Proceedings of Presented at the Third International Conference on the Structural Design of Asphalt Pavements. London, 1972
Fujimoto A, Tokunaga R A, Kiriishi M, et al. A road surface freezing model using heat, water and salt balance and its validation by field experiments. Cold Regions Sci Tech, 2014, 106–107: 1–10
Shao J. Application of an artificial neural network to improve short-term road ice forecasts. Expert Syst Appl, 1998, 14: 471–482
Li J. A combination of PSO and SVM for road icing forecast. J Comput, 2010, 5: 1372–1379
Klein-Paste A, Wåhlin J. Wet pavement anti-icing—A physical mechanism. Cold Regions Sci Tech, 2013, 96: 1–7
Liu W, Rao Z. Road icing warning system based on support vector classification. In: Proceedings of IOP Conference Series: Earth and Environmental Science. IOP Publishing, Boston, 2020. 052071
Zhang C, Bengio S, Hardt M, et al. Understanding deep learning (still) requires rethinking generalization. Commun ACM, 2021, 64: 107–115
Lim B, Zohren S. Time-series forecasting with deep learning: A survey. Phil Trans R Soc A, 2021, 379: 20200209
Wang X, Wang R, Shu G Q, et al. Energy management strategy for hybrid electric vehicle integrated with waste heat recovery system based on deep reinforcement learning. Sci China Tech Sci, 2022, 65: 713–725
Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science, 2006, 313: 504–507
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, 2016. 770–778
Sesti N, Garau-Luis J J, Crawley E, et al. Integrating lstms and gnns for covid-19 forecasting. arXiv: 2108.10052
Elman J L. Finding structure in time. Cogn Sci, 1990, 14: 179–211
Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9: 1735–1780
Zhang W J, Qin J, Mei F, et al. Short-term power load forecasting using integrated methods based on long short-term memory. Sci China Tech Sci, 2020, 63: 614–624
Jiang Y H, Yu Y F, Huang J Q, et al. Li-ion battery temperature estimation based on recurrent neural networks. Sci China Tech Sci, 2021, 64: 1335–1344
Xu X, Qin F, Zhao W, et al. Anomaly detection with GRU based Bi-autoencoder for industrial multimode process. Int J Control Autom Syst, 2022, 20: 1827–1840
Pei J Z, Su Y X, Zhang D H, et al. Velocity forecasts using a combined deep learning model in hybrid electric vehicles with V2V and V2I communication. Sci China Tech Sci, 2020, 63: 55–64
Huang C Y, Li L, Fang S N, et al. Energy saving performance improvement of intelligent connected PHEVs via NN-based lane change decision. Sci China Tech Sci, 2021, 64: 1203–1211
Yang T T, Tong C. Real-time detection network for tiny traffic sign using multi-scale attention module. Sci China Tech Sci, 2022, 65: 396–406
Graves A, Mohamed A R, Hinton G. Speech recognition with deep recurrent neural networks. In: Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, IEEE, 2013. 6645–6649
Zhang Z, Takanobu R, Zhu Q, et al. Recent advances and challenges in task-oriented dialog systems. Sci China Tech Sci, 2020, 63: 2011–2027
Kangas M, Heikinheimo M, Hippi M. RoadSurf: A modelling system for predicting road weather and road surface conditions. Met Apps, 2015, 22: 544–553
Sun F K, Lang C, Boning D. Adjusting for autocorrelated errors in neural networks for time series. Adv Neural Infor Process Syst, 2021, 34: 29806–29819
Pu Z, Liu C, Shi X, et al. Road surface friction prediction using long short-term memory neural network based on historical data. J Intelligent Transpation Syst, 2022, 26: 34–45
Pu Z, Cui Z, Wang S, et al. Time-aware gated recurrent unit networks for forecasting road surface friction using historical data with missing values. IET Intelligent Transp Syst, 2020, 14: 213–219
Liu W, Rao Z. Pavement icing forecasting based on long short-term memory network. In: Proceedings of IOP Conference Series: Earth and Environmental Science. IOP Publishing, 2020. 052070
Hou Y, Zhao S, Xue Z, et al. Intelligent analysis of subbase strain based on a long-term comprehensive monitoring. Trans Geotech, 2022, 33: 100720
Tan Q, Ma A J, Deng H, et al. A hybrid residual network and long short-term memory method for peptic ulcer bleeding mortality prediction. In: Proceedings of AMIA Annual Symposium. American Medical Informatics Association, 2018. 998
Shao J, Lister P J. An automated nowcasting model of road surface temperature and state for winter road maintenance. J Appl Meteor, 1996, 35: 1352–1361
Leontjeva A, Kuzovkin I. Combining static and dynamic features for multivariate sequence classification. In: Proceedings of 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA). IEEE, 2016. 21–30
Han X, Dasgupta S, Ghosh J. Simultaneously reconciled quantile forecasting of hierarchically related time series. In: Proceedings of International Conference on Artificial Intelligence and Statistics. PMLR, 2021. 190–198
Mahura A, Petersen C, Sass B H. Road icing conditions in Denmark. Danish Meteorological Institute, 2008
Wan X, Lai Y, Wang C. Experimental study on the freezing temperatures of saline silty soils. Permafrost Periglac Process, 2015, 26: 175–187
Kuroiwa D. The kinetic friction on snow and ice. J Glaciol, 1977, 19: 141–152
Shu S, Xiong S, Chen Y, et al. Warning model of road surface icing of expressway in Hubei province. Meteorology, 2019, 45: 1589–1599
Cho K, Van Merriënboer B, Bahdanau D, et al. On the properties of neural machine translation: Encoder-decoder approaches. arXiv: 1409.1259
Park E L, Hagiwara M, Milajevs D, et al. Proceedings of workshop for nlp open source software (nlp-oss). In: Proceedings of the Workshop for NLP Open Source Software (NLP-OSS). Melbourne, 2018
Shewalkar A, Nyavanandi D, Ludwig S A. Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU. J Artif Intell Soft Comput Res, 2019, 9: 235–245
Zeyer A, Bahar P, Irie K, et al. A comparison of transformer and lstm encoder decoder models for ASR. In: Proceedings of 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Sentosa, IEEE, 2019. 8–15
Yu W, Guo M, Lai Y, et al. Icing problems on road and mitigation methods in China. In: Proceedings of Current Practices in Cold Regions Engineering. Orono, 2006
Yu Y, Ren Z, Gao F, et al. Changes in surface icing duration over north China during 1961–2015. Atmos Sci Lett, 2018, 19: e827
Abadi M, Agarwal A, Barham P, et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv: 1603.04467
Tarvainen A, Valpola H. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, 2017
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, 2017
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the Fundamental Research Funds for the Central Universities (Grant No. 2020JBM265), the Beijing Natural Science Foundation (Grant No. 3222016), the National Natural Science Foundation of China (Grant No. 62103035), the China Postdoctoral Science Foundation (Grant No. 2021M690337), and the Beijing Laboratory for Urban Mass Transit (Grant No. 353203535). The authors would like to acknowledge the database support from the China Academy of Transportation Science, the drawings from Siyang Zhang of Beihang University, and the suggestions from Dr. Shuai Zhang of Beihang University.
Rights and permissions
About this article
Cite this article
Wang, S., Wang, T., Pei, X. et al. Highway icing time prediction with deep learning approaches based on data from road sensors. Sci. China Technol. Sci. 66, 1987–1999 (2023). https://doi.org/10.1007/s11431-022-2230-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11431-022-2230-8