A Comprehensive Study of Deep Learning Approaches for Predicting Reciprocal Traffic Dynamics and Climate Variability

Abrar Ali; Wadhah R.  Baiee

doi:10.30572/2018/KJE/160302

Authors

Abrar Ali Software Department, College of Information Technology, University of Babylon, Babylon, Iraq https://orcid.org/0009-0007-6283-1976
Wadhah R. Baiee Software Department, College of Information Technology, University of Babylon, Babylon, Iraq

DOI:

https://doi.org/10.30572/2018/KJE/160302

Keywords:

Climate variability, traffic flow, deep learning models, statistical methods, weather impact

Abstract

Climate change requires innovative solutions to improve traffic management and safety in transportation systems. This paper tries to expand on the complex relationship between weather, traffic, climate, and an integrated approach to traffic data. In the round, the general aim is to come up with the entire understanding of the relationship between weather and traffic, analyzing the way weather interacts with traffic and the way that traffic interacts with weather. It attempts to consider climate change through the consideration of the variables of extreme temperatures and precipitation, among others. It also looks into the work of traffic forecasting in the traffic models by highlighting the emissions and environmental impacts on environment-related accidents, the impacts of transportation systems on the nature of all living organisms, and a detailed table that aids in the clear comparison of different methods with the literature reviewed to understand the details of the interactions of the complex elements. That includes the elements of importance, such as the data sources, methods, and the advantages, along with some of the shortcomings or limitations that were found in them. Finally, it explains the challenges that the researchers had to face. The main findings from our study also suggest that the traffic forecasting patterns by deep learning models may contribute to 15% improvement over the traditional statistical method. In addition, the significant impact of extreme weather events on traffic flow was found; for instance, heavy precipitation events can lead to a 30% decrease in speed and increased accident rates up to 20%. Climate variability integrated into traffic models increases the prediction of long-term traffic trends by 12%, justifying the significance of the influence of climate factors in traffic management systems

Downloads

Download data is not yet available.

References

A. Nasser, A. and Simon, V. (2021) 'A Novel Method for Analyzing Weather Effect on Smart City Traffic', 2021 IEEE 22nd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM), Pisa, Italy, pp. 335–340. doi:10.1109/WoWMoM51794.2.

A.Nigam, A. and Srivastava, S. (2020) 'Macroscopic Traffic Stream Variable Prediction with Weather Impact Using Recurrent Learning Approach', 2020 IEEE-HYDCON, Hyderabad, India, pp. 1–6. doi:10.1109/HYDCON48903.2020.9242908.

Aditya, Srivastava. and Aryan. (2023) 'A Survey Paper on Traffic Prediction Using Machine Learning', International Journal For Science Technology And Engineering, 11(5), pp. 44–48. doi:10.22214/ijraset.2023.51390.

Binshaflout, E., Ghazzai, H. and Massoud, Y. (2023) 'Graph Neural Networks for Traffic Pattern Recognition: An Overview', 2023 IEEE International Conference on Smart Mobility (SM), Thuwal, Saudi Arabia, pp. 110–115. doi:10.1109/SM57895.2023.10112264.

Braz, F.J., Ferreira, J., Gonçalves, F., Weege, K., Almeida, J., Baldo, F. and Gonçalves, P. (2022) 'Road Traffic Forecast Based on Meteorological Information through Deep Learning Methods', Sensors, 22(12), pp. 1–19. doi:10.3390/s22124485.

Comert, G., Darko, S., Huynh, N., Elijah, B. and Eloise, Q. (2020) 'Evaluating the Impact of Traffic Volume on Air Quality in South Carolina', International Journal of Transportation Science and Technology, 9(1), pp. 29–41.

Dominika, Jarmuż. and Jerzy, Chmiel. (2020) 'A Review of Approaches to the Study of Weather's Effect on Road Traffic Parameters', Transport Problems, 15, pp. 241–251. doi:10.21307/TP-2020-063.

Evans, B., Chen, A.S., Djordjević, S., Webber, J., Gómez, A.G. and Stevens, J. (2020) 'Investigating the Effects of Pluvial Flooding and Climate Change on Traffic Flows in Barcelona and Bristol', Sustainability (Switzerland), 12(6). doi:10.3390/su12062065.

Hassaballah, M., Kenk, M.A. and Muhammad, K. (2020) 'Vehicle Detection and Tracking in Adverse Weather Using a Deep Learning Framework', [Journal/Conference Name], pp. 1–13.

Huang, Z. & Luo, J. (2022). Short-Time Traffic Flow Prediction Based on PCC-AT-CNNGRU. In 2022 China Automation Congress (CAC), Xiamen, China, pp. 5575–5580. https://doi.org/10.1109/CAC57257.2022.10055037

Ji, T., Yao, Y., Dou, Y., Deng, S., Yu, S., Zhu, Y. and Liao, H. (2022) 'The Impact of Climate Change on Urban Transportation Resilience to Compound Extreme Events', Sustainability, 14(7), 3880. doi:10.3390/su14073880.

Kamel Boulos, M.N. and Wilson, J.P. (2023) 'Geospatial Techniques for Monitoring and Mitigating Climate Change and Its Effects on Human Health', International Journal of Health Geographics, 22(1), pp. 1–7. doi:10.1186/s12942-023-00324-9.

Li, Z. and Hossain, E. (2019) 'Machine Learning for Wireless Communication in the Internet of Things: A Comprehensive Survey', IEEE Communications Surveys & Tutorials, 21(3), pp. 2658–2693. doi:10.1109/COMST.2019.2899352.

Lincoln Muniz Alves, Hayley Fowler, Naurinete de Jesus da Costa Barreto and Marta Llopart (2021) 'Chapter 3 - Climate Change and Climate Variability', pp. 53–68. doi:10.1016/B978-0-12-822699-5.00003-3.

Minji, Kang., Hyeonju, Park., Chung-won, Lim., Sang-kook, Han. and Gwangyong, Gim. (2022) 'Analysis of the Predictive Power of Highway Traffic Flow with Weather Conditions', pp. 45–49. doi:10.1109/BCD54882.2022.9900728.

Nachev, N. and Congeduti, S.E. (2023) 'Effects of Weather Data on Traffic Flow Predictions Using an LSTM Deep Learning Model'].

Nagesh Lad and Prof. Dr. Mitra V. (2023) 'Advancements in Machine Learning Techniques for Traffic Flow Prediction in Autonomous Vehicles: A Comprehensive Review', International Journal of Advanced Research in Science, Communication, and Technology, pp. 145–149.

Narmadha, S. and Vijayakumar, V. (2021) 'Spatio-Temporal Vehicle Traffic Flow Prediction Using Multivariate CNN and LSTM Model', Materials Today: Proceedings. doi:10.1016/j.matpr.2021.04.24.

National Oceanic and Atmospheric Administration (NOAA). (2021) 'Extreme Weather and Climate Change'. Available at: https://www.noaa.gov/education.

Ruizhe, Shi. and Lijing, Du. (2022) 'Multi-Section Traffic Flow Prediction Based on MLR-LSTM Neural Network', Sensors, 22(19), 7517. doi:10.3390/s22197517.

Sharaf, AlKheder. and Abdullah, Alomair. (2021) 'Urban Traffic Prediction Using Meteorological Data with Fuzzy Logic, Long Short-Term Memory (LSTM), and Decision Trees (DTs)', Natural Hazards, pp. 1–35. doi:10.1007/S11069-021-05112-X.

Shoaeinaeini, M., Ozturk, O. and Gupta, D. (2022) 'Twitter-Informed Prediction for Urban Traffic Flow Using Machine Learning', 6th IEEE International Conference on Universal Village (UV 2022), pp. 1–6. doi:10.1109/UV56588.2022.10185516.

Smith, J.A. and Brown, L.R. (2020) 'The Effects of Inclement Weather on Road Safety: A Comprehensive Review', Journal of Transportation Research, 45(3), pp. 215–229.

Snyder, C. and Do, M.N. (2019) 'STREETS: A Novel Camera Network Dataset for Traffic Flow', Advances in Neural Information Processing Systems, 32 (NeurIPS).

Sulaiman, I., Alaka, H., Olu-Ajayi, R., Ahmad, M., Ajayi, S. and Hye, A. (2022) 'Effect of Traffic Dataset on Various Machine-Learning Algorithms When Forecasting Air Quality', Journal of Engineering, Design and Technology.

Torino, P.D.I., Rossi, C., Farasin, A., Torino, P. and Falcone, G. (2019) A Machine Learning Approach to Monitor Air Quality from Traffic and Weather data .August 2020.

Vajjarapu, H., Verma, A. and Allirani, H. (2020) 'Evaluating Climate Change Adaptation Policies for Urban Transportation in India', International Journal of Disaster Risk Reduction, 47, 101528. doi:10.1016/j.ijdrr.2020.101528.

Wang, R., Zhao, H., Xu, Z., Ding, Y., Li, G., Zhang, Y. and Li, H. (2023) 'Real-Time Vehicle Target Detection in Inclement Weather Conditions Based on YOLOv4', Frontiers in Neurorobotics, 17. doi:10.3389/fnbot.2023.1058723.

Yang, D., Zhang, S., Niu, T., Wang, Y., Xu, H., Zhang, K.M. and Wu, Y. (2019) 'High-Resolution Mapping of Vehicle Emissions of Atmospheric Pollutants Based on Large-Scale, Real-World Traffic Datasets', Atmospheric Chemistry and Physics, 19(13), pp. 8831–8843.

Yue, Hou, Y., Deng, Z., & Cui, H. (2021). Short-Term Traffic Flow Prediction with Weather Conditions: Based on Deep Learning Algorithms and Data Fusion. Complexity, 2021. https://doi.org/10.1155/2021/6662959

Zennaro, F., Furlan, E., Simeoni, C., Torresan, S., Aslan, S., Critto, A., & Marcomini, A. (2021). Exploring machine learning potential for climate change risk assessment. Earth-Science Reviews, 220, 103752. https://doi.org/10.1016/j.earscirev.2021.103752ResearchGate

Zhang, Z. & Zhang, W. (2020). Traffic pattern analysis and traffic state prediction of urban traffic road network based on correlated routes. In 2020 39th Chinese Control Conference (CCC), Shenyang, China, pp. 5654–5659. https://doi.org/10.23919/CCC50068.2020.9189082

Zheng, Z., Liu, Z., & Wang, Y. (2020). Deep Learning for Traffic Prediction: A Survey. IEEE Transactions on Intelligent Transportation Systems, 22(7), 4337–4351. https://doi.org/10.1109/TITS.2020.3006170

Zhou, Q., Chen, N., & Lin, S. (2022). FASTNN: A Deep Learning Approach for Traffic Flow Prediction Considering Spatiotemporal Features. Sensors, 22(18), 6921. https://doi.org/10.3390/s22186921

Zou, Y., Zhang, Y., & Cheng, K. (2021). Exploring the impact of climate and extreme weather on fatal traffic accidents. Sustainability, 13(1), 390. https://doi.org/10.3390/su13010390.