Abstract: Deep learning has empowered traffic prediction models to integrate diverse auxiliary data sources, such as weather and temporal features, for enhanced forecasting accuracy. However, existing approaches often suffer from limited generality and scalability, and the field lacks a unified benchmark for fair model comparison. This absence hinders consistent performance evaluation, slows the development of robust and adaptable models, and makes it challenging to quantify the incremental benefits of different auxiliary data sources. To address these issues, we present MltAuxTSPP, a unified benchmark framework for deep learning-based traffic state prediction with multi-source auxiliary data. The framework features a standardized data container and a fusion embedding module, enabling consistent utilization of heterogeneous data and improving scalability. It produces unified hidden representations that can be seamlessly adopted by various downstream models, ensuring fair and reproducible comparisons under identical conditions. Extensive experiments on real-world datasets demonstrate that MltAuxTSPP effectively leverages weather and temporal features to improve long-term forecast performance and offers a practical and reproducible foundation for advancing research in traffic state prediction.

MltAuxTSPP：一个融合多源辅助数据的交通预测深度学习统一基准框架

[1]Akiba T, Sano S, Yanase T, et al., 2019. Optuna: a next-generation hyperparameter optimization framework. Proc 25^th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining, p.2623-2631.

[2]Albanese D, Filosi M, Visintainer R, et al., 2013. Minerva and minepy: a C engine for the MINE suite and its R, Python and MATLAB wrappers. Bioinformatics, 29(3):407-408.

[3]Bączek J, Zhylko D, Titericz G, et al., 2024. TSPP: a unified benchmarking tool for time-series forecasting.

[4]Bai HY, Liu X, 2025. T-Graphormer: using Transformers for spatiotemporal forecasting.

[5]Do LNN, Taherifar N, Vu HL, 2019. Survey of neural network-based models for short-term traffic state prediction. WIREs Data Min Knowl Disc, 9(1):e1285.

[6]Essien A, Petrounias I, Sampaio P, et al., 2018. The impact of rainfall and temperature on peak and off-peak urban traffic. Int Conf on Database and Expert Systems Applications, p.399-407.

[7]Essien A, Petrounias I, Sampaio P, et al., 2021. A deep-learning model for urban traffic flow prediction with traffic events mined from twitter. World Wide Web, 24(4):1345-1368.

[8]Fang Z, Long QQ, Song GJ, et al., 2021. Spatial-temporal graph ODE networks for traffic flow forecasting. Proc 27^th ACM SIGKDD Conf on Knowledge Discovery & Data Mining, p.364-373.

[9]FHWA, 2024. How Do Weather Events Affect Roads? https://ops.fhwa.dot.gov/weather/q1_roadimpact.htm [Accessed on May 20, 2025].

[10]Guo SN, Lin YF, Feng N, et al., 2019. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. Proc 39^th AAAI Conf on Artificial Intelligence, p.922-929.

[11]Hochreiter S, Schmidhuber J, 1997. Long short-term memory. Neur Comput, 9(8):1735-1780.

[12]Lee K, Eo M, Jung E, et al., 2021. Short-term traffic prediction with deep neural networks: a survey. IEEE Access, 9:54739-54756.

[13]Li Y, Yu R, Shahabi C, et al., 2018. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. https://openreview.net/forum?id=SJiHXGWAZ [Accessed on May 20, 2025].

[14]Lim B, Arık SO, Loeff N, et al., 2021. Temporal fusion Transformers for interpretable multi-horizon time series forecasting. Int J Forecast, 37(4):1748-1764.

[15]Liu J, Guan W, 2004. A summary of traffic flow forecasting methods. J Highway Transport Res Dev, 21(3):82-85 (in Chinese).

[16]Liu X, Xia YT, Liang YX, et al., 2023. LargeST: a benchmark dataset for large-scale traffic forecasting. Proc 37^th Int Conf on Neural Information Processing Systems, p.75354-75371.

[17]Ma XL, Yu HY, Wang YP, et al., 2015. Large-scale transportation network congestion evolution prediction using deep learning theory. PLoS ONE, 10(3):e0119044.

[18]Meta Research, 2019. Hydra—a Framework for Elegantly Configuring Complex Applications. https://github.com/facebookresearch/hydra [Accessed on May 20, 2025].

[19]Nagy AM, Simon V, 2018. Survey on traffic prediction in smart cities. Pervasive Mob Comput, 50:148-163.

[20]Reshef DN, Reshef YA, Finucane HK, et al., 2011. Detecting novel associations in large data sets. Science, 334(6062):1518-1524.

[21]Shao ZZ, Wang F, Xu YJ, et al., 2025. Exploring progress in multivariate time series forecasting: comprehensive benchmarking and heterogeneity analysis. IEEE Trans Knowl Data Eng, 37(1):291-305.

[22]Shaygan M, Meese C, Li WX, et al., 2022. Traffic prediction using artificial intelligence: review of recent advances and emerging opportunities. Transport Res Part C Emerg Technol, 145:103921.

[23]Song C, Lin YF, Guo SN, et al., 2020. Spatial-temporal synchronous graph convolutional networks: a new framework for spatial-temporal network data forecasting. Proc 34^th AAAI Conf on Artificial Intelligence, p.914-921.

[24]Sutskever I, Vinyals O, Le QV, 2014. Sequence to sequence learning with neural networks. Proc 27^th Int Conf on Neural Information Processing Systems, p.3104-3112.

[25]Taghipour H, Parsa AB, Mohammadian AK, 2020. A dynamic approach to predict travel time in real time using data driven techniques and comprehensive data sources. Transport Eng, 2:100025.

[26]Vaswani A, Shazeer N, Parmar N, et al., 2017. Attention is all you need. Proc 31^st Int Conf on Neural Information Processing Systems, p.6000-6010.

[27]Wang JY, Jiang JW, Jiang WJ, et al., 2021. LibCity: an open library for traffic prediction. Proc 29^th Int Conf on Advances in Geographic Information Systems, p.145-148.

[28]Wu HX, Hu TG, Liu Y, et al., 2023. TimesNet: temporal 2D-variation modeling for general time series analysis.

[29]Wu ZH, Pan SR, Long GD, et al., 2019. Graph WaveNet for deep spatial-temporal graph modeling. Proc 28^th Int Joint Conf on Artificial Intelligence, p.1907-1913.

[30]Yang XX, Zou YJ, Tang JJ, et al., 2020. Evaluation of short-term freeway speed prediction based on periodic analysis using statistical models and machine learning models. J Adv Transport, 2020(1):9628957.

[31]Yu B, Yin HT, Zhu ZX, 2018. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. Proc 27^th Int Joint Conf on Artificial Intelligence, p.3634-3640.

[32]Zhao L, Song YJ, Zhang C, et al., 2020. T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transport Syst, 21(9):3848-3858.

[33]Zheng X, Bagloee SA, Sarvi M, 2025. A comparative study of deep learning and ensemble learning to extend the horizon of traffic forecasting.

[34]Zhou HY, Zhang SH, Peng JQ, et al., 2021. Informer: beyond efficient Transformer for long sequence time-series forecasting. Proc 39^th AAAI Conf on Artificial Intelligence, p.11106-11115.

[35]Zhu L, Yu FR, Wang YG, et al., 2019. Big data analytics in intelligent transportation systems: a survey. IEEE Trans Intell Trans Syst, 20(1):383-398.