Trend-Season Dual-Branch Fusion Network with Harmonic Weighting for Traffic Prediction
Downloads
Traffic flow prediction is an important component of intelligent transportation systems. Most existing studies adopt spatio-temporal methods for real-time short-term prediction. However, when dealing with complex and dynamically changing historical data in long-term prediction tasks, several challenges arise, such as high complexity, high computational cost and unstable spatial dependencies. In response to this deficiency, this paper proposes a trend-season dual-branch fusion network with harmonic weighting for long-sequence traffic flow prediction. This model decomposes the original sequence into trend and seasonal components. Specifically, the trend branch applies multi-scale sampling, and the trend components at different scales are fused in a top-down manner to enhance information representation. Finally, a linear layer is used to predict the trend results. The seasonal branch encodes the seasonal components through wavelet transform, and a harmonic weighting mechanism is designed to adaptively fuse the prediction results of both branches. Experiments conducted on multiple public transportation datasets demonstrate that the proposed model significantly outperforms existing mainstream methods in long-term predictions at time steps of 96, 192, 288 and 336, thereby verifying the effectiveness and robustness of time-series modelling approach in long-sequence prediction scenarios.
Downloads
Hossain MN, Ahmed N, Wazid Ullah SM. Traffic flow forecasting in intelligent transportation systems prediction using machine learning. Proceedings of the 2022 International Conference on Futuristic Technologies (INCOFT), 25-27 Nov. 2022, Belgaum, India. 2022. p. 1–5. DOI: 10.1109/INCOFT55651.2022.10094319.
Yu B, Yin H, Zhu Z. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’18). Stockholm, Sweden, 13–19 July 2018. AAAI Press; 2018. p. 3634–3640. DOI: 10.24963/IJCAI.2018/505.
Li Y, Yu R, Shahabi C, Liu Y. Diffusion convolutional recurrent neural network: data-driven traffic forecasting. Proceedings of the 6th International Conference on Learning Representations (ICLR 2018), 30 Apr. - 3 May 2018, Vancouver, Canada. 2018. arXiv:1707.01926.
He Z, Chow CY, Zhang JD. STCNN: A spatio-temporal convolutional neural network for long-term traffic prediction. Proceedings of the 20th IEEE International Conference on Mobile Data Management (MDM 2019). Hong Kong, China, 10–13 June 2019. 2019. p. 226–233. DOI: 10.1109/MDM.2019.00053.
Chen YT, et al. Traffic flow prediction based on spatial-temporal multi factor fusion graph convolutional networks. Scientific Reports. 2025;15(1):12612. DOI: 10.1038/s41598-025-96801-1.
Hou Z, Li X. Repeatability and similarity of freeway traffic flow and long-term prediction under big data. IEEE Transactions on Intelligent Transportation Systems. 2016;17(6):1786–1796. DOI: 10.1109/TITS.2015.2511156.
Kumar SV, Vanajakshi L. Short-term traffic flow prediction using seasonal ARIMA model with limited input data. European Transport Research Review. 2015;7(3):21. DOI: 10.1007/s12544-015-0170-8.
Wang H, et al. Empirical mode decomposition–autoregressive integrated moving average hybrid short-term traffic speed prediction model. Transportation Research Record. 2014;2460(1):66–76. DOI: 10.3141/2460-08.
Chi Z, Shi L. Short-term traffic flow forecasting using ARIMA–SVM algorithm and R. Proceedings of the 5th International Conference on Information Science and Control Engineering (ICISCE 2018). Chengdu, China, 20–22 July 2018. 2018. p. 517–522. DOI: 10.1109/ICISCE.2018.00114.
Ye J, Xue S, Jiang A. Attention-based spatio-temporal graph convolutional network considering external factors for multi-step traffic flow prediction. Digital Communications and Networks. 2022;8(3):343–350. DOI: 10.1016/j.dcan.2021.09.007.
Xu Y, et al. Urban traffic flow prediction: a spatio-temporal variable selection-based approach. Journal of Advanced Transportation. 2016;50(4):489–506. DOI: 10.1002/atr.1356.
Chen Y, et al. Acting as a decision maker: traffic-condition-aware ensemble learning for traffic flow prediction. IEEE Transactions on Intelligent Transportation Systems. 2022;23(4):3190–3200. DOI: 10.1109/TITS.2020.3032758.
Wang D, et al. Bayesian optimization of support vector machine for regression prediction of short-term traffic flow. Intelligent Data Analysis. 2019;23(2):481–497. DOI: 10.3233/IDA-183832.
Cheng S, Lu F, Peng P, Wu S. Short-term traffic forecasting: an adaptive ST-KNN model that considers spatial heterogeneity. Computers, Environment and Urban Systems. 2018;71:186–198. DOI: 10.1016/j.compenvurbsys.2018.05.009.
Tang J, et al. An improved fuzzy neural network for traffic speed prediction considering periodic characteristic. IEEE Transactions on Intelligent Transportation Systems. 2017;18(9):2340–2350. DOI: 10.1109/TITS.2016.2643005.
Liu Z, et al. A hybrid short-term traffic flow forecasting method based on neural networks combined with K-nearest neighbor. Promet – Traffic & Transportation. 2018;30(4):445–456. DOI: 10.7307/ptt.v30i4.2651.
Akin M, Sagiroglu S. Short-term traffic speed prediction with RNN method for roads characterized by density-based clustering method. Journal of the Faculty of Engineering and Architecture of Gazi University. 2022;37(2):581–593. DOI: 10.17341/gazimmfd.921035.
Xia D, et al. RSAB-ConvGRU: A hybrid deep-learning method for traffic flow prediction. Multimedia Tools and Applications. 2023;83(7):20559–20585. DOI: 10.1007/s11042-023-15877-x.
Lu H, et al. A temporal-aware LSTM enhanced by loss-switch mechanism for traffic flow forecasting. Neurocomputing. 2021;427:169–178. DOI: 10.1016/j.neucom.2020.11.026.
Walch M, Neubauer M, Schildorfer W. Floating car data-based short-term travel time forecasting with deep recurrent neural networks incorporating weather data. Journal of Transportation Engineering, Part A: Systems. 2023;149(6):04023059. DOI: 10.1061/JTEPBS.TEENG-7647.
Zeng A, Chen M, Zhang L, Xu Q. Are transformers effective for time series forecasting? Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023). 7–14 Feb. 2023, Washington, DC, USA. 2023. p. 11121–11128. DOI: 10.1609/aaai.v37i9.26317.
Wang S, et al. TimeMixer: decomposable multiscale mixing for time series forecasting. Proceedings of the International Conference on Learning Representations (ICLR 2024). 7–11 May 2024, Vienna, Austria. 2024. DOI: 10.48550/arXiv.2305.08891.
Yu H, Guo P, Sano A. AdaWaveNet: Adaptive wavelet network for time series analysis. Transactions on Machine Learning Research. 2024 Nov. Epub ahead of print. DOI: 10.48550/arXiv.2306.10931.
Jiang J, Han C, Zhao WX, Wang J. Propagation delay-aware dynamic long-range Transformer for traffic flow prediction. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2023). 7–14 Feb. 2023, Washington, DC, USA. 2023. p. 4493–4501. DOI: 10.1609/aaai.v37i4.25556.
Xiao J, Long B. A multi-channel spatial-temporal Transformer model for traffic flow forecasting. Information Sciences. 2024;671:120648. DOI: 10.1016/j.ins.2024.120648.
Evans J, Waterson B, Hamilton A. Forecasting road traffic conditions using a context-based random forest algorithm. Transport Planning and Technology. 2020;43(2):123–138. DOI: 10.1080/03081060.2020.1728470.
Wang Z, Su X, Ding Z. Long-term traffic prediction based on LSTM encoder-decoder architecture. IEEE Transactions on Intelligent Transportation Systems. 2021;22(10):6561–6571. DOI: 10.1109/TITS.2020.2995546.
Li Y, Chai S, Ma Z, Wang G. A hybrid deep learning framework for long-term traffic flow prediction. IEEE Access. 2021;9:11264–11271. DOI: 10.1109/ACCESS.2021.3050836.
Wu H, Xu J, Wang J, Long M. Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021). 6–14 Dec. 2021, Virtual Conference. 2021. p. 22419–22430. DOI: 10.48550/arXiv.2106.13008.
Chan RKC, Lim JMY, Parthiban R. Long-term traffic speed prediction utilizing data augmentation via segmented time frame clustering. Knowledge-Based Systems. 2025;308:112785. DOI: 10.1016/j.knosys.2025.112785.
Wang X, Chen Y, Huang T. Long-horizon traffic flow forecasting using hierarchical temporal aggregation and recurrent residual modeling. IEEE Transactions on Intelligent Transportation Systems. 2024. Early Access. DOI: 10.1109/TITS.2024.3365129.
Sweldens W. The lifting scheme: a construction of second generation wavelets. SIAM Journal on Mathematical Analysis. 1998;29(2):511–546. DOI: 10.1137/S0036141095289051.
Chen C, et al. Freeway performance measurement system: mining loop detector data. Transportation Research Record: Journal of the Transportation Research Board. 2001;1748(1):96–102. DOI: 10.3141/1748-12.
Liu X, et al. LargeST: A benchmark dataset for large-scale traffic forecasting. Proceedings of the 37th Conference on Neural Information Processing Systems Datasets & Benchmarks. 10–16 Dec. 2023, Virtual Conference. 2023. p. 1–12. DOI: 10.48550/arXiv.2306.08259.
Li Y, Zhao Q, Wang M. High-resolution traffic flow data from the urban traffic control system in Glasgow. Scientific Data. 2025;12(1):253. DOI: 10.1038/s41597-025-04494-y.
Liu S, et al. Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. Proceedings of the International Conference on Learning Representations (ICLR 2022). 25–29 Apr. 2022, Virtual Conference. 2022. DOI: 10.48550/arXiv.2201.12746.
Liu Y, et al. iTransformer: Inverted transformers are effective for time series forecasting. Proceedings of the International Conference on Learning Representations (ICLR 2024). 7–11 May 2024, Vienna, Austria. 2024. DOI: 10.48550/arXiv.2310.06625.
Lin S, et al. Cyclenet: Enhancing time series forecasting through modeling periodic patterns. Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024). 9–15 Dec. 2024, New Orleans, LA, USA. 2024. p. 106315-106345. DOI: 10.48550/arXiv.2405.11892.
Copyright (c) 2026 Yangyi LIU, Siyuan ZHANG, Wenjun ZHOU, Yifan WANG, Quan ZHANG, Bo PENG
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
