現今以深度學習方式預測交通流量、旅行時間的相關研究已經非常純熟，但是結合交通基本理論的相關討論研究比較缺乏，所以此篇論文探討的是結合交通流理論模型、深度學習、非線性雙曲型守恆定律，預測高速公路下交通流量預測，深度學習、數值模擬、結合數值模擬跟深度學習模型的比較研究。

Using deep learning model to predict traffic flow nowadays is a very popular method for research, but most of the traffic flow research only put data into deep learning model without traffic flow fundamental theorem. We combine the numerical simulation which is partial differential equation model with deep learning model which is recurrent neural networks model and predict the traffic flow. In partial difference equation, there is some theorem of traffic flow, and we have assumption by the theorem. We use a machine learning tool, partial differential equation based numerical simulation, and their hybrid technique for traffic flow prediction.

[1] E. Cascetta. Transportation Systems Engineering: Theory and Methods. Springer
Science & Business Media, 2013.
[2] W.-T. Sung. A study of multilane highway traffic flow models. Master’s thesis,
National Chiao Tung University, 2012.
[3] S. Ardekani, M. Ghandehari, and S. Nepal. Macroscopic speed-flow models for characterization
of freeway and managed lanes. Buletinul Institutului Politehnic din lasi.
Sectia Constructii, Arhitectura, 57:149, 2011.
[4] M. M. Hamed, H. R. Al-Masaeid, and Z. M. B. Said. Short-term prediction of traffic
volume in urban arterials. J. Transp. Eng., 121:249–254, 1995.
[5] V. D. V. Mascha, M. Dougherty, and S. Watson. Combining kohonen maps with
arima time series models to forecast traffic flow. Transportation Research Part C:
Emerging Technologies, 4:307–318, 1996.
[6] A. Bressan and K. T. Nguyen. Conservation law models for traffic flow on a network
of roads. Networks Heter. Media, 10:255–293, 2015.
[7] Y.-T. Lee. Nonlinear Balance Laws in Traffic Flow - A Model with Lane-changing
Intensity. Master’s thesis, National Central University, 2013.
[8] C.-W. Liang. A Study of Some Numerical Schemes for Hyperbolic PDE Problems.
Master’s thesis, National Central University, 2017.
[9] C.-H. Lin. Applications of High-order Markov Chains in Traffic Flow. Master’s thesis,
National Chiao Tung University, 2017.
[10] C. Siripanpornchana, S. Panichpapiboon, and P. Chaovalit. Travel-time prediction
with deep learning. In Region 10 Conference (TENCON), 2016 IEEE, pages 1859–
1862. IEEE, 2016.
[11] Y. Lv, Y. Duan, W. Kang, Z. Li, and F.-Y. Wang. Traffic flow prediction with big
data: a deep learning approach. IEEE Trans. Intell. Transp. Syst., 16:865–873, 2015.
[12] E. I. Vlahogianni, M. G. Karlaftis, and J. C. Golias. Optimized and meta-optimized
neural networks for short-term traffic flow prediction: A genetic approach. Transport.
Res. C Emerg. Tech., 13:211–234, 2005.
[13] R. Fu, Z. Zhang, and L. Li. Using LSTM and GRU neural network methods for
traffic flow prediction. In Chinese Association of Automation (YAC), Youth Academic
Annual Conference of, pages 324–328. IEEE, 2016.
[14] M. Levin and Y.-D. Tsao. On forecasting freeway occupancies and volumes. Transp.
Res. Rec., pages 47–49, 1980.
[15] S. Lee and D. Fambro. Application of subset autoregressive integrated moving average
model for short-term freeway traffic volume forecasting. Transp. Res. Rec., pages
179–188, 1999.
[16] B. Williams. Multivariate vehicular traffic flow prediction: Evaluation of arimax
modeling. Transp. Res. Rec., pages 194–200, 2001.
[17] W.-L. Jin. A multi-commodity lighthill-whitham-richards model of lane-changing
traffic flow. Procedia Soc Behav Sci, 80:658–677, 2013.
[18] P. Goatin and S. Scialanga. The Lighthill-Whitham-Richards traffic flow model with
non-local velocity: analytical study and numerical results. PhD thesis, Inria Sophia
Antipolis; INRIA, 2015.