A stochastic model for theme park ride waiting times is developed by modeling the waiting time as a continuous-time, discrete-state Markov process with state-dependent, time-varying transition rates. These transition rates are interpreted as a control term acting on the waiting-time process, allowing the model calibration task to be formulated as a data-driven optimal control problem. To solve this problem efficiently, we construct a physics-informed neural network (PINN) that embeds the Kolmogorov forward equation solver into its architecture. Under mild assumptions, we prove the existence of an optimal control, providing theoretical support for the learning procedure. Numerical simulations demonstrate the effectiveness of the PINN-based solution. The proposed framework provides an interpretable, physically consistent, and data-driven approach for modeling and forecasting ride waiting times.
Citation: William Wang, Lingju Kong, Min Wang. Physics-informed stochastic models for theme park ride waiting times[J]. Electronic Research Archive, 2026, 34(6): 4158-4171. doi: 10.3934/era.2026186
A stochastic model for theme park ride waiting times is developed by modeling the waiting time as a continuous-time, discrete-state Markov process with state-dependent, time-varying transition rates. These transition rates are interpreted as a control term acting on the waiting-time process, allowing the model calibration task to be formulated as a data-driven optimal control problem. To solve this problem efficiently, we construct a physics-informed neural network (PINN) that embeds the Kolmogorov forward equation solver into its architecture. Under mild assumptions, we prove the existence of an optimal control, providing theoretical support for the learning procedure. Numerical simulations demonstrate the effectiveness of the PINN-based solution. The proposed framework provides an interpretable, physically consistent, and data-driven approach for modeling and forecasting ride waiting times.
| [1] |
M. Steptoe, R. Krüger, R. Garcia, X. Liang, R. Maciejewski, A visual analytics framework for exploring theme park dynamics, ACM Trans. Interact. Intell. Syst., 8 (2018), 4. https://doi.org/10.1145/3162076 doi: 10.1145/3162076
|
| [2] |
G. Hernandez-Maskivker, G. Ryan, M. Pàmies, Waiting times at theme parks: How managers interpret waiting, Tourismos, 11 (2016), 158–184. https://doi.org/10.26215/tourismos.v11i4.498 doi: 10.26215/tourismos.v11i4.498
|
| [3] | D. Gross, J. F. Shortle, J. M. Thompson, C. M. Harris, Fundamentals of Queueing Theory, Wiley, 2008. |
| [4] |
X. Chen, D. Worthington, Staffing of time-varying queues using a geometric discrete time modelling approach, Ann. Oper. Res., 252 (2017), 63–84. https://doi.org/10.1007/s10479-015-2058-3 doi: 10.1007/s10479-015-2058-3
|
| [5] | J. Li, Q. Li, Analysis of queue management in theme parks introducing the fast pass system, Heliyon, 9 (2023), https://doi.org/10.1016/j.heliyon.2023.e18001}. |
| [6] | A. Law, Simulation Modeling and Analysis, 5th edition, McGraw Hill, 2015. |
| [7] |
W. H. Fun, E. H. Tan, R. Khalid, S. Sararaks, K. F. Tang, I. Ab Rahim, et al., Applying discrete event simulation to reduce patient wait times and crowding: The case of a specialist outpatient clinic with dual practice system, Healthcare (Basel), 10 (2022), 189. https://doi.org/10.3390/healthcare10020189 doi: 10.3390/healthcare10020189
|
| [8] | E. Allen, Modeling with It$\hat{o}$ Stochastic Differential Equations, Springer, 2007. |
| [9] | A. Chadwick, S. S. Ho, Y. Li, M. Wang, A discrete model for bike share inventory, Int. J. Differ. Equations, 15 (2020), 363–375. |
| [10] | L. Kong, M. Wang, Deterministic and stochastic online social network models with varying population size, DCDIS Ser. A Math. Anal., 30 (2023), 253–275. |
| [11] |
L. Kong, M. Wang, Optimal control for an ordinary differential equation online social network model, Differ. Equations Appl., 14 (2022), 205–214. http://dx.doi.org/10.7153/dea-2022-14-13 doi: 10.7153/dea-2022-14-13
|
| [12] |
A. Farea, O. Yli-Harja, F. Emmert-Streib, Understanding physics-informed neural networks: Techniques, applications, trends, and challenges, AI, 5 (2024), 1534–1557. https://doi.org/10.3390/ai5030074 doi: 10.3390/ai5030074
|
| [13] |
K. Luo, J. Zhao, Y. Wang, J. Li, J. Wen, J. Liang, et al., Physics-informed neural networks for PDE problems: A comprehensive review, Artif. Intell. Rev., 58 (2025), 323. https://doi.org/10.1007/s10462-025-11322-7 doi: 10.1007/s10462-025-11322-7
|
| [14] |
W. He, J. Li, X. Kong, L. Deng, Multi-level physics informed deep learning for solving partial differential equations in computational structural mechanics, Commun. Eng., 3 (2024), 151. https://doi.org/10.1038/s44172-024-00303-3 doi: 10.1038/s44172-024-00303-3
|
| [15] |
S. Cuomo, V. S. Di Cola, F. Giampaolo, G. Rozza, M. Raissi, F. Piccialli, Scientific machine learning through physics–informed neural networks: Where we are and what's next, J. Sci. Comput., 92 (2022), 88. https://doi.org/10.1007/s10915-022-01939-z doi: 10.1007/s10915-022-01939-z
|
| [16] |
D. Llorente-Vidrio, M. Ballesteros, I. Salgado, I. Chairez, Deep learning adapted to differential neural networks used as pattern classification of electrophysiological signals, IEEE TPAMI, 44 (2022), 4807–4818. https://doi.org/10.1109/TPAMI.2021.3066996 doi: 10.1109/TPAMI.2021.3066996
|
| [17] | W. E, T. Li, E. Vanden-Eijnden, Applied Stochastic Analysis, AMS, 2019. |
| [18] | Queue Times. Available from: https://queue-times.com/en-US/. |
| [19] |
L. Kong, R. Shi, M. Wang, A physics-informed neural network model for social media user growth, Appl. Comput. Intell., 4 (2024), 195–208. https://doi.org/10.3934/aci.2024012 doi: 10.3934/aci.2024012
|
| [20] |
L. Kong, R. Shi, M. Wang, An age-structured model for COVID-19 hospitalization rate, Mathematics, 14 (2026), 58. https://doi.org/10.3390/math14010058 doi: 10.3390/math14010058
|
| [21] | D. Kincaid, W. Cheney, Numerical Analysis: Mathematics of Scientific Computing, 3rd edition, American Mathematical Society, 2002. |
Figures(5) / Tables(1)
William Wang, Lingju Kong, Min Wang. Physics-informed stochastic models for theme park ride waiting times[J]. Electronic Research Archive, 2026, 34(6): 4158-4171. doi: 10.3934/era.2026186
DownLoad: