Abstract
Airport terminals are complex sociotechnical systems, in which humans interact with diverse technical systems. A natural way to represent them is through agent-based modeling. However, this method has two drawbacks: it entails a heavy computational burden and the emergent properties are often difficult to analyze. The purpose of our research is therefore to accurately abstract and explain the dynamics of airport terminal operations by means of computationally efficient and interpretable surrogate models, based on an existing agent-based simulation model. We propose a methodology consisting of two stages. Stage I involves the development of faithful surrogates. A sample is collected according to an active learning strategy, upon which Gaussian process regression, higher-order polynomials, gradient boosting, and random forests are fitted. Stage II then applies state-of-the-art techniques from the emerging field of explainable artificial intelligence to these models. Both model-agnostic and model-specific methods are considered, and their results are synthesized in order to explain the emergent properties. We prove the efficacy of this approach by conducting two case studies on AATOM, an existing Agent-based Airport Terminal Operations Model. Altogether, we clearly observed the preservation of emergent phenomena in surrogate models, and conclude that their combination with interpretable machine learning is an effective way to explain the dynamics of complex sociotechnical systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
De Leeuw, B., Mohammadi Ziabari, S.S., Sharpanskykh, A.: Surrogate modeling of agent-based airport terminal operations. In: Lorig, F., Norling, E. (eds.) Multi-Agent-Based Simulation XXIII, Auckland, New Zealand, MABS 2022. LNCS, vol. 13743, pp. 82–94. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-22947-3_7, https://mabsworkshop.github.io/articles/MABS_2022_paper_9.pdf
Fuhg, J.N., Fau, A., Nackenhorst, U.: State-of-the-art and comparative review of adaptive sampling methods for Kriging. Arch. Comput. Methods Eng. 28(4), 2689–2747 (2021). ISSN 1134-3060, https://doi.org/10.1007/s11831-020-09474-6, https://link.springer.com/10.1007/s11831-020-09474-6
Wu, P.P.-Y., Mengersen, K.: A review of models and model usage scenarios for an airport complex system. Transp. Res. Part A Policy Pract. 47, 124–140 (2013). ISSN 0965-8564, https://doi.org/10.1016/j.tra.2012.10.015, https://linkinghub.elsevier.com/retrieve/pii/S0965856412001541
Thurmond, V.A.: The point of triangulation. J. Nurs. Sch. 33(3), 253–258 (2001). ISSN 1527-6546, 1547-5069, https://doi.org/10.1111/j.1547-5069.2001.00253.x, https://onlinelibrary.wiley.com/doi/10.1111/j.1547-5069.2001.00253.x
Noble, H., Heale, R.: Triangulation in research, with examples. Evid. Based Nurs. 22(3), 67–68 (2019). ISSN 1367-6539, 1468-9618. https://doi.org/10.1136/ebnurs-2019-103145, https://ebn.bmj.com/lookup/doi/10.1136/ebnurs-2019-103145
Manataki, I.E., Zografos, K.G.: Development and demonstration of a modeling framework for airport terminal planning and performance evaluation. Transp. Res. Rec. J. Transp. Res. Board 2106(1), 66–75 (2009). ISSN 0361-1981, https://doi.org/10.3141/2106-08, http://journals.sagepub.com/doi/10.3141/2106-08
Belle, V., Papantonis, I.: Principles and practice of explainable machine learning. Front. Big Data 4, 39 (2021). ISSN 2624-909X, https://doi.org/10.3389/fdata.2021.688969, https://www.frontiersin.org/article/10.3389/fdata.2021.688969
Fisher, A., Rudin, C., Dominici, F.: All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously. J. Mach. Learn. Res. 20(177), 1–81 (2019). ISSN 1533-7928, http://jmlr.org/papers/v20/18-760.html
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. Adaptive Computation And Machine Learning. MIT Press, Cambridge (2006). ISBN 978-0-262-18253-9
Janssen, S., Sharpanskykh, A., Curran, R.: Agent-based modelling and analysis of security and efficiency in airport terminals. Transp. Res. Part C Emerg. Technol. 100, 142–160 (2019). ISSN 0968-090X, https://doi.org/10.1016/j.trc.2019.01.012, https://linkinghub.elsevier.com/retrieve/pii/S0968090X1830809X
Borgonovo, E., Plischke, E.: Sensitivity analysis: a review of recent advances. Eur. J. Oper. Res. 248(3), 869–887 (2016). ISSN 0377-2217, https://doi.org/10.1016/j.ejor.2015.06.032, https://linkinghub.elsevier.com/retrieve/pii/S0377221715005469
Chicco, D., Warrens, M.J., Jurman, G.: The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput. Sci. 7, e623 (2021). ISSN 2376-5992, https://doi.org/10.7717/peerj-cs.623, https://peerj.com/articles/cs-623
Jia, L., Alizadeh, R., Hao, J., Wang, G., Allen, J.K., Mistree, F.: A rule-based method for automated surrogate model selection. Adv. Eng. Inform. 45, 101123 (2020). ISSN 1474-0346, https://doi.org/10.1016/j.aei.2020.101123, https://linkinghub.elsevier.com/retrieve/pii/S1474034620300926
Timmins, B., Austin, K.: Heathrow flight cancellations cause queues and ‘chaos’. BBC News, June 2022. https://www.bbc.com/news/business-61857008
IATA. Airport Development Reference Manual, 9th edn., Montreal (2004). ISBN 978-92-9195-086-7
Macal, C., North, M.: Tutorial on agent-based modeling and simulation. In: Proceedings of the Winter Simulation Conference, pp. 2–15, December 2005. https://doi.org/10.1109/WSC.2005.1574234, ISSN: 1558-4305
Hutter, F., Lücke, J., Schmidt-Thieme, L.: Beyond manual tuning of hyperparameters. Künstliche Intelligenz 29(4), 329–337 (2015). ISSN 0933-1875, https://doi.org/10.1007/s13218-015-0381-0, http://link.springer.com/10.1007/s13218-015-0381-0
Magalhães, L., Reis, V., Macário, R.: A new methodological framework for evaluating flexible options at airport passenger terminals. Case Stud. Transp. Policy 8(1), 76–84 (2020). ISSN 2213-624X. https://doi.org/10.1016/j.cstp.2018.03.003, https://linkinghub.elsevier.com/retrieve/pii/S2213624X18300749
Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30, Long Beach, CA, USA. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html
Lam, C.Q.: Sequential adaptive designs in computer experiments for response surface model fit. Ph.D. thesis, Ohio State University (2008). http://rave.ohiolink.edu/etdc/view?acc_num=osu1211911211
Lamperti, F., Roventini, A., Sani, A.: Agent-based model calibration using machine learning surrogates. J. Econ. Dyn. Control 90, 366–389 (2018). ISSN 0165-1889, https://doi.org/10.1016/j.jedc.2018.03.011, https://linkinghub.elsevier.com/retrieve/pii/S0165188918301088
Janssen, S., Sharpanskykh, A., Curran, R.: AbSRiM: an agent-based security risk management approach for airport operations. Risk Anal. 39(7), 1582–1596 (2019). ISSN 1539-6924, https://doi.org/10.1111/risa.13278, http://onlinelibrary.wiley.com/doi/abs/10.1111/risa.13278
Janssen, S., Blok, A.-N., Knol, A.: AATOM - an agent-based airport terminal operations model. Delft University of Technology, April 2018. https://research.tudelft.nl/en/publications/aatom-an-agent-based-airport-terminal-operations-model
Westermann, P., Evins, R.: Surrogate modelling for sustainable building design a review. Energy Build. 198, 170–186 (2019). ISSN 0378-7788, https://doi.org/10.1016/j.enbuild.2019.05.057, https://www.sciencedirect.com/science/article/pii/S0378778819302877
James, K.C., Bhasi, M.: Development of model categories for performance improvement studies related to airport terminal operations. J. Simul. 4(2), 98–108 (2010). ISSN 1747-7778, https://doi.org/10.1057/jos.2009.27, https://www.tandfonline.com/doi/full/10.1057/jos.2009.27
Janssen, S., Sharpanskykh, A., Curran, R., Langendoen, K.: Using causal discovery to analyze emergence in agent-based models. Simul. Model. Pract. Theory 96, 101940 (2019). ISSN 1569190X, https://doi.org/10.1016/j.simpat.2019.101940, https://linkinghub.elsevier.com/retrieve/pii/S1569190X19300735
Curcio, D., Longo, F., Mirabelli, G., Pappoff, E.: Passengers flow analysis and security issues in airport terminals using modeling & simulation. In: ECMS 2007, pp. 374–379. ECMS, June 2007. ISBN 978-0-9553018-2-7, https://doi.org/10.7148/2007-0374, http://www.scs-europe.net/dlib/2007/2007-0374.htm
Williams, B., Cremaschi, S.: Selection of surrogate modeling techniques for surface approximation and surrogate-based optimization. Chem. Eng. Res. Des. 170, 76–89 (2021). ISSN 0263-8762, https://doi.org/10.1016/j.cherd.2021.03.028, https://www.sciencedirect.com/science/article/pii/S0263876221001465
Ziabari, S.S.M., Sanders, G., Mekic, A., Sharpanskykh, A.: Demo paper: a tool for analyzing COVID-19-related measurements using agent-based support simulator for airport terminal operations. In: Dignum, F., Corchado, J.M., De La Prieta, F. (eds.) PAAMS 2021. LNCS (LNAI), vol. 12946, pp. 359–362. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-85739-4_32
Sanders, G., Mohammadi Ziabari, S.S., Mekić, A., Sharpanskykh, A.: Agent-based modelling and simulation of airport terminal operations under COVID-19-related restrictions. In: Dignum, F., Corchado, J.M., De La Prieta, F. (eds.) PAAMS 2021. LNCS (LNAI), vol. 12946, pp. 214–228. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-85739-4_18
Mekić, A., Mohammadi Ziabari, S.S., Sharpanskykh, A.: Systemic agent-based modeling and analysis of passenger discretionary activities in airport terminals. Aerospace 8(6), 162 (2021)
Janssen, S., Sharpanskykh, A., Mohammadi Ziabari, S.S.: Using causal discovery to design agent-based models. In: Lorig, F., Norling, E. (eds.) Multi-Agent-Based Simulation XXIII, MABS 2021, Virtual Event, 3–7 May 2021, Revised Selected Papers. LNCS, vol. 13743, pp. 15–28. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-22947-3_7
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
de Bosscher, B.C.D., Mohammadi Ziabari, S.S., Sharpanskykh, A. (2024). Towards a Better Understanding of Agent-Based Airport Terminal Operations Using Surrogate Modeling. In: Nardin, L.G., Mehryar, S. (eds) Multi-Agent-Based Simulation XXIV. MABS 2023. Lecture Notes in Computer Science(), vol 14558. Springer, Cham. https://doi.org/10.1007/978-3-031-61034-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-61034-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-61033-2
Online ISBN: 978-3-031-61034-9
eBook Packages: Computer ScienceComputer Science (R0)