Applied Intelligence

, Volume 42, Issue 1, pp 3–23 | Cite as

A spatio-temporal probabilistic model of hazard- and crowd dynamics for evacuation planning in disasters

  • Jaziar Radianti
  • Ole-Christoffer Granmo
  • Parvaneh Sarshar
  • Morten Goodwin
  • Julie Dugdale
  • Jose J. Gonzalez
Article

Abstract

Managing the uncertainties that arise in disasters – such as a ship or building fire – can be extremely challenging. Previous work has typically focused either on modeling crowd behavior, hazard dynamics, or targeting fully known environments. However, when a disaster strikes, uncertainties about the nature, extent and further development of the hazard is the rule rather than the exception. Additionally, crowds and hazard dynamics are both intertwined and uncertain, making evacuation planning extremely difficult. To address this challenge, we propose a novel spatio-temporal probabilistic model that integrates crowd and hazard dynamics, using ship- and building fire as proof-of-concept scenarios. The model is realized as a dynamic Bayesian network (DBN), supporting distinct kinds of crowd evacuation behavior, being based on studies of physical fire models, crowd psychology models, and corresponding flow models. Simulation results demonstrate that the DBN model allows us to track and forecast the movement of people until they escape, as the hazard develops from time step to time step. Our scheme thus opens up for novel in situ threat mapping and evacuation planning under uncertainty, with applications to emergency response.

Keywords

Dynamic bayesian networks Evacuation planning Crowd modeling Hazard modeling 

References

  1. 1.
    Woodrow B (2012) Fire as vulnerability: the value added from adopting a vulnerability approach, vol 28. World Fire Statistics Bulletin, Valéria PacellaGoogle Scholar
  2. 2.
    MacGregor Smith J (1991) State-dependent queueing models in emergency evacuation networks. Transportation res Part B: Methodological 25(6):373–389. doi:10.1016/0191-2615(91)90031-D CrossRefGoogle Scholar
  3. 3.
    Hedman GE (2011) Travel along stairs by individuals with disabilities: a summary of devices used during routine travel and travel during emergencies. In: Peacock R D, Kuligowski E D, Averill J D (eds) Pedestrian and evacuation dynamics. Springer US, pp 109–119Google Scholar
  4. 4.
    Larusdottir AR, Dederichs AS (2011) Evacuation dynamics of children – walking speeds, flows through doors in daycare centers. In: Peacock R D, Kuligowski E D, Averill J D (eds) pedestrian and evacuation dynamics. Springer US, pp 139–147Google Scholar
  5. 5.
    Adams APM, Galea ER (2011) An Experimental evaluation of movement devices used to sssist people with reduced mobility in high-rise building evacuations. In: Peacock R D, Kuligowski E D, Averill J D (eds) Pedestrian and evacuation dynamics. Springer US, pp 129–138Google Scholar
  6. 6.
    Liu S, Yang L, Fang T, Li J (2009) Evacuation from a classroom considering the occupant density around exits. Phys A: Statistical Mechanics and its Applications 388(9):1921–1928. doi:10.1016/j.physa.2009.01.008 CrossRefGoogle Scholar
  7. 7.
    Wang JH, Lo SM, Sun JH, Wang QS, Mu H-l (2012) Qualitative simulation of the panic spread in large-scale evacuation. Simulation 88(12):1465–1474. doi:10.1177/0037549712456884 CrossRefGoogle Scholar
  8. 8.
    Musse SR, Jung CR, Jacques JCS, Braun A (2007) Using computer vision to simulate the motion of virtual agents. Computer Anim and Virtual Worlds 18(2):83–93. doi:10.1002/cav.163 CrossRefGoogle Scholar
  9. 9.
    Braun A, Bodmann BEJ, Musse SR (2005) Simulating virtual crowds in emergency situations. Paper presented at the Proceedings of the ACM symposium on Virtual reality software and technology, MontereyGoogle Scholar
  10. 10.
    Helbing D, Farkas I, Vicsek T (2000) Simulating dynamical features of escape panic. Nature 407(6803):487–490CrossRefGoogle Scholar
  11. 11.
    Thompson PA, Marchant EW (1995) A computer model for the evacuation of large building populations. Fire Saf J 24(2):131–148. doi:10.1016/0379-7112(95)00019-p CrossRefGoogle Scholar
  12. 12.
    Choi J, Hwang H, Hong W (2011) Predicting the probability of evacuation congestion occurrence relating to elapsed time and vertical section in a high-rise building. In: Peacock R D, Kuligowski E D, Averill J D (eds) Pedestrian and evacuation dynamics. Springer US, pp 37–46Google Scholar
  13. 13.
    Georgiadou PS, Papazoglou IA, Kiranoudis CT, Markatos NC (2007) Modeling emergency evacuation for major hazard industrial sites. Reliability Eng Syst Saf 92(10):1388–1402. doi:10.1016/j.ress.2006.09.009 CrossRefGoogle Scholar
  14. 14.
    Murphy KP (2002) Dynamic bayesian networks : representation, inference and learning. Dissertation. University of California, BerkeleyGoogle Scholar
  15. 15.
    Daganzo CF, So SK (2011) Managing evacuation networks. Transportation Res Part B: Methodological 45(9):1424–1432. doi:10.1016/j.trb.2011.05.015 CrossRefGoogle Scholar
  16. 16.
    CIEM SmartRescue Project. http://ciem.uia.no/project/smartrescue. Accessed 15 June 2014Google Scholar
  17. 17.
    Jarque CM, Bera AK (1980) Efficient tests for normality, homoscedasticity and serial independence of regression residuals. Econ Lett 6(3):255–259. doi:10.1016/0165-1765(80)90024-5 CrossRefMathSciNetGoogle Scholar
  18. 18.
    Lorenz J, Rauhut H, Schweitzer F, Helbing D (2011) How social influence can undermine the wisdom of crowd effect. Proc Natl Acad Sci USA 108(22):9020–9025. doi:10.1073/pnas.1008636108 CrossRefGoogle Scholar
  19. 19.
    Vorst HCM (2010) Evacuation models and disaster psychology. Procedia Eng 3(0):15–21. doi:10.1016/j.proeng.2010.07.004 CrossRefGoogle Scholar
  20. 20.
    Kobes M, Helsloot I, de Vries B, Post JG (2010) Building safety and human behaviour in fire: A literature review. Fire Saf J 45(1):1–11. doi:10.1016/j.firesaf.2009.08.005 CrossRefGoogle Scholar
  21. 21.
    Pires TT (2005) An approach for modeling human cognitive behavior in evacuation models. Fire Saf J 40(2):177–189. doi:10.1016/j.firesaf.2004.10.004 CrossRefGoogle Scholar
  22. 22.
    Weidlich W, Helbing D (1998) A mathematical model of group dynamics including the effects of solidarity. In: Doreian P, Fararo T (eds) The problem of solidarity: Theories and models. Gordon and Breach, London, pp 139–196Google Scholar
  23. 23.
    Helbing D, Molnár P (1995) Social force model for pedestrian dynamics. Phys Rev E 51(5):4282–4286CrossRefGoogle Scholar
  24. 24.
    Helbing D (1992) A fluid-dynamic model for the movement of pedestrians. Complex Syst 6:391–415MathSciNetMATHGoogle Scholar
  25. 25.
    Burger M, Markowich PA, Pietschmann JF (2011) Continuous limit of a crowd motion and herding model: analysis and numerical simulations. Kinet Relat Models 4(4):1025–1047. doi:10.3934/krm.2011.4.1025 CrossRefMathSciNetMATHGoogle Scholar
  26. 26.
    Helbing D (2009) Pattern formation, social forces, and diffusion instability in games with success-driven motion. Eur Phys J B 67(3):345–356. doi:10.1140/epjb/e2009-00025-7 CrossRefMathSciNetMATHGoogle Scholar
  27. 27.
    Zhao DL, Yang LZ, Li J (2008) Occupants’ behavior of going with the crowd based on cellular automata occupant evacuation model. Physica a-Statistical Mechanics and Its Applications 387(14):3708–3718. doi:10.1016/j.physa.2008.02.042 CrossRefGoogle Scholar
  28. 28.
    Maury B, Venel J (2008) A mathematical framework for a crowd motion model. Comptes Rendus Math 346(23-24):1245–1250. doi:10.1016/j.crma.2008.10.014 CrossRefMathSciNetMATHGoogle Scholar
  29. 29.
    Zhou S, Chen D, Cai W, Luo L, Low MYH, Tian F, Tay VS-H, Ong DWS, Hamilton B D (2010) owd modeling and simulation technologies. ACM Trans Model Comput Simul 20(4):1–35. doi:10.1145/1842722.1842725 CrossRefGoogle Scholar
  30. 30.
    Aguirre BE, El-Tawil S, Best E, Gill KB, Fedorov V (2011) Contributions of social science to agent-based models of building evacuation. Contemp Soc Sci 6(3):415–432. doi:10.1080/21582041.2011.609380 CrossRefGoogle Scholar
  31. 31.
    Eleye-Datubo AG, Wall A, Saajedi A, Wang J (2006) Enabling a powerful marine and offshore decision-support solution through Bayesian Network technique. Risk Anal 26(3):695–721. doi:10.1111/j.1539-6924.2006.00775.x CrossRefGoogle Scholar
  32. 32.
    Kruger M, Ziegler L, Heller KA generic Bayesian Network for identification and assessment of objects in maritime surveillance. In: Inf. Fusion (FUSION), 2012 15th International Conference on, 9-12 July 2012, pp 2309–2316Google Scholar
  33. 33.
    Chaze X, Bouejla A, Napoli A, Guarnieri F, Eude T, Alhadef B (2012) Database Systems for Advanced Applications, vol 7240. Lecture Notes in Computer Science. In: Yu H, Yu G, Hsu W, Moon Y-S, Unland R, Yoo J (eds). Springer, Berlin, pp 81–91Google Scholar
  34. 34.
    Pilato G, Augello A, Missikoff M, Taglino F Integration of ontologies and Bayesian Networks for maritime situation awareness. In: Semantic Computing (ICSC), 2012 IEEE Sixth International Conference on, 19-21 Sept. 2012 2012. pp 170–177Google Scholar
  35. 35.
    Akhtar MJ, Utne IB (2014) Human fatigue’s effect on the risk of maritime groundings – A Bayesian Networkmodeling approach. Saf Sci 62(0):427–440. doi:10.1016/j.ssci.2013.10.002 CrossRefGoogle Scholar
  36. 36.
    Friis-Hansen A (2000) Bayesian networks as a decision support tool in marine applicationsGoogle Scholar
  37. 37.
    Faber MH, Kroon IB, Kragh E, Bayly D, Decosemaeker P (2002) Risk Assessment of Decommissioning Options Using Bayesian Networks. J Offshore Mechanics Arctic Eng 124:231CrossRefGoogle Scholar
  38. 38.
    Cheng H, Hadjisophocleous GV (2011) Dynamic modeling of fire spread in building. Fire Saf J mag 46(4):211–224. doi:10.1016/j.firesaf.2011.02.003 CrossRefGoogle Scholar
  39. 39.
    Charniak E (1991) Bayesian Networks without Tears. AI Mag 12(4):50–63Google Scholar
  40. 40.
    Pearl J (1988) Probabilistic reasoning in intelligent systems : networks of plausible inference. The Morgan Kaufman series in representation and reasoning. Morgan Kaufmann Publishers, San MateoGoogle Scholar
  41. 41.
    DSL GeNIe (Graphical Network Interface) and SMILE (Structural Modeling, Inference, and Learning Engine). University of Pittsburg. http://genie.sis.pitt.edu/. Accessed June, 15 2014
  42. 42.
    Jian C, Marek JD (2000) AIS-BN: An adaptive importance sampling algorithm for evidential reasoning in large bayesian networks. J Artif Intell Res 13(1):155–188Google Scholar
  43. 43.
    Yuan C, Druzdzel MJ (2003) An importance sampling algorithm based on evidence pre-propagation. Paper presented at the Proceedings of the Nineteenth conference on Uncertain. in Artificial Intell., AcapulcoGoogle Scholar
  44. 44.
    Proulx G (2008) Evacuation Time. In: The SFPE Handbook of Fire Protection Engineering. National fire Protection Association, QuincyGoogle Scholar
  45. 45.
    Purser D (2010) Comparisons of evacuation efficiency and pre-travel activity times in response to a sounder and two different voice alarm messages. In: Klingsch W W F, Rogsch C, Schadschneider A, Schreckenberg M (eds) Pedestrian and evacuation dynamics 2008. Springer, Berlin, pp 121–134CrossRefGoogle Scholar
  46. 46.
    Choi J, Kim M (2007) Evacuation efficiency evaluation model based on euclidean distance with visual depth. In: Proceeding of the 6th Int. Space Syntax Symp., İstanbulGoogle Scholar
  47. 47.
    IMO (2007) Interim guidelines for evacuation analyses for new and existing passenger ships. MSC/Circ. 1033Google Scholar
  48. 48.
    The National Institute of Standards and Technology (NIST). Fire dynamics simulators and smokeview (FDS-SMV), https://code.google.com/p/fds-smv/. Accessed 15 June 2014Google Scholar
  49. 49.
    Peng Y, Zhang S, Pan R (2010) Bayesian network reasoning with uncertain evidences. Int J Uncertain, Fuzziness Knowl-Based Syst 18(05):539–564CrossRefMathSciNetMATHGoogle Scholar
  50. 50.
    Granmo O-C, Radianti J, Goodwin M, Dugdale J, Sarshar P, Glimsdal S, Gonzalez J (2013) A Spatio-temporal probabilistic model of hazard and crowd dynamics in disasters for evacuation planning. In: Ali M, Bosse T, Hindriks K, Hoogendoorn M, Jonker C, Treur J (eds) Recent Trends in Applied Artificial Intelligence., vol 7906. Lecture notes in computer science. Springer, Berlin, pp 63–72Google Scholar
  51. 51.
    Goodwin M, Granmo O-C, Radianti J (2014) Escape planning in realistic fire scenarios with Ant Colony Optimisation. Appl Intell:1–12. doi:10.1007/s10489-014-0538-9

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Jaziar Radianti
    • 1
  • Ole-Christoffer Granmo
    • 1
  • Parvaneh Sarshar
    • 1
  • Morten Goodwin
    • 1
  • Julie Dugdale
    • 1
    • 2
  • Jose J. Gonzalez
    • 1
  1. 1.Centre for Integrated Emergency ManagementUniversity of Agder GrimstadAgder GrimstadNorway
  2. 2.Grenoble 2 University/Grenoble Informatics Laboratory (LIG)GrenobleFrance

Personalised recommendations