All Issue

2026 Vol.61, Issue 2
Exploring Crowd Evacuation Patterns Using Agent-Based Model: The Case Study of Gocheok Sky Dome

에이전트 기반 모델을 활용한 군중 대피 패턴 분석 - 고척 스카이돔을 사례로 -

Jungho Choia
,
Jeon-Young Kangb*
최 정호a
,
강 전영b*
aUndergraduate Student, Department of Geography, Kyung Hee University
bAssistant Professor, Department of Geography･Department of Climate-Social Science Convergence, Kyung Hee University
a경희대학교 지리학과 학부과정
b경희대학교 지리학과･기후사회과학융합학과 조교수
*Corresponding Author
30 April 2026. pp. 161-173
PDF XML Citation
Abstract

Large sports arenas are prone to mass-casualty incidents during fires or terrorist attacks because high spectator densities interact with tightly spaced seat rows and steep, multi-level circulation. To quantify the spatiotemporal evacuation vulnerability that emerges from the interaction of crowd density and seat layout, this study develops an Agent-Based Model (ABM) of the Gocheok Sky Dome. The ABM represents individual pedestrians with rule-based movement and local interactions, enabling emergent congestion to evolve through time and space. We simulate multiple crowd-density levels and evaluate evacuation time and spatiotemporal patterns. Under high-density conditions, congestion intensified around key nodes, and detouring behavior emerged. In the medium-density range (40–60%), run-to-run variance is the largest, suggesting substantial potential to improve egress performance through routing design and seat/section allocation. By linking occupancy to emergent patterns, the results provide a basis for safer and more efficient evacuation scenario design for large sports stadiums.

Keywords
Geosimulation
Agent-Based Model
Evacuation Simulation
Stadium Evacuation
Spacetime Kernel Density Estimation

대형 실내 스포츠 경기장은 화재･테러 등 재난 발생 시 관람객 밀집으로 대형 참사로 이어질 위험이 크므로, 좌석 열이 촘촘하고 경사가 큰 다층 구조를 고려한 효율적 대피 시나리오 구축이 필요하다. 관중 밀도와 좌석 위치에 따른 건물 구조–관중 상호작용이 만들어내는 시공간적 대피 취약성을 규명하기 위해, 본 연구는 에이전트 기반 모델링(Agent-Based Modeling, ABM)으로 고척스카이돔의 관중 밀도를 중심으로 대피 시간과 시공간 패턴을 분석하였다. ABM은 개별 보행자의 규칙과 상호작용을 반영해 창발적 혼잡의 시공간 전개를 재현할 수 있다. 그 결과, 고밀도 조건에서는 주요 결절점의 혼잡이 심화되며 우회 현상이 나타났고, 40-60% 중밀도 구간에서는 시행 간 분산이 크게 나타나 동선 설계 및 좌석 배치 조정을 통해 개선할 여지가 확인되었다. 본 연구는 관중 밀도와 공간구조의 상호작용이 만들어내는 패턴을 제시함으로써, 안전하고 효율적인 대피 시나리오 설계에 기초자료를 제공하고자 한다.

키워드
공간 시뮬레이션
에이전트 기반 모델
대피 시뮬레이션
경기장 대피
시공간 커널밀도
References
1

강전영･신혜섭･최문기, 2024, “공간 시뮬레이션 모델(Geosimulation Model)과 활용 분야: 질병 및 보건, 재해 대피, 도시 교통,” 대한지리학회지, 59(3), 417-430.

10.22776/kgs.2024.59.3.417
2

김동범･김혜민･전철민, 2024, “패닉 상황을 고려한 동적 인지 에이전트 기반 화재 대피 시뮬레이션,” 대한공간정보학회지, 32(2), 59-66.

10.7319/kogsis.2024.32.2.059
3

김민준･강전영, 2022, “서울시의 도시홍수 관련 임시대피시설의 공간적 분포 탐색,” 국토지리학회지, 56(3), 235-244.

10.22905/kaopqj.2022.56.3.7
4

김주성･송명신･강승민, 2014, “화재에 노출된 인간의 대피거동에 대한 Modeling 해석,” 한국방재학회 학술대회, 인천, 2월 19일, 350.

5

이재영, 2020, 화재 확산을 고려한 실내 화재 대피 시뮬레이션, 서울시립대학교 석사학위논문.

6

조성진, 2014, 프로스포츠 경기장의 안전성 분석을 위한 피난 시뮬레이션 적용, 국민대학교 석사학위논문.

7

조장원･배종환･유현배･박선희, 2025, “A* 알고리즘을 활용한 재난 상황 대피경로 탐색,” 디지털콘텐츠학회 논문지, 26(3), 685-691.

10.9728/dcs.2025.26.3.685
8

최문기･박진우･지상훈, 2022, “행위자 기반 모델을 활용한 인구과밀 및 병목현상의 위험성 분석,” 대한지리학회지, 57(6), 595-609.

10.22776/kgs.2022.57.6.595
9

한국공예･디자인문화진흥원, 고척스카이돔 안전안심 프로젝트 사진, 2020년 2월 19일 수정, https://blog.naver.com/kcdf2010/221815479167, 2026년 2월 12일 접속.

10

Chen, X., Meaker, J. W. and Zhan, F. B., 2006, “Agent-based modeling and analysis of hurricane evacuation procedures for the Florida Keys,” Natural Hazards, 38(3), 321-338.

10.1007/s11069-005-0263-0
11

Choi, M. and Hohl, A., 2021, Investigating spatiotemporal indoor contact patterns using ABM and STKDE, 4th ACM SIGSPATIAL International Workshop on GeoSpatial Simulation, New York, 11월 2일, 1-8.

10.1145/3486184.3491077
12

Choi, M. and Hohl, A., 2023, Investigating factors in indoor transmission of respiratory disease through agent‐based modeling, Transactions in GIS, 27(6), 1794-1827.

10.1111/tgis.13099
13

Chris, B., Jonathan C. and Gary H., 2007, Visualising space and time in crime patterns: A comparison of methods, Computers, Environment and Urban Systems, 31(1), 52-75.

10.1016/j.compenvurbsys.2005.07.009
14

Cotfas, L. A., Delcea, C., Iancu, L. D., Ioanăş, C. and Ponsiglione, C., 2022, Large event halls evacuation using an agent-based modeling approach, IEEE Access, 10, 49359-49384.

10.1109/ACCESS.2022.3172285
15

Crooks, A., Heppenstall, A., Manley, E. and Malleson, N., 2018, Agent-Based Modelling and Geographical Information Systems: A Practical Primer, SAGE, Thousand Oaks.

10.4135/9781529793543
16

Delmelle, E., Dony, C., Casas, I., Jia, M. and Tang, W., 2014, “Visualizing the impact of space-time uncertainties on dengue fever patterns, International Journal of Geographical Information Science, 28(5), 1107-1127.

10.1080/13658816.2013.871285
17

Hwang, S., Rhim, H., Kang, J. Y. and Choi, J., 2026, Exploring the inequality of the particulate matter exposure level of public bicycle scheme users using an agent-based model, Computers, Environment and Urban Systems, 123, 102367.

10.1016/j.compenvurbsys.2025.102367
18

Islas-Toski, M., Cuevas, E., Pérez-Cisneros, M. and Escobar, H., 2024, Agent-based evacuation modeling: Enhancing building safety in emergency scenarios, Smart Cities, 7(6), 3165-3187.

10.3390/smartcities7060123
19

Jiang, N., Crooks, A. T., Kavak, H., Burger, A. and Kennedy, W. G., 2022, A method to create a synthetic population with social networks for geographically-explicit agent-based models, Computational Urban Science, 2(1), 7.

10.1007/s43762-022-00034-1
20

Kang, J. Y. and Aldstadt, J, 2021, Using multiple scale space-time patterns to determine the number of replicates and burn-in periods in spatially explicit agent-based modeling of vector-Borne disease transmission, ISPRS International Journal of Geo-Information, 10(9), 604.

10.3390/ijgi10090604
21

Kang, J. Y. and Aldstadt, J., 2019a, Using multiple scale spatio-temporal patterns for validating spatially explicit agent-based models, International Journal of Geographical Information Science, 33(1), 193-213.

10.1080/13658816.2018.153512131695574PMC6834355
22

Kang, J. Y. and Aldstadt, J., 2019b, Using multiple scale space-time patterns in variance-based global sensitivity analysis for spatially explicit agent-based models, Computers, Environment and Urban Systems, 75, 170-183.

10.1016/j.compenvurbsys.2019.02.00631728075PMC6855397
23

Kang, J. Y. and Aldstadt, J., 2020, A CyberGIS approach to spatiotemporally explicit uncertainty and global sensitivity analysis for agent-based modeling of vector-borne disease transmission, Annals of the American Association of Geographers, 110(6), 1855-1873.

10.1080/24694452.2020.172340035106407PMC8803269
24

Kang, J. Y., Michels, A., Crooks, A., Aldstadt, J. and Wang, S., 2022, An integrated framework of global sensitivity analysis and calibration for spatially explicit agent‐based models, Transactions in GIS, 26(1), 100-128.

10.1111/tgis.12837
25

Wu, K., Sun, H., Zhu, Z., Hu, H., Xu, J., Zhu, K., Zhang, X. and Zhang, T, 2025, Experimental study on the emergency evacuation behavior in building with bottleneck group, Journal of Building Engineering, 106, 112576.

10.1016/j.jobe.2025.112576
26

Makinoshima, F. and Oishi, Y., 2022, Crowd flow forecasting via agent-based simulations with sequential latent parameter estimation from aggregate observation, Scientific Reports, 12(1), 11168.

10.1038/s41598-022-14646-435778445PMC9249888
27

Moyaux, T., Liu, Y., Bouleux, G. and Cheutet, V., 2023, An agent-based architecture of the digital twin for an emergency department, Sustainability, 15(4), 3412.

10.3390/su15043412
28

Van Haeringen, E. S., Gerritsen, C. and Hindriks, K. V., 2023, Emotion contagion in agent-based simulations of crowds: A systematic review, Autonomous Agents and Multi-Agent Systems, 37(1), 6.

10.1007/s10458-022-09589-z
29

Vandewalle, R., Kang, J. Y., Yin, D. and Wang, S., 2019, Integrating CyberGIS-Jupyter and spatial agent-based modelling to evaluate emergency evacuation time, 2nd ACM SIGSPATIAL International Workshop on GeoSpatial Simulation, Chicago Illinois, 5, November, 28-31.

10.1145/3356470.3365530
30

Zhang, X., Dunn, S., Luo, Y. and Shen, Y., 2025, Integrating human behaviors in an agent-based model for multi-floor building emergency evacuation, Journal of Building Engineering, 112, 113716.

10.1016/j.jobe.2025.113716
Information
  • Publisher :The Korean Geographical Society
  • Publisher(Ko) :대한지리학회
  • Journal Title :Journal of the Korean Geographical Society
  • Journal Title(Ko) :대한지리학회지
  • Volume : 61
  • No :2
  • Pages :161-173
  • Received Date : 2025-12-30
  • Revised Date : 2026-03-04
  • Accepted Date : 2026-03-13
  • DOI :https://doi.org/10.22776/kgs.2026.61.2.161
Journal Informaiton Journal of the Korean Geographical Society Journal of the Korean Geographical Society
online submission
  • NRF
  • KISTI Current Status
  • KISTI Cited-by
  • KCI 문헌 유사도 검사
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close