Journal of Industrial Convergence (산업융합연구)

DAEHAN Society of Industrial Management (대한산업경영학회)
권호 표지
DOI QR코드

DOI QR Code

District-Level Seismic Vulnerability Rating and Risk Level Based-Density Analysis of Buildings through Comparative Analysis of Machine Learning and Statistical Analysis Techniques in Seoul

머신러닝과 통계분석 기법의 비교분석을 통한 건물에 대한 서울시 구별 지진취약도 등급화 및 위험건물 밀도분석

  • Sang-Bin Kim (Department of Drone & GIS Engineering, Namseoul University) ;
  • Seong H. Kim (Department of Drone & GIS Engineering, Namseoul University) ;
  • Dae-Hyeon Kim (Data Science Lab, Korea Electric Power Corporation)
  • 김상빈 (남서울대학교 드론공간정보공학과) ;
  • 김성훈 (남서울대학교 드론공간정보공학과) ;
  • 김대현 (한국전력 데이터사이언스연구소)
  • Received : 2023.06.01
  • Accepted : 2023.07.20
  • Published : 2023.07.28
Download PDF
⟨ Previous Next ⟩

Abstract

In the recent period, there have been numerous earthquakes both domestically and internationally, and buildings in South Korea are particularly vulnerable to seismic design and earthquake damage. Therefore, the objective of this study is to discover an effective method for assessing the seismic vulnerability of buildings and conducting a density analysis of high-risk structures. The aim is to model this approach and validate it using data from pilot area(Seoul). To achieve this, two modeling techniques were employed, of which the predictive accuracy of the statistical analysis technique was 87%. Among the machine learning techniques, Random Forest Model exhibited the highest predictive accuracy, and the accuracy of the model on the Test Set was determined to be 97.1%. As a result of the analysis, the district rating revealed that Gwangjin-gu and Songpa-gu were relatively at higher risk, and the density analysis of at-risk buildings predicted that Seocho-gu, Gwanak-gu, and Gangseo-gu were relatively at higher risk. Finally, the result of the statistical analysis technique was predicted as more dangerous than those of the machine learning technique. However, considering that about 18.9% of the buildings in Seoul are designed to withstand the Seismic intensity of 6.5 (MMI), which is the standard for seismic-resistant design in South Korea, the result of the machine learning technique was predicted to be more accurate. The current research is limited in that it only considers buildings without taking into account factors such as population density, police stations, and fire stations. Considering these limitations in future studies would lead to more comprehensive and valuable research.

최근 국내‧외적으로 많은 지진이 발생하고 있는 상황에서, 우리나라의 건물은 내진설계 및 지진피해에 매우 취약한 상황이다. 따라서 현 연구의 목적은 건물에 대한 지진취약도 등급화 및 위험건물 밀도분석을 수행하는 효과적인 방법을 발굴하고 이를 모델화하여, 시범지역(서울시)자료를 활용해 검증해 보는데 있다. 이를 위해 활용된 두 가지 모델링 기법 중, 통계 분석 기법의 예측정확도는 87%였고, 머신러닝 기법은 Random Forest모델의 예측정확도가 가장 높았으며, 해당 모델의 Test Set 정확도는 97.1%로 도출되었다. 분석결과, 구별 등급화 결과는 광진구와 송파구가 상대적으로 위험하다고 예측되었으며, 위험건물 밀도분석은 서초구, 관악구, 강서구가 상대적으로 위험하다고 예측되었다. 최종적으로, 통계분석 기법을 활용한 분석결과가 머신러닝 기법을 활용한 분석결과보다 위험하게 도출되었으나, 우리나라에서는 지진 강도 6.5(MMI)가 내진설계의 기준인데, 서울시 건물의 약 18.9%가 내진설계 되어있는 것으로 확인된 것을 고려하면, 머신러닝 기법의 결과가 더 정확할 것으로 예측되었다. 현 연구는 인구 및 인프라와 경찰서, 소방서 등을 고려 않은 오직 건물만을 고려한 한계점이 있으며, 해당 한계를 포함해 수행하면 더욱 포괄적인 연구가 될 것이다.

Keywords

Acknowledgement

This research was supported a grant from geospatial information workforce development program funded by the Ministry of Land, Infrastructure and Transport of Korean in 2023 Government(2022-02-01)

References

  1. The Seoul Institute. (2017). Seoul's buildings, how well can they withstand earthquakes?. Seoul. https://www.seoul.go.kr/ 
  2. Kim, S. H., Kim, S. B., Kim, D. H. (2023). A Spatial Analysis of Seismic Vulnerability of Buildings Using Statistical and Machine Learning Techniques Comparative Analysis. Journal of Industrial Convergence, 21(1), 159-165. DOI : 10.22678/jic.2023.21.1.159 
  3. Koh, J. H., Kwon, J. H., & Choi, Y. S. (2005). Error Assessment of Attitude Determination Using Wireless Internet-Based DGPS. Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 23(3), 239-249. 
  4. Han, J., & Kim, J. (2019). A GIS-based seismic vulnerability mapping and assessment using AHP: A case study of Gyeongju, Korea. Korean Journal of Remote Sensing, 35(2), 217-228. DOI : 10.7780/KJRS.2019.35.2.2 
  5. Chun, Y. (2017). A Study on Earthquake Hazard Mapping using Risk Factors. Proc. of Korean Society for Geospatial Information Science, Seoul, Korea, May, 25-26. 
  6. Sun, C. G. (2009). Seismic zonation on site responses in Daejeon by building geotechnical information system based on spatial GIS framework. Journal of the Korean Geotechnical Society, 25(1), 5-19. DOI : 10.7843/kgs.2009.25.1.5 
  7. Federal Emergency Management Agency (US) (Ed.). (2015). Rapid visual screening of buildings for potential seismic hazards: a handbook. Government Printing Office. 
  8. Federal Emergency Management Agency (US) (Ed.). (2015). Rapid visual screening of buildings for potential seismic hazards: a handbook. a Handbook (Third Edition).Government Printing Office. 
  9. Catlin, A. C., & Pujol, S. (2015). NIST Disaster and Failure Studies Data Repository: The Chile Earthquake Database-Ground Motion and Building Performance Data from the 2010 Chile Earthquake-User Manual. 
  10. Kim, S. B., & Kim, S. H. (2020). A Development of a Seismic Vulnerability Model and Spatial Analysis for Buildings. Journal of the Korea Convergence Society, 11(10), 9-18. DOI : 10.15207/JKCS.2020.11.10.009 
  11. Rundle, J. B., Donnellan, A., Fox, G., Crutchfield, J. P., & Granat, R. (2021). Nowcasting earthquakes: Imaging the earthquake cycle in California with machine learning. Earth and Space Science, 8(12), e2021EA001757. 
  12. Bui, D. T., Hoang, N. D., & Samui, P. (2019). Spatial pattern analysis and prediction of forest fire using new machine learning approach of Multivariate Adaptive Regression Splines and Differential Flower Pollination optimization: A case study at Lao Cai province (Viet Nam). Journal of environmental management, 237, 476-487. 
  13. Harirchian, E., Jadhav, K., Kumari, V., & Lahmer, T. (2022). ML-EHSAPP: A prototype for machine learning-based earthquake hazard safety assessment of structures by using a smartphone app. European Journal of Environmental and Civil Engineering, 26(11), 5279-5299.  https://doi.org/10.1080/19648189.2021.1892829
  14. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.