한국지반환경공학회 논문집 (Journal of the Korean GEO-environmental Society)

  • 제24권4호
  • /
  • Pages.23-29
  • /
  • 2023
  • /
  • 1598-0820(pISSN)
  • /
  • 2714-1233(eISSN)
한국지반환경공학회 (Korean Geo-Environmental Society)
권호 표지
DOI QR코드

DOI QR Code

기계학습 기반 지하매설물 속성 및 밀집도를 활용한 지반함몰 위험도 예측 모델

Ground Subsidence Risk Grade Prediction Model Based on Machine Learning According to the Underground Facility Properties and Density

  • Sungyeol Lee (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Jaemo Kang (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Jinyoung Kim (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology)
  • 투고 : 2023.02.15
  • 심사 : 2023.03.09
  • 발행 : 2023.04.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

지반함몰의 주요 발생원인은 지하매설물의 손상으로 알려져 있다. 지반함몰은 상·하수관의 손상으로 인한 물길 형성에 따른 지반 내 토립자의 이동으로 공동이 형성되어 상부지반이 붕괴되는 메커니즘을 보이고 있다. 따라서 지반함몰은 지하매설물의 밀집도가 높은 도심지를 중심으로 발생하고 있으며, 사고 발생 시 인명 및 경제적 피해를 야기하므로 사고에 대한 대비가 반드시 필요하다. 이에 따라 지반함몰 위험을 예측하기 위한 연구가 꾸준히 수행되고 있으며, 본 연구에서는 ○○시의 2개 구를 대상으로 지반함몰 위험도 예측 모델을 제시하고자 하였다. 대상 지역의 지하매설물 속성 데이터(활용년수, 관직경)와 지하매설물 밀집도, 지반함몰 이력 데이터를 활용하여 데이터셋을 구축하고 전처리를 수행한 뒤, 기계학습 모델에 적용하여 최적의 평가지표가 도출되는 모델을 선정하였으며, 선정된 모델의 신뢰도를 평가하고 모델에서 도출되는 지반함몰 위험도 예측 시 활용된 영향인자의 중요도를 제시하고자 하였다.

Ground subsidence shows a mechanism in which the upper ground collapses due to the formation of a cavity due to the movement of soil particles in the ground due to the formation of a waterway because of damage to the water supply/sewer pipes. As a result, cavity is created in the ground and the upper ground is collapsing. Therefore, ground subsidence frequently occurs mainly in downtown areas where a large amount of underground facilities are buried. Accordingly, research to predict the risk of ground subsidence is continuously being conducted. This study tried to present a ground subsidence risk prediction model for two districts of ○○ city. After constructing a data set and performing preprocessing, using the property data of underground facilities in the target area (year of service, pipe diameter), density of underground facilities, and ground subsidence history data. By applying the dataset to the machine learning model, it is evaluated the reliability of the selected model and the importance of the influencing factors used in predicting the ground subsidence risk derived from the model is presented.

키워드

과제정보

본 연구는 (23주요-대1-임무)지하 공간 정보 정확도 개선 및 매설관 안전관리 기술개발 (4/4) 지원으로 수행되었으며, 이에 깊은 감사를 드립니다.

참고문헌

  1. Breiman, L., Friedman, J., Stone, C. and Olshen, R. (1984), Classification and regression trees, Taylor & Francis. 
  2. Chen, T. and Guestrin, C. (2016), XGBoost: A Scalable Tree Boosting System, KDD'16 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785~794. 
  3. Han, M. S. (2017), A risk assessment of ground subsidence by GPR and CCTV investigation, Master's thesis, Seoul National University of Science and Technology (In Korean). 
  4. Jin, Y. S. (2018), The Analysis on Correlation of Precipitation and Risk Factors to the Soil Subsidence, Ph D. dissertation, Chonnam National University, pp. 104~105 (In Korean). 
  5. Kim, J. Y., Kang, J. M., Choi, C. H. and Park, D. H. ( 2017), Correlation analysis of sewer integrity and ground subsidence, Journal of the Korean Geo-Environmental Society, Vol. 18, No.6, pp. 31~37 (In Korean).  https://doi.org/10.14481/jkges.2017.18.1.31
  6. Kim, J. Y., Kang, J. M. and Choi, C. H. ( 2021), Correlation analysis of the occurrence of ground subsidence according to the density of underground pipelines, Journal of the Korean Geo-Environmental Society, Vol. 22, No. 11, pp. 23~29 (In Korean). 
  7. Kim, K. Y. (2018), Susceptibility Model for Sinkholes Caused by Damaged Sewer Pipes Based on Logistic Regression, Master's thesis, Seoul National University (In Korean). 
  8. Kuwano, R., Horii, T., Kohashi, H. and Yamauchi, K. (2006), Defects of sewer pipes causing cave-in's in the road, Proc. 5th International Symposium on New Technologies for Urban Safety of Mega Cities in Asia,Phuket, Thailand, pp. 347~353. 
  9. Lee, J. T. (2009), A Study on Multi-Class Classification Method Using Adaboost, Master's thesis, Hanyang University (In Korean). 
  10. Lee, S. H., Yoon, Y. A., Jung, J. H., Sim, H. S., Chang, T. W. and Kim, Y. S. (2020), A machine learning model for predicting silica concentrations through time series analysis of mining data, Journal of Korean Society for Quality Management, Vol. 48, No. 3, pp. 511~520 (In Korean).  https://doi.org/10.7469/JKSQM.2020.48.3.511
  11. Lee, S. Y., Kang, J. M. and Kim, J. Y. (2022), Development of machine learning model to predict the ground subsidence risk grade according to the Characteristics of underground facility, Journal of the Korean Geo-Environmental Society, Vol. 23, No. 4, pp. 5~10 (In Korean).  https://doi.org/10.14481/JKGES.2022.23.4.5
  12. Lee, S. Y., Kim, J. Y., K., J. M. and Baek, W. J. (2022), Comparison of machine learning models to predict the occurrence of ground subsidence according to the gharacteristics of sewer, Journal of Korean Geo-Environmental Society, Vol. 23, Issue. 4, pp. 5~10 (In Korean). 
  13. Mukunoki, T., Kuwano, N., Otani, J. and Kuwano, R. (2009), Visualization of three dimensional failure in sand due to water inflow and soil drainage from defected underground pipe using X-ray CT, Soils and Foundations, Vol. 49, No. 6. 
  14. Park, E. J., Park, J. H. and Kim, H. H. (2019), Mapping species-specific optimal plantation sites using random forest in Gyeongsangnam-do province, South Korea, Journal of Agriculture & Life Science, Vol. 53, No. 6, pp. 65~74 (In Korean). 
  15. Seoul Seokchon-dong Cavity Cause Investigation Committee (2014), Cause Analysis of Cavity at Seokchon Underground Roadway and Road Cavity Special Management Measures. 
  16. Takeuchi, D., Fukatani, W., Miyamoto, T. and Yokota, T. (2017), Using decision tree analysis to extract factors affecting road subsidence, Journal of the Japan sewage works association, Vol. 54, No. 657, pp. 124~133. 
  17. Tom Fawcett (2005), An introduction to ROC analysis, Patter Recognition Letters, Edited by Francesco Tortorella, Vol. 27 Issue 8, pp. 861~874.  https://doi.org/10.1016/j.patrec.2005.10.010