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

Korean Geo-Environmental Society (한국지반환경공학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Machine Learning Model to Predict the Ground Subsidence Risk Grade According to the Characteristics of Underground Facility

지하매설물 속성을 활용한 기계학습 기반 지반함몰 위험도 예측모델 개발

  • Lee, Sungyeol (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Kang, Jaemo (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Kim, Jinyoung (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology)
  • Received : 2022.05.20
  • Accepted : 2022.06.14
  • Published : 2022.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

Ground Subsidence has been continuously occurring in densely populated downtown. The main cause of ground subsidence is the damaged underground facility like sewer. Currently, ground subsidence is being dealt with by discovering cavities in ground using GPR. However, this consumes large amount of manpower and cost, so it is necessary to predict hazardous area for efficient operation of GPR. In this study, ◯◯city is divided into 500 m×500 m grids. Then, data set was constructed using the characteristics of the underground facility and ground subsidence in grids. Data set used to machine learning model for ground subsidence risk grade prediction. The purposed model would be used to present a ground subsidence risk map of target area.

인구 밀집도가 높은 도시 중심지에서 발생하는 지반함몰의 주요 원인은 하수관 및 상수관과 같은 지하매설물의 손상으로 알려져 있다. 이와 관련하여 지반함몰의 원인 규명과 지반함몰 위험 예측에 관한 연구가 꾸준히 수행되고 있다. 현재 지반함몰은 지중탐사레이더를 통해 선제적으로 공동을 발견하여 대응하고 있으나, 이는 인력 및 비용의 소비가 크기 때문에 효율적인 장비의 운영을 위해 위험지역을 예측하고 예측된 지역을 우선순위로 탐사해야 할 필요가 있다. 따라서 본 연구에서는 ◯◯시의 2개 구를 500m×500m 크기의 그리드로 분할하고, 해당 그리드 내의 지하매설관 속성과 지반함몰 발생 데이터를 활용하여 데이터셋을 구축하였다. 구축된 데이터셋으로 기계학습을 통한 적절한 지반함몰 위험등급 예측 모델을 제시하였고, 제시된 모델을 활용하여 대상지역의 지반함몰 위험지도를 제시하고자 하였다.

Keywords

Acknowledgement

본 연구는 (22주요-대1-임무)지하 공간 정보 정확도 개선 및 매설관 안전관리 기술개발 (3/3) 지원으로 수행되었으며, 이에 깊은 감사를 드립니다.

References

  1. Breiman, L. (2001), Random Forest. Machine Leaerning, Kluwer Academic Publishers, 45, pp. 5~32.
  2. G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye and T. Liu. (2017), LightGBM: A Highly Efficient Gradient Boosting Decision Tree, Part of Advances in Neural Information Processing Systems 30.
  3. Ha, J. E., Shin, H. C. and Lee, Z. K. (2017), Korean text classification using randomforest and XGBoost focusing on Seoul metropolitan civil complaint data, The Journal of Bigdata, Vol. 2, Issue 2, pp. 95~104. https://doi.org/10.36498/kbigdt.2017.2.2.95
  4. 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).
  5. Jin, Y. S. (2020), The Analysis on Correlation of Precipitation and Risk Factors to the Soil Subsidence, Ph D. dissertation, Chonnam National University, pp. 104~105 (In Korean).
  6. Kim, K. Y. (2018), Susceptibility Model for Sinkholes Caused by Damaged Sewer Pipes Based on Logistic Regression, Master's thesis, Seoul National University.
  7. 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.
  8. 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 characteristics of sewer, Journal of Korean Geo-Environmental Society, Vol. 23, Issue 4, pp. 5~10.
  9. 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.
  10. Seoul Seokchon-dong Cavity Cause Investigation Committee, (2014), Cause Analysis of Cavity at Seokchon Underground Roadway and Road Cavity.
  11. Seoul Institute (2016), The Road Subsidence Conditions and Safety Improvement Plans in Seoul (In Korean).
  12. 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