DOI QR코드

DOI QR Code

손상 하수관으로 인한 지반함몰의 위험도 평가를 위한 랜덤 포레스트 모델 개발

Development of Random Forest Model for Sewer-induced Sinkhole Susceptibility

  • 김준영 (한남대학교 스마트융합공학부) ;
  • 강재모 (한국건설기술연구원 지반연구본부) ;
  • 백성하 (한국건설기술연구원 지반연구본부)
  • Kim, Joonyoung (Disivion of Smart Interdiscplinary Engrg., Hannam Univ.) ;
  • Kang, Jae Mo (Korea Institute of Civil Engrg. and Building Technology) ;
  • Baek, Sung-Ha (Korea Institute of Civil Engrg. and Building Technology)
  • 투고 : 2021.12.07
  • 심사 : 2021.12.17
  • 발행 : 2021.12.31

초록

시민의 안전을 위협하는 지반재해 중 하나인 지반함몰이 최근 도심지에서 빈번하게 보고되고 있다. 다양한 지반함몰 발생 메커니즘 중, 하수관 손상부를 통한 토사 유실이 서울시에서 발생하는 지반함몰의 주요원인으로 나타났다. 본 연구에서는 서울시 하수관 정보와 지반함몰이 발생한 위치 정보를 기반으로 머신러닝 기법 중 하나인 랜덤 포레스트 알고리즘을 이용하여 하수관 정보로부터 손상 하수관으로 유발되는 지반함몰의 발생 여부를 예측하는 모델을 학습하였다. 모델 성능 평가 결과, 본 연구에서 도출한 모델이 지반함몰을 상당히 훌륭하게 예측할 수 있는 것으로 나타났다. 또한, 입력변수로 사용한 하수관 정보 중 하수관 길이, 해발고도, 경사, 매립 심도, 하수관 순서로 지반함몰 발생 위험에 영향을 미치는 것을 확인하였다. 본 연구의 결과는 지반함몰 위험도 지도 작성, 지하공동 탐사 계획 수립 및 하수관 정비 사업 계획 수립의 기초 자료로 활용될 수 있을 것으로 기대된다.

The occurrence of ground subsidence and sinkhole in downtown areas, which threatens the safety of citizens, has been frequently reported. Among the various mechanisms of a sinkhole, soil erosion through the damaged part of the sewer pipe was found to be the main cause in Seoul. In this study, a random forest model for predicting the occurrence of sinkholes caused by damaged sewer pipes based on sewage pipe information was trained using the information on the sewage pipe and the locations of the sinkhole occurrence case in Seoul. The random forest model showed excellent performance in the prediction of sinkhole occurrence after the optimization of its hyperparameters. In addition, it was confirmed that the sewage pipe length, elevation above sea level, slope, depth of landfill, and the risk of ground subsidence were affected in the order of sewage pipe information used as input variables. The results of this study are expected to be used as basic data for the preparation of a sinkhole susceptibility map and the establishment of an underground cavity exploration plan and a sewage pipe maintenance plan.

키워드

과제정보

본 연구는 한국건설기술연구원 주요사업 '(21주요-대1-임무)지하 공간 정보 정확도 개선 및 매설관 안전관리기술개발(2/3)'의 지원으로 수행되었으며, 이에 깊은 감사를 드립니다.

참고문헌

  1. Bae, Y., Shin, S.,Won, J., and Lee, D. (2016), "The Road Subsidence Conditions and Safety Improvement Plans in Seoul", 2016-PR-09, The Seoul Institute.
  2. Chen, W., Xie, X., Wang, J., Pradhan, B., Hong, H., Bui, D. T.,... and Ma, J. (2017), A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility, Catena, Vol.151, pp. 147-160. https://doi.org/10.1016/j.catena.2016.11.032
  3. Guo, S., Shao, Y., Zhang, T., Zhu, D.Z., Asce, M., and Zhang, Y. (2013), "Physical Modeling on Sand Erosion around Defective Sewer Pipes under the Influence of Groundwater", Journal of Hydraulic Engineering, Vol.139, pp.1247-1257. https://doi.org/10.1061/(asce)hy.1943-7900.0000785
  4. Hosmer, D. W., Lemeshow, S., and Rodney, X. S. (2000), Applied logistic regression, Wiley, New York.
  5. Indiketiya, S., Jegatheesan, P., and Pathmanathan, R. (2017), "Evaluation of Defective Sewer Pipe Induced Internal Erosion and Associated Ground Deformation Using Laboratory Model Test", Canadian Geotechnical Journal, Vol.54, pp.1184-1195. https://doi.org/10.1139/cgj-2016-0558
  6. Korea Institute of Civil Engineering and Building Technology (2020), "Underground Space DB Accuracy Improvement and Underground Utilities Safe Management Technology", KICT 2020-215.
  7. Korea Institute of Geoscience and Mineral Resources (2014), "A Study on the Causes and Policy Recommendations of Sinkholes", Final Report.
  8. Kim, C ., Jung, J., C hoi, C ., and Yoo, W. (2015), "Causes of Ground Subsidence (Sinkholes), Technology and Policy Countermeasures", Ssangyong Engineering & Construction Research Institute, Vol.71, pp.17-25.
  9. Kim, K., Kim, J., Kwak, T. Y., and Chung, C. K. (2018), Logistic regression model for sinkhole susceptibility due to damaged sewer pipes, Natural Hazards, Vol.93, No.2, pp.765-785. https://doi.org/10.1007/s11069-018-3323-y
  10. Kuwano, R., Horii, T., Yamauchi, K., and Kohashi, H. (2010), "Formation of Subsurface Cavity and Loosening due to Defected Sewer Pipes", Japanese Geotechnical Journal, Vol.5, pp.349-361. https://doi.org/10.3208/jgs.5.349
  11. Kwak, T. Y., Woo, S. I., Kim, J., and Chung, C. K. (2019), "Model Test Assessment of the Generation of Underground Cavities and Ground Cave-ins by Damaged Sewer Pipes", Soils and Foundations, Vol.59, pp.586-600. https://doi.org/10.1016/j.sandf.2018.12.011
  12. Kwak, T. Y., Woo, S. I., Chung, C. K., and Kim, J. (2020), "Experimental Assessment of the Relationship between Rainfall Intensity and Sinkholes Caused by Damaged Sewer Pipes", Natural Hazards and Earth System Sciences, Vol.20, pp.3343-3359. https://doi.org/10.5194/nhess-20-3343-2020
  13. Matin, S. S., Farahzadi, L., Makaremi, S., C helgani, S. C ., and Sattari, G. (2018), "Variable Selection and Prediction of Uniaxial Compressive Strength and Modulus of Elasticity by Random Forest", Applied Soft Computing, Vol.70, pp.980-987. https://doi.org/10.1016/j.asoc.2017.06.030
  14. Mukunoki, T., Kumano, N., Otani, J., and Kuwano, R. (2009), "Visualization of Three Dimensional Failure in Sand due to Water Inflow and Soil Drainage from Defective Underground Pipe Using X-Ray CT", Soils and Foundations, Vol.49, pp.959-968. https://doi.org/10.3208/sandf.49.959
  15. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... and Duchesnay, E. (2011), "Scikit-learn: Machine Learning in Python. the Journal of machine Learning research", Vol.12, pp.2825-2830.
  16. Sato, M. and Kuwano, R. (2015), "Influence of Location of Subsurface Structures on Development of Underground Cavities Induced by Internal Erosion", Soils and Foundations, Vol.55, pp.829-840. https://doi.org/10.1016/j.sandf.2015.06.014
  17. Sun, D., Xu, J., Wen, H., and Wang, D. (2021), "Assessment of Landslide Susceptibility Mapping based on Bayesian Hyperparameter Optimization: A Comparison between Logistic Regression and Random Forest", Engineering Geology, Vol.281, 105972. https://doi.org/10.1016/j.enggeo.2020.105972
  18. Yokota, T., Fukatani, W., and Miyamoto, T. (2012), "The Present Situation of the Road Cave in Sinkholes Caused by Sewer Systems".
  19. Zhang, W., Wu, C., Zhong, H., Li, Y., and Wang, L. (2021), "Prediction of Undrained Shear Strength Using Extreme Gradient Boosting and Random Forest based on Bayesian Optimization", Geoscience Frontiers, Vol.12, No.1, pp.469-477. https://doi.org/10.1016/j.gsf.2020.03.007