All Issue

2025 Vol.35, Issue 3 Preview Page

Research Article

Analysis of the Influence of Slope Failure Factors on the Selection of Countermeasure Methods

비탈면 대책공법 선정에 대한 붕괴 요인 영향 분석

Sun-Kyum Kim1
,
Seung-Hyun Kim2*
김 선겸1
,
김 승현2*
1Senior Researcher, Korea Institute of Civil Engineering and Building Technology
2Research Fellow, Korea Institute of Civil Engineering and Building Technology
1한국건설기술연구원 수석연구원
2한국건설기술연구원 연구위원
*Corresponding Author
30 September 2025. pp. 355-366
PDF XML Citation
Abstract

This study analyzed the influence of slope failure factors on the selection of countermeasure methods using preliminary data from the Cut Slope Management System (CSMS). Variable contributions were assessed with eXtreme Gradient Boosting (XGBoost), SHapley Additive exPlanations (SHAP), and Goodman-Kruskal’s λ. Results showed that type of failure, collapse history, loose rock blocks, depth of soil, and type of discontinuity were the most influential factors, while valley presence, slope shapes, and upper angle served as supplementary indicators. The three approaches produced consistent rankings (Spearman ρ≈0.8), whereas Goodman-Kruskal’s λ values were small even for top predictors (~0.00–0.02), highlighting the limits of univariate association. SHAP interaction analysis further revealed that combinations such as type of failure-loose rock blocks (≈0.029) and type of failure-collapse history (≈0.026) strongly amplified predicted failure risk. These results go beyond prior work by addressing single-method interpretability limits while accounting for complex factor interactions. They enhance the objectivity and consistency of countermeasure selection and support more efficient policy making and budget allocation.

Keywords
slope failure
CSMS
XGBoost
SHAP
Goodman-Kruskal’s λ

본 연구는 도로비탈면관리시스템(Cut Slope Management System, CSMS) 기초조사 데이터를 활용하여 비탈면 붕괴 요인이 대책공법 선정에 미치는 영향을 정량적으로 분석하였다. XGBoost (eXtreme Gradient Boosting)를 통한 변수 예측 기여도 산출, SHAP (SHapley Additive exPlanations)를 활용한 기여도 해석, Goodman-Kruskal’s λ를 이용한 연관도 평가를 수행한 결과, 붕괴 유형, 붕괴 이력, 뜬돌, 토층심도, 불연속면 등이 핵심 요인으로 도출되었다. 또한 계곡 여부, 비탈면 형상, 상부 경사와 같은 지형·환경적 요인도 중요한 보조 지표로 확인되었다. 세 기법의 변수 순위는 상호 보완적으로 일치하였고 Spearman ρ≈0.8로 일관성이 확인되었다. 반면 Goodman-Kruskal’s λ는 상위 변수에서도 0.00–0.02 수준으로 단변량 연관도의 한계를 시사하였다. 더 나아가 SHAP 상호작용 분석에서는 붕괴 유형-뜬돌(≈0.029), 붕괴 유형-붕괴 이력(≈0.026) 조합이 위험 예측을 크게 강화하는 것으로 나타났다. 이러한 결과는 단일 기법의 해석 한계를 보완하고, 복합적 요인 상호작용을 고려할 수 있다는 점에서 기존 연구와 차별성을 갖는다. 아울러 공법 선정 과정의 객관성과 일관성을 높이고, 향후 관리 정책 수립과 예산 활용의 효율성 향상에 기여하고자 한다.

키워드
비탈면 붕괴
도로비탈면관리시스템
XGBoost
SHAP
Goodman-Kruskal’s λ
References
1

Akoglu, H., 2018, User’s guide to correlation coefficients, Turkish Journal of Emergency Medicine, 18(3), 91-93.

10.1016/j.tjem.2018.08.00130191186PMC6107969
2

Chen, T., Guestrin, C., 2016, XGBoost: A scalable tree boosting system, In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, 785-794.

10.1145/2939672.2939785
3

Goodman, L.A., Kruskal, W.H., 1954, Measures of association for cross classifications, Journal of the American Statistical Association, 49(268), 732-764.

10.1080/01621459.1954.10501231
4

KICT (Korea Institute of Civil Engineering and Building Technology), 2019, Operation of road cut slope management system in 2018, Ministry of Land, Infrastructure and Transport, 355p (in Korean).

5

Kim, S.H., Koo, H.B., Hwang, J.H., Son, M., 2011, Case study on the cause of failure and characteristics of soil at a collapsed cut-slope at the ◯◯ detour, Jeonranam-do, The Journal of Engineering Geology, 21(4), 313-322 (in Korean with English abstract).

10.9720/kseg.2011.21.4.313
6

Kim, S.K., Kim, S.H., 2024, Analysis of slope failure factors based on data and prediction of countermeasure methods using artificial intelligence, The Journal of Engineering Geology, 34(4), 563-575 (in Korean with English abstract).

10.9720/KSEG.2024.4.563
7

Lee, K.B., Shin, H.S., Kim, S.H., Ha, D.M., Choi, I., 2019, A study on automatic classification of characterized ground regions on slopes by a deep learning based image segmentation, Tunnel and Underground Space, 29(6), 508-522 (in Korean with English abstract).

10.7474/TUS.2019.29.6.508
8

MLTMA (Ministry of Land, Transport and Maritime Affairs), 2011, Practical manual for roadside slope management, 443p (in Korean).

9

Mosca, E., Szigeti, F., Tragianni, S., Gallagher, D., Groh, G., 2022, SHAP-based explanation methods: A review for NLP interpretability, In: Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, 4593-4603.

10

Myers, L., Sirois, M.J., 2004, Spearman correlation coefficients, differences between, In: Kotz, S., Balakrishnan, N., Read, C.B., Vidakovic, B. (Eds.), Encyclopedia of Statistical Sciences, John Wiley & Sons, Hoboken, NJ, 7901-7903.

10.1002/0471667196.ess5050.pub2
11

Park, D.G., Kim, T.H., Park, J.H., 2006, Current status of slope disaster damage and countermeasures in Korea, Geotechnical Engineering, 22(6), 6-18 (in Korean).

12

Pradhan, B., Dikshit, A., Lee, S., Kim, H., 2023, An explainable AI (XAI) model for landslide susceptibility modeling, Applied Soft Computing, 142, 110324.

10.1016/j.asoc.2023.110324
13

Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., Gulin, A., 2018, CatBoost: Unbiased boosting with categorical features, In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, 6639-6649.

14

Saqlain, M., Jargalsaikhan, B., Lee, J.Y., 2019, A voting ensemble classifier for wafer map defect patterns identification in semiconductor manufacturing, IEEE Transactions on Semiconductor Manufacturing, 32(2), 171-182.

10.1109/TSM.2019.2904306
15

Zhang, J., Ma, X., Zhang, J., Sun, D., Zhou, X., Mi, C., Wen, H., 2023, Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model, Journal of Environmental Management, 332, 117357.

10.1016/j.jenvman.2023.117357
Information
  • Publisher :Korean Society of Engineering Geology
  • Publisher(Ko) :대한지질공학회
  • Journal Title :The Journal of Engineering Geology
  • Journal Title(Ko) :지질공학
  • Volume : 35
  • No :3
  • Pages :355-366
  • Received Date : 2025-08-25
  • Revised Date : 2025-09-11
  • Accepted Date : 2025-09-15
  • DOI :https://doi.org/10.9720/kseg.2025.3.355
Journal Informaiton The Journal of Engineering Geology The Journal of Engineering Geology
Online Submission
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close