All Issue

2024 Vol.40, Issue 6 Preview Page
Analysis of Multiple Correlations Between Ground Information and Final Settlement of Soft Ground Using Ensemble-Based Models

앙상블 기반 모델을 활용한 지반정보와 연약지반 최종침하량의 다중상관관계 분석

Seongho Hong1
,
Minho Lee2
,
Seok-Jun Ko3
,
Tae-Young Kwak4
,
Sung-Ryul Kim5*
홍 성호1
,
이 민호2
,
고 석준3
,
곽 태영4
,
김 성렬5*
1Member, Ph.D Student, Dept. of Civil & Environmental Engrg., Seoul National Univ.
2Member, Master Student, Dept. of Civil & Environmental Engrg., Seoul National Univ.
3Member, Leader, Geotechnical Engrg. Team, RIF Tech., GS E&C
4정회원, 서울대학교 건설환경공학부 교수
5Member, Prof., Dept. of Civil & Environmental Engrg., Seoul National Univ.
1정회원, 서울대학교 건설환경공학부 박사과정
2정회원, 서울대학교 건설환경공학부 석사과정
3정회원, GS건설 RIF Tech. 기반기술연구센터 지반터널팀 전임연구원
4정회원, 한국건설기술연구원 지반연구본부 수석연구원
5정회원, 서울대학교 건설환경공학부 교수
*Corresponding Author
31 December 2024. pp. 111-124
PDF XML Citation
Abstract

Accurate prediction of the final consolidation settlement is essential to minimize residual settlement and ensure the stability of structures. In Korea, the one-dimensional consolidation theory is applied during the design phase, and measurement-based prediction techniques (e.g., the hyperbolic method) are employed during the construction phase. However, these methods are limited because they may not fully reflect the site-specific characteristics or require long-term monitoring. Thus, in this study, ensemble-based deep learning models (i.e., the random forest, gradient boosting machine, XGBoost, and LightGBM models) were developed using the final fill height and ground information to improve the accuracy of the final settlement predictions and analyze the correlations with the input variables. In addition, a database was constructed from the measurement results and borehole data collected from six sites in Busan Port. The prediction results demonstrate that the random forest model achieved the highest accuracy with an average mean absolute error of 0.51 m and a mean absolute percentage error of 8.38%. In addition, the other models demonstrated high performance within specific data distributions; however, they tended to exhibit increased prediction errors when encountering out-of-distribution data. Shapley additive explanations analysis showed that the final fill height, plasticity index, consolidation ratio, clay layer thickness, and natural moisture content were the most significant contributors to predicting the final settlement.

Keywords
Consolidation settlement
Ensemble deep learning model
Final settlement prediction
SHAP analysis
Soft ground

대심도 연약지반 현장에서는 잔류침하량을 최소화하고 구조물의 안정성을 확보하기 위해 최종침하량의 정확한 예측이 필수적이다. 국내에서는 설계단계에서 1차원 압밀이론을, 시공단계에서 계측 기반 예측기법(쌍곡선법 등)을 적용하고 있으나, 현장 특성을 충분히 반영하지 못하거나 장기간 계측이 필요하다는 한계가 있다. 본 연구에서는 최종성토고와 지반정보를 활용하여 앙상블 기반 딥러닝 모델(Random Forest, Gradient Boosting Machine, XGBoost, LightGBM)을 구축하고, 이를 통해 최종침하량 예측 정확도를 향상시키며 입력변수와의 상관관계를 분석하였다. 데이터베이스는 부산항 신항 내 6개 현장에서 숮비된 계측결과와 시추공 데이터를 기반으로 구축되었다. 최종침하량 예측 결과, Random Forest 모델이 평균 절대 오차 0.51m, 평균 절대 백분율 오차 8.38%로 가장 높은 예측 정확도를 보였다. 다른 모델들은 특정 데이터 분포 내에서 높은 성능을 보였으나, 분포를 벗어난 데이터에서는 예측 오차가 증가하는 경향을 보였다. SHAP(Shapley Additive Explanations) 분석 결과, 최종성토고, 소성지수, 압밀비, 점토층 두께, 자연 함수비의 순서로 최종침하량 예측에 기여도가 높은 것으로 나타났다.

References
1

Asaoka, A. (1978), "Observational Procedure of Settlement Prediction", Soils and Foundations, Vol.18, No.4, pp.87-101.

10.3208/sandf1972.18.4_87
2

Baghbani, A., Choudhury, T., Costa, S., and Reiner, J. (2022), "Application of Artificial Intelligence in Geotechnical Engineering: A State-of-the-art Review", Earth-Science Reviews, 228, 103991.

10.1016/j.earscirev.2022.103991
3

Barron, R. A. (1948), "Consolidation of Fine-grained Soils by Drain Wells by Drain Wells", Transactions of the American Society of Civil Engineers, Vol.113, No.1, pp.718-742.

10.1061/TACEAT.0006098
4

Bozorgzadeh, N. and Feng, Y. (2024), "Evaluation Structures for Machine Learning Models in Geotechnical Engineering", Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, Vol.18, No.1, pp.52-59.

10.1080/17499518.2024.2313485
5

Breiman, L. (1996), "Bagging Predictors", Machine Learning, 24, pp.123-140.

10.1007/BF00058655
6

Breiman, L. (2001), "Random Forests", Machine Learning, 45, pp.5-32.

10.1023/A:1010933404324
7

Buhlmann, P. and Yu, B. (2002), "Analyzing Bagging", The Annals of Statistics, Vol.30, No.4, pp.927-961.

10.1214/aos/1031689014
8

Chandrasekhar, C. K., Bagyalakshmi, H., Srinivasan, M. R., and Gallo, M. (2016), "Partial Ridge Regression under Multicollinearity", Journal of Applied Statistics, Vol.43, No.13, pp.2462-2473.

10.1080/02664763.2016.1181726
9

Chen, T. and Guestrin, C. (2016, August), "Xgboost: A Scalable Tree Boosting System", In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp.785-794).

10.1145/2939672.2939785
10

Chen, Z. J., Feng, W. Q., Yin, J. H., and Shi, X. S. (2023), "Finite Element Model and Simple Method for Predicting Consolidation Displacement of Soft Soils Exhibiting Creep Underneath Embankments in 2-D Condition", Acta Geotechnica, Vol.18, No.5, pp.2513-2528.

10.1007/s11440-022-01741-z
11

Christian, J. T. and David Carrier III, W. (1978), "Janbu, Bjerrum and Kjaernsli's Chart Reinterpreted", Canadian Geotechnical Journal, Vol.15, No.1, pp.123-128.

10.1139/t78-010
12

Chung, S. G., Choi, G. H., Choi, H. K., and Cho, K. Y. (1998), "√s-Observational Procedure for Consolidation Analysis", Geotechnical Engineering, Vol.14, No.2, pp.41-53.

13

Cohen, J. (2013), Statistical Power Analysis for the Behavioral Sciences, routledge.

10.4324/9780203771587
14

De, W. E. T. (1962), "Three-dimensional Consolidation", Highway Research Board Bulletin, (342).

15

Dietterich, T. G. (2000, June), "Ensemble Methods in Machine Learning", In International Workshop on Multiple Classifier Systems (pp.1-15). Berlin, Heidelberg: Springer Berlin Heidelberg.

10.1007/3-540-45014-9_1
16

Farrar, D. E. and Glauber, R. R. (1967), "Multicollinearity in Regression Analysis: the Problem Revisited", The Review of Economic and Statistics, pp.92-107.

10.2307/1937887
17

Freund, Y. and Schapire, R. E. (1997), "A Decision-theoretic Generalization of On-line Learning and an Application to Boosting", Journal of Computer and System Sciences, Vol.55, No.1, pp.119-139.

10.1006/jcss.1997.1504
18

Frisch, R. (1934), Statistical Confluence Analysis by Means of Complete Regression Systems. (No Title)

19

Ge, Q., Xia, Y., Shu, J., Li, J., and Sun, H. (2024), "Explainable Ensemble Learning Approaches for Predicting the Compression Index of Clays", Journal of Marine Science and Engineering, Vol.12, No.10, p.1701.

10.3390/jmse12101701
20

Hong, S., Ko, S. J., Woo, S. I., Kwak, T. Y., and Kim, S. R. (2024), "Time-series Forecasting of Consolidation Settlement Using LSTM Network", Applied Intelligence, Vol.54, No.2, pp.1386-1404.

10.1007/s10489-023-05219-7
21

Hosseinpour, I., Almeida, M. S., Riccio, M., and Baroni, M. (2017), "Strength and Compressibility Characteristics of a Soft Clay Subjected to Ground Treatment", Geotechnical and Geological Engineering, Vol.35, pp.1051-1066.

10.1007/s10706-017-0161-8
22

Hoshino, S. (1962), "Problems of Foundation s in Recent Years", Society of Civil Engineering, Vol.47, No.7, pp.63-67 (in Japanese).

23

Hossen, I., Anders, M. A., Wang, L., and Adam, G. C. (2022), "Data-driven RRAM Device Models Using Kriging Interpolation", Scientific Reports, Vol.12, No.1, p.5963.

10.1038/s41598-022-09556-435396453PMC8993845
24

Janbu, N. (1965), "Consolidation of Clay Layers based on Non-linear Stress-strain", In Proceedings 6th International Conference on Soil Mechanics and Foundation Engineering, Montreal (Vol.2, pp.83-87).

25

Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... and Liu, T. Y. (2017), "Lightgbm: A Highly Efficient Gradient Boosting Decision Tree", Advances in Neural Information Processing Systems, 30.

26

Kendall, M. G. (1948), Rank Correlation Methods.

27

Kim, J. H. (2019), "Multicollinearity and Misleading Statistical Results", Korean Journal of Anesthesiology, Vol.72, No.6, pp.558-569.

10.4097/kja.1908731304696PMC6900425
28

Kim, M., Senturk, M. A., Tan, R. K., Ordu, E., and Ko, J. (2024), "Deep Learning Approach on Prediction of Soil Consolidation Characteristics", Buildings, Vol.14, No.2, p.450.

10.3390/buildings14020450
29

Kwak, T. Y., Hong, S., Lee, J. H., and Woo, S. I. (2022), "Analysis of the Limitations of the Existing Subsidence Prediction Method Based on the Subsidence Measurement Data and Suggestions for Improvement Method Through Weighted Nonlinear Regression Analysis", Journal of the Korean Geotechnical Society, Vol.38, No.12, pp.103-112 (in Korean).

30

Kwak, T. Y., Woo, S. I., Hong, S., Lee, J. H., and Baek, S. H. (2023), "Settlement Prediction Accuracy Analysis of Weighted Nonlinear Regression Hyperbolic Method According to the Weighting Method", Journal of the Korean Geotechnical Society, Vol.38, No.12, pp.103-112 (in Korean).

31

Long, T., He, B., Ghorbani, A., and Khatami, S. M. H. (2023), "Tree-based Techniques for Predicting the Compression Index of Clayey Soils", Journal of Soft Computing in Civil Engineering, Vol.7, No.3, pp.52-67.

32

Pham, B. T., Nguyen, M. D., Van Dao, D., Prakash, I., Ly, H. B., Le, T. T., ... and Bui, D. T. (2019), "Development of Artificial Intelligence Models for the Prediction of Compression Coefficient of Soil: An Application of Monte Carlo Sensitivity Analysis", Science of The Total Environment, Vol.679, pp.172-184.

10.1016/j.scitotenv.2019.05.06131082591
33

Ozturk, F. and Akdeniz, F. (2000), "Ill-conditioning and Multicollinearity", Linear Algebra and its Applications, Vol.321, No.1-3, pp.295-305.

10.1016/S0024-3795(00)00147-6
34

Plaxis, B. V. (2002), "Plaxis, Finite Element Code for Soil and Rock Analyses", RBJ Brinkgreve Delft, Netherlands.

35

Pyrah, I. C. (1996), "One-dimensional Consolidation of Layered Soils", Geotechnique, Vol.46, No.3, pp.555-560.

10.1680/geot.1996.46.3.555
36

Rokach, L. (2010), "Ensemble-based Classifiers", Artificial Intelligence Review, Vol.33, pp.1-39.

10.1007/s10462-009-9124-7
37

Sridharan, A., Murthy, N. S., and Prakash, K. (1987), "Rectangular Hyperbola Method of Consolidation Analysis", Geotechnique, Vol.37, No.3, pp.355-368.

10.1680/geot.1987.37.3.355
38

Sridharan, A. and Rao, A. S. (1981), "Rectangular Hyperbola Fitting Method for One Dimensional Consolidation", Geotechnical Testing Journal, Vol.4, No.4, pp.161-168.

10.1520/GTJ10785J
39

Tan, S. A. (1993), "Ultimate Settlement by Hyperbolic Plot for Clays with Vertical Drains", Journal of Geotechnical Engineering, ASCE, Vol.119, No.5, pp.950-956

10.1061/(ASCE)0733-9410(1993)119:5(950)
40

TAN, S. and CHEW, S. (1996), "Comparison of the Hyperbolic and Asaoka Observational Method of Monitoring Consolidation with Vertical Drains", Soils and Foundations, Vol.36, No.3, pp.31-42.

10.3208/sandf.36.3_31
41

Tan, T. S., Inoue, T., and Lee, S. L. (1991), "Hyperbolic Method for Consolidation Analysis", Journal of Geotechnical Engineering, Vol.117, No.11, pp.1723-1737.

10.1061/(ASCE)0733-9410(1991)117:11(1723)
42

Terzaghi, K. (1943), Theoretical Soil Mechanics.

10.1002/9780470172766
43

Watanabe, S. (2023), "Tree-structured Parzen Estimator: Understanding its Algorithm Components and their Roles for better Empirical Performance", arXiv preprint arXiv:2304.11127.

44

Yin, J. H., Chen, Z. J., and Feng, W. Q. (2022), "A General Simple Method for Calculating Consolidation Settlements of Layered Clayey Soils with Vertical Drains under Staged Loadings", Acta Geotechnica, Vol.17, No.8, pp.3647-3674.

10.1007/s11440-021-01318-2
45

Yoo, H. K. and Kim, J. H. (2000), "A Study on the Prediction of Long-Term Settlement by the Modified Hyperbolic Method", Journal of the Korean Geotechnical Society, Vol.16, No.3, pp.163-172 (in Korean).

Information
  • Publisher :The Korean Geotechnical Society
  • Publisher(Ko) :한국지반공학회
  • Journal Title :Journal of the Korean Geotechnical Society
  • Journal Title(Ko) :한국지반공학회 논문집
  • Volume : 40
  • No :6
  • Pages :111-124
  • Received Date : 2024-11-26
  • Accepted Date : 2024-12-01
  • DOI :https://doi.org/10.7843/kgs.2024.40.6.111
Journal Informaiton Journal of the Korean Geotechnical Society Journal of the Korean Geotechnical Society
Archives
: Vol.23~28 (2007~2012)
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close