All Issue

2026 Vol.42, Issue 3 Preview Page
Data Augmentation via Gaussian Noise Injection for Simulation Data-Based Prediction of Retaining Wall Behavior under Field Variability

해석 데이터 기반 흙막이 벽체 거동 예측에서의 현장 변동성을 고려한 가우시안 노이즈 주입 데이터 증강 기법

Jihoon Kim1
,
Inyoung Huh2
,
Jingi Hong2
,
Heejung Youn3*
김 지훈1
,
허 인영2
,
홍 진기2
,
윤 희정3*
1Member, Ph.D. Student, Dept. of Civil and Environmental Engineering, Hongik Univ.
2M.S. Student, Dept. of Civil and Environmental Engineering, Hongik Univ.
3Member, Prof., Dept. of Civil and Environmental Engineering, Hongik Univ.
1정회원, 홍익대학교 건설환경공학과 박사과정
2비회원, 홍익대학교 건설환경공학과 석사과정
3정회원, 홍익대학교 건설환경공학과 교수
*Corresponding Author
30 June 2026. pp. 125-142
PDF XML Citation
Abstract

This study presents a Gaussian noise–based data augmentation strategy to improve the predictive performance of a multi-resolution ConvLSTM framework for predicting retaining wall deformation during excavation. Although an initial training database comprising 4,200 samples was generated using finite element analysis (PLAXIS 2D), the dataset was inherently limited by the idealized, smooth deformation patterns typically produced by numerical simulations. Consequently, it could not adequately represent the localized and irregular deformation characteristics observed under field conditions. To address this limitation, Gaussian noise with varying spatial resolutions and amplitudes was injected into the simulation-based displacement data, expanding the database to 16,800 samples. The trained model was subsequently validated using 34 inclinometer datasets collected from 11 excavation sites in South Korea. The results demonstrated that the proposed data augmentation strategy effectively mitigated overfitting to idealized simulation data, significantly improving the prediction accuracy and reproducibility of diverse, irregular deformation patterns observed in the field while reducing prediction uncertainty.

Keywords
Data augmentation
Field applicability
Gaussian noise
Retaining wall
Time-series prediction

본 연구에서는 굴착에 따른 흙막이 벽체의 변형 예측을 위한 다중 해상도 ConvLSTM 프레임워크의 성능 향상을 위해 Gaussian noise 기반 데이터 증강 기법을 제안하였다. 기존 유한요소해석(PLAXIS 2D)을 이용하여 4,200개의 학습 데이터베이스를 구축하였으나, 해당 데이터는 수치해석 특성상 정형화되고 평활한(smooth) 변형 형상만을 나타내므로 실제 현장에서 관측되는 국부적이고 불규칙한 변형 특성을 반영하지 못하는 한계가 있었다. 이를 개선하기 위하여 다양한 공간 해상도와 진폭을 갖는 Gaussian noise를 수치해석 기반 변위 데이터에 주입하여 데이터베이스를 16,800개로 확장하였다. 학습된 모델은 국내 11개 굴착 현장에서 수집된 34개의 지중경사계 계측자료를 이용하여 검증하였다. 분석 결과, 제안된 데이터 증강 기법은 이상적인 해석 데이터에 대한 과적합을 방지하여 실제 현장의 다양한 불규칙 변형 형상에 대한 예측 정확도와 재현성을 유의미하게 개선하였으며, 예측 불확실성을 감소시키는 것으로 나타났다.

References
1

Bishop, C.M. (1995), “Training with Noise is Equivalent to Tikhonov Regularization”, Neural Computation, Vol.7, No.1, pp.108-116, https://doi.org/10.1162/neco.1995.7.1.108.

10.1162/neco.1995.7.1.108
2

Calvello, M. and Finno, R.J. (2004), “Selecting parameters to Optimize in Model Calibration by Inverse Analysis”, Computers and Geotechnics, Vol.31, No.5, pp.410-424, https://doi.org/10.1016/j.compgeo.2004.03.004.

10.1016/j.compgeo.2004.03.004
3

Clough, G.W. (1990), “Construction Induced Movements of Insitu Wall, Design and Performance of Earth Retaining Structure”, In ASCE pp.439-479.

4

Gal, Y. and Ghahramani, Z. (2016), “Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning”, In International Conference on Machine Learning, pp.1050-1059.

5

Gao, Y., Xiao, Z., Gong, Z., Huang, S., and Zhu, H. (2025), “Spatiotemporal Deformation Prediction Model for Retaining Structures Integrating ConvGRU and Cross-Attention Mechanism”, Buildings, Vo.15, No.14, 2537, https://doi.org/10.3390/buildings15142537.

10.3390/buildings15142537
6

Ge, L. and Sadhu, A. (2024), “Domain Adaptation for Structural Health Monitoring via Physics-informed and Self-attention-enhanced Generative Adversarial Learning”, Mechanical Systems and Signal Processing, Vol.211, 111236, https://doi.org/10.1016/j.ymssp.2024.111236.

10.1016/j.ymssp.2024.111236
7

He, P., Di, H., He, C., Zhang, X., Liu, C., and Zhou, S. (2025), “Spatio-temporal Graph Convolutional Networks with Multi-source Fusion for Predicting Excavation Deformation”, Advanced Engineering Informatics, Vol.68, 103722, https://doi.org/10.1016/j.aei.2025.103722.

10.1016/j.aei.2025.103722
8

Iglesias, G., Talavera, E., González-Prieto, Á., Mozo, A., and Gómez-Canaval, S. (2023), “Data augmentation techniques in time series domain: a survey and taxonomy”, Neural Computing and Applications, Vol.35, No.14, pp.10123-10145, https://doi.org/10.1007/s00521-023-08459-3.

10.1007/s00521-023-08459-3
9

Iwana, B.K. and Uchida, S. (2021), “An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks”, Plos One, Vol.16, No.7, e0254841, https://doi.org/10.1371/journal.pone.0254841.

10.1371/journal.pone.025484134264999PMC8282049
10

Kim, D., Kim, J., and Youn, H. (2024), “Automated Ground Penetrating Radar B-scan Detection Enhanced by Data Augmentation Techniques”, Geomechanics and Engineering, Vol.38, No.1, pp.29-44, https://doi.org/10.12989/gae.2024.38.1.029.

10.12989/gae.2024.38.1.029
11

Kim, D. and Youn, H. (2024), “Classifying Roundness and Sphericity of Sand Particles Using CNN Regression Models to Alleviate Data Imbalance”, Acta Geotechnica, Vol.19, No.10, pp.6569-6584. https://doi.org/10.1007/s11440-024-02410-z.

10.1007/s11440-024-02410-z
12

Kim, J. and Youn, H. (2026), “Spatio-Temporal Forecasting of Retaining Wall Deformation: Mitigating Error Accumulation via Multi-Resolution ConvLSTM Stacking Ensemble”, Geomechanics and Engineering, Vol.45, No.5, pp.649-674, https://doi.org/10.12989/gae.2026.45.5.649.

10.12989/gae.2026.45.5.649
13

Kim, J., Kim, S., and Youn, H. (2026), “Field Validation of a Multi-Resolution ConvLSTM Framework for Retaining Wall Deformation Prediction”, arXiv preprint arXiv:2606.05556, https://doi.org/10.48550/arXiv.2606.05556.

10.48550/arXiv.2606.05556
14

Le Guennec, A., Malinowski, S., and Tavenard, R. (2016, September), “Data Augmentation for Time Series Classification Using Convolutional Neural Networks”, In ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data.

15

Lee, D.G., Yu, J.Y., Choi, J.Y., and Song, K.I. (2023), “Development of Stability Evaluation Algorithm for CIP Retaining Walls during Excavation”, Journal of the Korean Geotechnical Society, Vol.39 No.9, pp.13-24, https://doi.org/10.7843/kgs.2023.39.9.13.

10.7843/kgs.2023.39.9.13
16

Long, M. (2001), “Database for Retaining Wall and Ground Movements due to Deep Excavations”, Journal of Geotechnical and Geoenvironmental Engineering, Vol.127, No.3, pp.203-224, https://doi.org/10.1061/(ASCE)1090-0241(2001)127:3(203).

10.1061/(ASCE)1090-0241(2001)127:3(203)
17

Moormann, C. (2004), “Analysis of Wall and Ground Movements due to Deep Excavations in Soft Soil based on a New Worldwide Database”, Soils and foundations, Vol.44, No.1, pp.87-98, https://doi.org/10.3208/sandf.44.87.

10.3208/sandf.44.87
18

Mumuni, A. and Mumuni, F. (2022), “Data Augmentation: A Comprehensive Survey of Modern Approaches”, Array, Vol.16, 100258. https://doi.org/10.1016/j.array.2022.100258.

10.1016/j.array.2022.100258
19

Ozdagli, A. and Koutsoukos, X. (2020, November), “Domain Adaptation for Structural Health Monitoring”, In Annual Conference of the PHM Society, Vol.12, No.1, pp.9-9, https://doi.org/10.36001/phmconf.2020.v12i1.1184.

10.36001/phmconf.2020.v12i1.1184
20

Park, C.S. and Joung, S.M. (2020), “Numerical Investigations on the Excavation Width and Property of Deformation of Earth Retaining Wall”, Journal of the Korean Geotechnical Society, Vol.36, No.12, pp.57-68, https://doi.org/10.7843/kgs.2020.36.12.57.

10.7843/kgs.2020.36.12.57
21

Peck, B.B. (1969), “Deep Excavation and Tunnelling in Soft Ground, State of the Art Volume”, In 7th ICSMFE, Vol.4, pp.225-290.

22

Rechea, C., Levasseur, S., and Finno, R. (2008), “Inverse Analysis Techniques for Parameter Identification in Simulation of Excavation Support Systems”, Computers and Geotechnics, Vol.35, No.3, pp.331-345, https://doi.org/10.1016/j.compgeo.2007.08.008.

10.1016/j.compgeo.2007.08.008
23

Shorten, C. and Khoshgoftaar, T.M. (2019), “A Survey on Image Data Augmentation for Deep Learning”, Journal of Big Data, Vol.6, No.1, pp.1-48, https://doi.org/10.1186/s40537-019-0197-0.

10.1186/s40537-019-0197-0
24

Shi, S., Yu, J., and Zhang, C. (2025), “Fractional Gaussian Noise: Spectral Density and Estimation Methods”, Journal of Time Series Analysis, Vol.46, No.6, pp.1146-1174, https://doi.org/10.1111/jtsa.12750.

10.1111/jtsa.12750
25

Tao, Y., Zeng, S., Sun, H., Cai, Y., Zhang, J., and Pan, X. (2024), “A Spatiotemporal Deep Learning Method for Excavation-induced Wall Deflections”, Journal of Rock Mechanics and Geotechnical Engineering, Vol.16, No.8, pp.3327-3338, https://doi.org/10.1016/j.jrmge.2023.09.034.

10.1016/j.jrmge.2023.09.034
26

Tarantola, A. (2005), “Inverse Problem Theory and Methods for Model Parameter Estimation”, Society for Industrial and Applied Mathematics.

10.1137/1.9780898717921
27

Um, T.T., Pfister, F.M., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U., and Kulić, D. (2017, November), “Data Augmentation of Wearable Sensor Data for Parkinson’s Disease Monitoring Using Convolutional Neural Networks”, In Proceedings of the 19th ACM International Conference on Multimodal Interaction, pp.216-220, https://doi.org/10.1145/3136755.3136817.

10.1145/3136755.3136817
28

Wen, Q., Sun, L., Yang, F., Song, X., Gao, J., Wang, X., and Xu, H. (2020), “Time Series Data Augmentation for Deep Learning: A Survey”, arXiv preprint arXiv:2002.12478, https://doi.org/10.24963/ijcai.2021/631.

10.24963/ijcai.2021/631
29

Willmott, C.J., Robeson, S.M., and Matsuura, K. (2012), “A Refined Index of Model Performance”, International Journal of Climatology, Vol.32, No.13, pp.2088-2094, https://doi.org/10.1002/joc.2419.

10.1002/joc.2419
30

Yuan, B., Choo, C.S., Yeo, L.Y., Wang, Y., Yang, Z., Guan, Q., Suryasentana, S., Choo, J., Shen, H., Megia, M., Zhang, J., Liu, Z., Song, Y., Wang, H., and Chen, X. (2025), “Physics-informed Machine Learning in Geotechnical Engineering: A Direction Paper”, Geomechanics and Geoengineering, Vol.20, No.5, pp.1128-1159, https://doi.org/10.1080/17486025.2025.2502029.

10.1080/17486025.2025.2502029
31

Zhao, H.J., Liu, W., Shi, P.X., Du, J.T., and Chen, X.M. (2021), “Spatiotemporal Deep Learning Approach on Estimation of Diaphragm Wall Deformation Induced by Excavation”, Acta Geotechnica, Vol.16, No.11, pp.3631-3645, https://doi.org/10.1007/s11440-021-01264-z.

10.1007/s11440-021-01264-z
Information
  • Publisher :The Korean Geotechnical Society
  • Publisher(Ko) :한국지반공학회
  • Journal Title :Journal of the Korean Geotechnical Society
  • Journal Title(Ko) :한국지반공학회 논문집
  • Volume : 42
  • No :3
  • Pages :125-142
  • Received Date : 2026-06-05
  • Revised Date : 2026-06-24
  • Accepted Date : 2026-06-25
  • DOI :https://doi.org/10.7843/kgs.2026.42.3.125
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