Journal of the Korean Geotechnical Society (한국지반공학회논문집)

Korean Geotechnical Society (한국지반공학회)
권호 표지
DOI QR코드

DOI QR Code

MLP-based 3D Geotechnical Layer Mapping Using Borehole Database in Seoul, South Korea

MLP 기반의 서울시 3차원 지반공간모델링 연구

  • Ji, Yoonsoo (Spatial Information Research Institute, LX) ;
  • Kim, Han-Saem (Earthquake Research Center, Korea Institute of Geoscience and Mineral Resources) ;
  • Lee, Moon-Gyo (Earthquake Research Center, Korea Institute of Geoscience and Mineral Resources) ;
  • Cho, Hyung-Ik (Earthquake Research Center, Korea Institute of Geoscience and Mineral Resources) ;
  • Sun, Chang-Guk (Earthquake Research Center, Korea Institute of Geoscience and Mineral Resources)
  • 지윤수 (한국국토정보공사 공간정보연구원) ;
  • 김한샘 (한국지질자원연구원 지진연구센터) ;
  • 이문교 (한국지질자원연구원 지진연구센터) ;
  • 조형익 (한국지질자원연구원 지진연구센터) ;
  • 선창국 (한국지질자원연구원 지진연구센터)
  • Received : 2021.04.29
  • Accepted : 2021.05.18
  • Published : 2021.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, the demand for three-dimensional (3D) underground maps from the perspective of digital twins and the demand for linkage utilization are increasing. However, the vastness of national geotechnical survey data and the uncertainty in applying geostatistical techniques pose challenges in modeling underground regional geotechnical characteristics. In this study, an optimal learning model based on multi-layer perceptron (MLP) was constructed for 3D subsurface lithological and geotechnical classification in Seoul, South Korea. First, the geotechnical layer and 3D spatial coordinates of each borehole dataset in the Seoul area were constructed as a geotechnical database according to a standardized format, and data pre-processing such as correction and normalization of missing values for machine learning was performed. An optimal fitting model was designed through hyperparameter optimization of the MLP model and model performance evaluation, such as precision and accuracy tests. Then, a 3D grid network locally assigning geotechnical layer classification was constructed by applying an MLP-based bet-fitting model for each unit lattice. The constructed 3D geotechnical layer map was evaluated by comparing the results of a geostatistical interpolation technique and the topsoil properties of the geological map.

최근 디지털 트윈 관점의 3차원 지하공간 지도의 수요 및 유관분야의 연계 활용 요구가 증대되고 있다. 그러나 전국단위의 지반조사 자료의 방대함과 이를 활용함에 있어 공간적/추계학적 기법 적용의 불확실성으로 인해 신뢰도 높은 지역적 지반특성화 연구와 그에 따른 최적화 모델 제시에 어려움이 있다. 따라서 본 연구에서는 서울지역 3차원 지하공간의 공학적 지층분류를 위해 다층 퍼셉트론(MLP) 기반의 최적 학습모델을 구축하였다. 먼저, 서울지역에 분포하는 시추공별 층상구조 및 3차원 공간좌표를 표준화 서식에 따라 지반정보 데이터베이스로 구축하고 기계학습을 위한 결측치 보정, 정규화 등의 데이터 전처리를 하였다. MLP 모델의 파라미터 최적화와 정밀도 및 정확도 관련 모델 성능 평가를 통해 최적의 피팅 모델을 설계하였다. 이후 3차원 지반 공간레이어 구축을 위한 수치표고모델 기반 격자망을 구성하고, 단위격자별 MLP기반 예측모델 적용을 통한 층상구조를 결정하고 이를 가시화하였다. 구축된 3차원 지반모델은 범용적인 지구통계학적 공간보간 기법의 적용 결과 및 지질도의 표토층 성상과 비교하여 그 성능을 평가하였다.

Keywords

Acknowledgement

본 연구는 한국지질자원연구원 주요사업인 '동남권 단층지진원 기반 강지진동 예측 및 지역특화 지진조기경보 기술개발' 과제의 일환으로 수행되었습니다.

References

  1. Ayachit, U. (2015), "The ParaView Guide: A Parallel Visualization Application", Kitware, Inc.: USA.
  2. Bressan, T. S., Kehl de Souza, M., Girelli, T. J., and Junior, F. C. (2020), "Evaluation of Machine Learning Methods for Lithology Classification Using Geophysical Data", Computers and Geosciences., Vol.139, 104475. https://doi.org/10.1016/j.cageo.2020.104475
  3. Chen, Q., Mariethoz, G., Liu, G., Comunian, A., and Ma, X. (2019), "Locality-based 3-D Multiple-point Statistics Reconstruction Using 2-D Geological Cross-sections", Hydrology and Earth System Sciences, Vol.22, pp.6547-6566. https://doi.org/10.5194/hess-22-6547-2018
  4. Chun, C., Choi, C., and Cho, J. (2019), "Comparison of Ordinary Kriging and Artificial Neural Network for Estimation of Ground Profile Information in Unboring Region", Journal of the Korean Geo-Environmental Society, Vol.20, No.3, pp.15-20.
  5. Costa, I., Tavares, F., and Oliveira, J. (2019), "Predictive Lithological Mapping through Machine Learning Methods: A Case Study in the Cinzento Lineament, Carajas Province, Brazil", Journal of the Geological Survey of Brazil, Vol.2, No.1, pp.26-36. https://doi.org/10.29396/jgsb.2019.v2.n1.3
  6. Entwisle, D. (2019), "3D Geological Modelling at the British Geological Survey" (BGS), NTU-BCA Workshop on 3D Geological Modelling, BCA Academy, Building and Construction Authority, Singapore.
  7. Fawcett, T. (2006), "An Introduction to ROC Analysis", Pattern recognition letters, Vol.27, No.8, pp.861-874. https://doi.org/10.1016/j.patrec.2005.10.010
  8. Fuentes, I., Padarian, J., Iwanaga, T., and Willem Vervoort, R. (2020), "3D Lithological Mapping of Borehole Descriptions Using Word Embeddings", Computers & Geosciences., Vol.141, 104516. https://doi.org/10.1016/j.cageo.2020.104516
  9. Getis, A. and J. K. Ord. (1992), "The Analysis of Spatial Association by Use of Distance Statistics", Geographical Analysis, Vol.24, No.3, pp.189-206. https://doi.org/10.1111/j.1538-4632.1992.tb00261.x
  10. Greve, M. H., Kheir, R. B., Greve, M. B., and Bocher, P. K. (2012), "Using Digital Elevation Models as an Environmental Predictor for Soil Clay Contents", Soil Science Society of America Journal, Vol.76, No.6, pp.2116-2127. https://doi.org/10.2136/sssaj2010.0354
  11. Hanley, J. A. and McNeil, B. J. (1982), "The Meaning and Use of the Area under a Receiver Operating Characteristic (ROC) Curve", Radiology, Vol.143, No.1, pp.29-36. https://doi.org/10.1148/radiology.143.1.7063747
  12. Kim, H. R., Kim, K. H., Yun, S. T., Hwang, S. I., Kim, H. D., Lee, G. T., and Kim, Y. J. (2012), "Evaluation of Geostatistical Approaches for better Estimation of Polluted Soil Volume with Uncertainty Evaluation", Journal of Soil and Groundwater Environment, Vol.17, No.6, pp.69-81. https://doi.org/10.7857/JSGE.2012.17.6.069
  13. Kim, H. S., Chung, C. K., and Kim, H. K. (2016), "Geo-spatial Data Integration for Subsurface Stratification of Dam Site with Outlier Analyses", Environmental Earth Sciences, Vol.75, No.2, pp.168. https://doi.org/10.1007/s12665-015-4931-4
  14. Kim, H. S., Chung, C. K., and Kim, J. J. (2018), "Three-dimensional Geostatistical Integration of Borehole and Geophysical Datasets in Developing Geological Unit Boundaries for Geotechnical Investigations", Quarterly Journal of Engineering Geology and Hydrogeology, Vol.51, No.1, pp.79-95. https://doi.org/10.1144/qjegh2016-012
  15. Kim, H. S., Sun, C. G., and Cho, H. I. (2017), "Geospatial Big DataBased Geostatistical Zonation of Seismic Site Effects in Seoul Metropolitan Area", ISPRS International Journal of Geo-Information, Vol.6, No.6, pp.174. https://doi.org/10.3390/ijgi6060174
  16. Kim, H. S., Sun, C. G., Cho, H. I., and Nam, J. H. (2018), "Regional Assessment of Seismic Site Effects and Induced Vulnerable Area in Gyeonggi-do, South Korea, Using GIS", Journal of the Korean Geotechnical Society, Vol.34, No.5, pp.19-35. https://doi.org/10.7843/KGS.2018.34.5.19
  17. Kim, J., Lim, H. S., and Nahm, W. -H. (2019), "Three-dimensional Modelling of Urban Area based on the Urban Geological Approach", Journal of the Geological Society of Korea, Vol.55, No.3, pp. 333-342. https://doi.org/10.14770/jgsk.2019.55.3.333
  18. Korea Institute of Geoscience and Mineral Resources (2009), Development on Technology of the Real Time Seismic Monitoring and the Seismic Hazard Prediction at Metropolitan Areas.
  19. McBratney, A. B., Santos, M. M., and Minasny, B. (2003), "On digital soil mapping", Geoderma, Vol.117, No.1-2, pp.3-52. https://doi.org/10.1016/S0016-7061(03)00223-4
  20. Mohamed, I. M., Mohamed, S., Mazher, I., and Chester, P. (2019), "Formation Lithology Classification: Insights into Machine Learning Methods", Proc. - SPE Annu. Tech. Conf. Exhib. 2019-September.
  21. Osterholt, V. and Dimitrakopoulos, R. (2007), "Simulation of Orebody Geology with Multiple-point Geostatistics: Application at Yandi Channel Iron Ore Deposit, WA and Implications for Resource Uncertainty", Orebody modelling and strategic mine planning, The Australasian Institute of Mining and Metallurgy, pp.51-60.
  22. Pan, X., Guo, W., Aung, Z., Nyo, A. K., Chiam, K., Wu, D., and Chu, J. (2018), "Procedure for Establishing a 3D Geological Model for Singapore", GeoShanghai International Conference, Springer, Singapore, pp.81-89.
  23. Ray, P., Manach, Y. L., Riou, B., Houle, T. T., and Warner, D.S. (2010), "Statistical Evaluation of a Biomarker", The Journal of the American Society of Anesthesiologists, Vol.112, No.4, pp.1023-1040.
  24. Sullivan, C. B. and Kaszynski, A. A. (2019), "PyVista: 3D Plotting and Mesh Analysis through a Streamlined Interface for the Visualization Toolkit (VTK)", Journal of Open Source Software, Vol.4, No.37, 1450. https://doi.org/10.21105/joss.01450
  25. Sun, C. G., Kim, H. J., Jung, J. H., and Jung, G. J. (2006), "Synthetic Application of Seismic Piezo-cone Penetration Test for Evaluating Shear Wave Velocity Korean Soil Deposits", Mulli-Tamsa, Vol.9, No.3, pp.207-224.
  26. Sun, C. G. and Kim, H. S. (2016), "Site Classification for Incheon According to Site-Specific Seismic Response Parameters by Estimating Geotechnical Spatial Information Based on GIS", Journal of the Korea Association of Geographic Information Studies, Vol.19, No. 4, pp.1-15. https://doi.org/10.11108/kagis.2016.19.4.001
  27. Thornton, J. M., Mariethoz, G., and Brunner, P. (2018), "A 3D Geological Model of a Structurally Complex Alpine Region as a Basis for Interdisciplinary Research", Scientific Data, Vol.5, No.1, pp.1-20. https://doi.org/10.1038/s41597-018-0002-5
  28. Wang, Z., Shi, W., Zhou, W., Li, X., and Yue, T. (2020), "Comparison of Additive and Isometric Log-ratio Transformations Combined with Machine Learning and Regression Kriging Models for Mapping Soil Particle Size Fractions", Geoderma, Vol.365, 114214. https://doi.org/10.1016/j.geoderma.2020.114214