Journal of the Korean Geotechnical Society (한국지반공학회논문집)

Korean Geotechnical Society (한국지반공학회)
권호 표지
DOI QR코드

DOI QR Code

Study for Relationship between Compressional Wave Velocity and Porosity based on Error Norm Method

중요도 분석 기법을 활용한 압축파 속도와 간극률 관계 연구

  • Yoon, Hyung-Koo (Dept. of Disaster Safety Engineering, Daejeon Univ.)
  • 윤형구 (대전대학교 재난안전공학과 )
  • Received : 2024.08.01
  • Accepted : 2024.08.13
  • Published : 2024.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this paper is to establish the relationship between compression wave velocity and porosity in unsaturated soil using a deep neural network (DNN) algorithm. Input parameters were examined using the error norm method to assess their impact on porosity. Compression wave velocity was conclusively found to have the most significant influence on porosity estimation. These parameters were derived through both field and laboratory experiments using a total of 266 numerical data points. The application of the DNN was evaluated by calculating the mean squared error loss for each iteration, which converged to nearly zero in the initial stages. The predicted porosity was analyzed by splitting the data into training and validation sets. Compared with actual data, the coefficients of determination were exceptionally high at 0.97 and 0.98, respectively. This study introduces a methodology for predicting dependent variables through error norm analysis by disregarding fewer sensitive factors and focusing on those with greater influence.

해당 논문의 목적은 deep neural network(DNN) 알고리즘을 이용하여 불포화토 지반의 압축파 속도와 간극률 간의 관계를 도출하는 것이다. 입력 인자는 error norm 방법으로 각각의 값이 간극률에 미치는 영향을 조사하였으며, 결론적으로 압축파 속도가 간극률 산정에 제일 큰 영향을 주는 것으로 나타났다. 압축파 속도와 간극률은 현장 및 실내 실험을 통해 도출하였으며, 총 266개의 수치 데이터를 이용하였다. DNN 적용 결과는 매 횟수마다 계산된 MSE 손실로 표현하였으며, 초반의 계산 횟수 단계에서 거의 0에 수렴하는 결과를 도출하였다. 예측된 간극률은 train과 validation으로 구분하여 분석하였으며, 실제 데이터와 비교하였을 경우 결정계수는 각각 0.97과 0.98로 나타나 높은 신뢰성을 보여준다. 해당 연구에서는 error norm 분석을 통해 민감도가 작은 인자는 배제하고 영향성이 높은 인자를 통해 종속 변수를 예측하는 방법론을 제시하였다.

Keywords

References

  1. Alqahtani, N., Armstrong, R. T., and Mostaghimi, P. (2018, October), Deep learning convolutional neural networks to predict porous media properties. In SPE Asia Pacific oil and gas conference and exhibition (p. D012S032R010). SPE. 
  2. Barak, M. S., Kumar, M., Kumari, M., and Singh, A. (2020), "Inhomogeneous Wave Propagation in Partially Saturated Soils", Wave Motion, Vol.93, 102470. 
  3. Choi, S. K., Yoon, H. K., Kim, Y. S., Kim, S. W., Choi, H. J., and Min, D. H. (2024), "IInvestigation of Underground buried Cables based on Ground Penetrating Radar Data", Journal of The Korean Geotechnical Society, Vol.40, No.2, pp.105-113. 
  4. Choo, H., Jun, H., and Yoon, H. K. (2018), "Porosity Estimation of Unsaturated Soil Using Brutsaert Equation", Soil Dynamics and Earthquake Engineering, Vol.104, pp.33-39. 
  5. Go, G. H., Jeon, J. S., Kim, Y. S., Kim H. W., and Choi, H. J. (2022), "Prediction of Hydrodynamic Behavior of Unsaturated Ground Due to Hydrogen Gas Leakage in a Low-depth Underground Hydrogen Storage Facility", Journal of The Korean Geotechnical Society, Vol.38, No.11, pp.107-118. 
  6. Jang, B. S., Kim, Y. S., Kim, S. W., Choi, H. J., and Yoon, H. K. (2023), "Assessment of Frozen Soil Characterization Via Electrical Resistivity Survey", Journal of The Korean Geotechnical Society, Vol.39, No.12, pp.115-125. 
  7. Jang, B. S., Kim, Y. S., Kim, S. W., Choi, H. J., and Yoon, H. K. (2023), "Assessment of Applicability of CNN Algorithm for Interpretation of Thermal Images Acquired in Superficial Defect Inspection Zones", Journal of The Korean Geotechnical Society, Vol.39, No.10, pp.41-48. 
  8. Kim, H. W. and Go, G. H. (2023), "Study on the Thermal Conductivity of Frozen Soil Considering Various Experimental Conditions", Journal of The Korean Geotechnical Society, Vol.39, No.9, 5-11. 
  9. Ko, H. and Choo, H. (2023), "Experimental Study on the Effect of Degree of Saturation on the Electrical Conductivity of Soils", Journal of The Korean Geotechnical Society, Vol.39, No.8, pp. 29-39. 
  10. Lee, J. S. and Lee, S. U. (2022), "Evaluation of Liquefaction Model using Dynamic Centrifuge Test", Journal of The Korean Geotechnical Society, Vol.38, No.11, pp.31-42. 
  11. Lee, S., Han, J. T., Park, K. H., and Kim, J. (2022), "Comparative Study on the Evaluation of Liquefaction Resistance Ratio According to the Application of the Korean Standard for Cyclic Triaxial Strength Test", Journal of The Korean Geotechnical Society, Vol.38, No.9, pp.35-44. 
  12. Lee, S., Ryou, J. E., Seo, J., and Jung, J. (2024), "Soil-Water Characteristic Curves for Drying and Wetting Processes in Granite-Weathered Soil Based on Variations in Fine Contents", Journal of The Korean Geotechnical Society, Vol.40, No.1, pp.47-54. 
  13. Lee, J. S. and Yoon, H. K. (2014), "Porosity Estimation based on Seismic Wave Velocity at Shallow Depths", Journal of Applied Geophysics, Vol.105, pp.185-190. 
  14. Linneman, D. C., Strickland, C. E., and Mangel, A. R. (2021), "Compressional Wave Velocity and Effective Stress in Unsaturated Soil: Potential Application for Monitoring Moisture Conditions in Vadose Zone Sediments". Vadose Zone Journal, Vol.20, No.5, e20143. 
  15. Liu, H., Jiang, M., Zhou, F., and Lu, G. (2021), "Attenuation Characteristics of Thermoelastic Waves in Unsaturated Soil", Arabian Journal of Geosciences, Vol.14, pp.1-11. 
  16. Min, D. H., Kim, Y. S., Kim, S., Choi, H. J., and Yoon, H. K. (2023), "Neural Network-Based Prediction of Dynamic Properties", Journal of The Korean Geotechnical Society, Vol.39, No.12, pp. 37-46. 
  17. Min, D. H. and Yoon, H. K. (2021), "Suggestion for a New Deterministic Model Coupled with Machine Learning Techniques for Landslide Susceptibility Mapping", Scientific reports, Vol.11, No.1, pp.1-24. 
  18. Shin, H. C., Whalley, W. R., Attenborough, K., and Taherzadeh, S. (2016), "On the Theory of Brutsaert about Elastic Wave Speeds in Unsaturated Soils", Soil and Tillage Research, Vol.156, pp.155-165. 
  19. Takbiri, S., Kazemi, M., Takbiri-Borujeni, A., and McIlvain, J. (2022), "A Deep Learning Approach to Predicting Permeability of Porous Media", Journal of Petroleum Science and Engineering, Vol.211, 110069. 
  20. Yan, B., Harp, D. R., Chen, B., Hoteit, H., and Pawar, R. J. (2022), "A Gradient-based Deep Neural Network Model for Simulating Multiphase Flow in Porous Media", Journal of Computational Physics, Vol.463, 111277. 
  21. Yoon, H. K. (2023), "Method for Assessing Landslide Susceptibility Using SMOTE and Classification Algorithms", Journal of The Korean Geotechnical Society, Vol.39, No.6, pp.5-12.