All Issue

2026 Vol.42, Issue 4 Preview Page
Comparative Analysis of the Structural Characteristics of Augmented Geotechnical Property Data for Forest-Road Landslide Hazard Assessment

임도 산사태 위험성 평가를 위한 제한된 지반 물성치 데이터의 증폭 기법별 구조적 특성 비교 분석

Man-Il Kim1
,
Soon Han Chung2
,
JaeHwan Kwak3
,
Hyung-Koo Yoon4*
김 만일1
,
정 순한2
,
곽 재환3
,
윤 형구4*
1Director, Korea Slope Safety Association
2Deputy Director, Ministry of the Interior and safety
3Senior Researcher, Korea Slope Safety Association
4Member, Prof., Dept. of Disaster Safety Engineering, Daejeon Univ.
1비회원, 한국급경사지안전협회 급경사지연구소 소장
2비회원, 행정안전부 안전예방정책실 시설사무관
3비회원, 한국급경사지안전협회 급경사지연구소 선임연구원
4정회원, 대전대학교 재난안전공학과 교수
*Corresponding Author
31 August 2026. pp. 253-262
PDF XML Citation
Abstract

The increasing occurrence of localized heavy rainfall and extreme weather has heightened interest in artificial-intelligence-based landslide hazard assessment. However, limited data availability remains a major challenge in geotechnical engineering. This study compares the structural characteristics of various data augmentation techniques using soil cohesion, friction angle, and soil density, which are closely related to shear strength and landslide hazard. Four techniques—the synthetic minority oversampling technique (SMOTE), adaptive synthetic sampling (ADASYN), kriging, and the Monte Carlo–genetic algorithm (MC-GA)—are applied to generate geotechnical property data. The generated datasets are evaluated using probability density functions, mean comparisons, Pearson correlation analysis, and principal component analysis. In addition, changes in the distribution range and correlation structure according to the augmentation techniques are investigated. The results indicate that SMOTE and ADASYN largely preserved the structural characteristics of the original dataset, whereas kriging tended to strengthen correlations among specific variables. MC-GA produced the widest distribution range but showed reduced intervariable structural consistency. Therefore, selecting augmentation techniques for landslide hazard assessment with limited geotechnical data should consider both dataset size and preservation of intervariable structure.

Keywords
Artificial intelligence
Data augmentation
Geotechnical properties
Landslide hazard
Shear strength

최근 집중호우 및 이상기후의 증가로 인해 산사태 위험성 평가를 위한 인공지능 기반 연구가 증가하고 있으나, 지반공학 분야에서는 제한된 데이터 확보 문제가 여전히 중요한 한계로 작용하고 있다. 본 연구에서는 산사태 위험성과 관련된 전단강도 특성을 고려하여 soil cohesion, friction angle 및 soil density를 대상으로 다양한 데이터 증폭 기법의 구조적 특성을 비교 분석하고자 하였다. 이를 위해 SMOTE, ADASYN, Kriging 및 Monte Carlo–Genetic Algorithm(MC-GA) 기반 데이터 증폭 기법을 적용하여 지반 물성치 데이터를 생성하였다. 이후 확률밀도함수, 평균값 비교, Pearson correlation 및 Principal Component Analysis(PCA)를 이용하여 각 기법에 따른 데이터 분포 및 구조적 특성을 분석하였다. 또한 데이터 증폭 기법에 따라 생성되는 데이터의 분포 범위와 상관구조 변화를 비교하였다. 분석 결과, SMOTE와 ADASYN은 원시 데이터의 구조적 특성을 비교적 안정적으로 유지하는 경향을 보였으며, Kriging은 특정 변수 간 상관성을 강화하는 특성을 보였다. MC-GA는 가장 넓은 데이터 분포 범위를 형성하였으나, 변수 간 구조적 일관성은 상대적으로 감소하는 경향을 나타내었다. 따라서 제한된 지반 데이터 조건에서 산사태 위험성 평가를 위한 데이터 증폭 기법 적용 시, 단순한 데이터 수 증가뿐만 아니라 생성 데이터의 구조적 특성 역시 함께 고려할 필요가 있는 것으로 판단된다.

References
1

Boumpoulis, V., Depountis, N., Dimas, A., and Papatheodorou, G. (2025), “Presentation and Analysis of the Geotechnical Coastal Vulnerability Index and Validation of its Application to Coastal Erosion Problems”, Scientific Reports, Vol.15, No.1, 1424, https://doi.org/10.1038/s41598-025-85594-y.

10.1038/s41598-025-85594-y39789131PMC11718066
2

De Hond, A. A., Van Buchem, M. M., and Hernandez-Boussard, T. (2022), “Picture a Data Scientist: A Call to Action for Increasing Diversity, Equity, and Inclusion in the Age of AI”, Journal of the American Medical Informatics Association, Vol.29, No.12, pp.2178-2181, https://doi.org/10.1093/jamia/ocac156.

10.1093/jamia/ocac15636048021PMC9667164
3

Jing, Y., Li, Y., Chang, J., Liu, Z., Ni, Z., Wang, Q., and Gao, D. (2025), “Factor of Safety Prediction for Slope Stability Using PCA and BPNN in Guangdong’s H Mining Area”, Scientific Reports, Vol.15, No.1, 12804, https://doi.org/10.1038/s41598-025-95498-6.

10.1038/s41598-025-95498-640229417PMC11997092
4

Kim, S. H. and Kim Y. U. (2025), “Development of Artificial Intelligence-Assisted Automation Grouting System and its Field Applicability Evaluation”, Journal of the Korean Geotechnical Society, Vol.41, No.4, pp.203-214, https://doi.org/10.7843/kgs.2025.41.4.203.

10.7843/kgs.2025.41.4.203
5

Kim, Y., Lee, H., Lee, S. J., and Na, S. (2025), “Evaluation of AI-Based Prediction for Ground Subsidence and Its Feature Importance Analysis Using Imbalanced Multivariate Data”, Journal of the Korean Geotechnical Society, Vol.41, No.6, pp.179-193, https://doi.org/10.7843/kgs.2025.41.6.179.

10.7843/kgs.2025.41.6.179
6

Kwon, H. J. and Kim, G. W. (2014), “Rock Slope Failure Analysis and Landslide Risk Map by Using GIS”, Journal of the Korean Geotechnical Society, Vol.30, No.12, pp.15-25, https://doi.org/10.7843/kgs.2014.30.12.15.

10.7843/kgs.2014.30.12.15
7

Lee, S. C., Hong, M. H., and Jeong, S. S. (2023), “Landslide Analysis Using the Wetting-Drying Process-Based Soil-Water Characteristic Curve and Field Monitoring Data”, Journal of the Korean Geotechnical Society, Vol.39, No.5, pp.13-26, https://doi.org/10.7843/kgs.2023.39.5.13.

10.7843/kgs.2023.39.5.13
8

Lee, G. S., Oh, J. W., and Lee, K, I. (2025), “A Study on the Application of an AI Model for Joint Detection using NM-GPR”, Journal of the Korean Geotechnical Society, Vol.41, No.3, pp.15-24, https://doi.org/10.7843/kgs.2025.41.3.15.

10.7843/kgs.2025.41.3.15
9

Lim, H., Jang, J. H., Song, K. I., and Kwon, T. H. (2024), “Slope Stability Analysis and Development of a Landslide Early Warning System for Mountain-Based Solar Power Plants”, Journal of the Korean Geotechnical Society, Vol.40, No.6, pp.139-149, https://doi.org/10.7843/kgs.2024.40.6.139.

10.7843/kgs.2024.40.6.139
10

Oh, S., Ahn, T. M., and Byung, G. J. (2024), “Case Study of Landslide Analysis due to Typhoon Hinnamnoh using Water Retention Characteristics based on the Evaporation Method”, Journal of the Korean Geotechnical Society, Vol.40, No.3, pp.7-18, https://doi.org/10.7843/kgs.2024.40.3.7.

10.7843/kgs.2024.40.3.7
11

Pan, H., Shuai, J., Li, J., Li, H., Zhang, H., Zhang, T., and Ji, X. (2025), “Analysis of Deformation Behavior Characteristics of Double-Prevention Boreholes Based on Pearson Correlation Coefficient: Analysis of Deformation Behavior”, Rock Mechanics and Rock Engineering, Vol.58, No.6, pp.6893-6915, https://doi.org/10.1007/s00603-025-04500-0.

10.1007/s00603-025-04500-0
12

Park, J. and Yoon, H. K (2025), “Methodology for Generating Diverse Geotechnical Datasets using Monte Carlo Simulation and Genetic Algorithms”, Computer‐Aided Civil and Infrastructure Engineering, Vol.40, No.29, pp.5494-5511, https://doi.org/10.1111/mice.70106.

10.1111/mice.70106
13

Roche, C., Wall, P. J., and Lewis, D. (2023), “Ethics and Diversity in Artificial Intelligence Policies, Strategies and Initiatives”, AI and Ethics, Vol.3, No.4, pp.1095-1115, https://doi.org/10.1007/s43681-022-00218-9.

10.1007/s43681-022-00218-936246014PMC9540088
14

Sangprasat, K., Puttiwongrak, A., and Inazumi, S. (2025), “Review of Correlations Between Soil Electrical Resistivity and Geotechnical Properties”, Geosciences, Vol.15, No.5, 166, https://doi.org/10.3390/geosciences15050166.

10.3390/geosciences15050166
15

Shams, R. A., Zowghi, D., and Bano, M. (2025), “AI and the Quest for Diversity and Inclusion: A Systematic Literature Review”, AI and Ethics, Vol.5, No.1, pp.411-438, https://doi.org/10.1007/s43681-023-00362-w.

10.1007/s43681-023-00362-w
16

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, https://doi.org/10.7843/kgs.2023.39.6.5.

10.7843/kgs.2023.39.6.5
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 :4
  • Pages :253-262
  • Received Date : 2026-08-06
  • Revised Date : 2026-08-13
  • Accepted Date : 2026-08-13
  • DOI :https://doi.org/10.7843/kgs.2026.42.4.253
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