All Issue

2023 Vol.22, Issue 2

Research Article

Comparison of Effective Soil Depth Classification Methods Using Topographic Information

지형정보를 이용한 유효토심 분류방법비교

Byung-Soo Kim1
,
Ju-Sung Choi2
,
Ja-Kyung Lee3
,
Na-Young Jung4
,
Tae-Hyung Kim5*
김 병수1
,
최 주성2
,
이 자경3
,
정 나영4
,
김 태형5*
1Non-Member, Graduate Student, Dept. of Civil and Environmental Engineering, Korea Maritime and Ocean Univ., 727 Taejong-ro, Yeongdo-gu, Busan 49112. Republic of Korea
2Non-Member, Graduate Student, Dept. of Civil and Environmental Engineering, Korea Maritime and Ocean Univ., 727 Taejong-ro, Yeongdo-gu, Busan 49112, Republic of Korea
3Non-Member, Graduate Student, Dept. of Civil and Environmental Engineering, Korea Maritime and Ocean Univ., 727 Taejong-ro, Yeongdo-gu, Busan 49112, Republic of Korea
4Non-Member, Graduate Student, Dept. of Civil and Environmental Engineering, Korea Maritime and Ocean Univ., 727 Taejong-ro, Yeongdo-gu, Busan 49112, Republic of Korea
5Member, Professor, Dept. of Civil Engineering, Korea Maritime and Ocean Univ., 727 Taejong-ro, Yeongdo-gu, Busan 49112, Republic of Korea
*Corresponding Author
30 June 2023. pp. 1-12
PDF XML Citation
Abstract

Research on the causes of landslides and prediction of vulnerable areas is being conducted globally. This study aims to predict the effective soil depth, a critical element in analyzing and forecasting landslide disasters, using topographic information. Topographic data from various institutions were collected and assigned as attribute information to a 100 m × 100 m grid, which was then reduced through data grading. The study predicted effective soil depth for two cases: three depths (shallow, normal, deep) and five depths (very shallow, shallow, normal, deep, very deep). Three classification models, including K-Nearest Neighbor, Random Forest, and Deep Artificial Neural Network, were used, and their performance was evaluated by calculating accuracy, precision, recall, and F1-score. Results showed that the performance was in the high 50% to early 70% range, with the accuracy of the three classification criteria being about 5% higher than the five criteria. Although the grading criteria and classification model's performance presented in this study are still insufficient, the application of the classification model is possible in predicting the effective soil depth. This study suggests the possibility of predicting more reliable values than the current effective soil depth, which assumes a large area uniformly.

Keywords
Effective soil depth
Classification
K-nearest neighbor
Random forest
Deep neural network

국내외적으로 다양한 산사태 발생원인 분석과 취약지역의 예측이 이루어지고 있다. 본 연구에서는 산사태에서 발생하는 재해의 분석 및 예측에 사용되는 많은 특성 중 필수적인 요소인 유효토심을 지형정보를 이용해 예측했다. 지형정보 데이터를 각 기관별로 획득한 후 100m × 100m의 격자에 속성정보로 할당하고 데이터 등급화를 통해 차원을 축소 시켜주었다. 분류 기준으로 3개 깊이(얕음, 보통, 깊음)와 5개 깊이(매우 얕음, 얕음, 보통, 깊음, 아주 깊음)의 두 가지 경우에 대해 유효토심을 예측했다. K-최근접 이웃, 랜덤 포레스트, 심층인공신경망 모델을 통해 예측하고 정확도, 정밀도, 재현율, F1-점수를 계산해 그 성능을 비교했다. 예측결과 모델에 따라 50% 후반에서 70% 초반의 성능을 보였다. 3개 분류기준의 정확도가 5개 분류기준의 정확도보다 5% 정도 높았다. 본 연구에서 제시한 등급화 기준과 분류모델의 성능은 아직 미흡하지만 유효토심의 예측에 있어서 분류모델의 적용이 가능하다고 판단된다. 큰 지역을 획일적으로 가정하여 사용하는 현재의 유효토심보다 신뢰성 있는 값의 예측이 가능하다고 사료된다.

References
1
Bourennane, H., King, D. and Couturier, A. (2000), “Comparison of kriging with external drift and simple linear regression for predicting soil horizon thickness with different sample densities”, Geoderma, Vol.97, pp.255-271 10.1016/S0016-7061(00)00042-2
2
Breiman, L. (2001), “Random Forests”, Machine Learning, Vol.45, pp.5-32, https://doi.org/10.1023/A:1010933404324 . 10.1023/A:1010933404324.
3
Chan, H. C., Chang, C. C., Chen, P. A. and Lee, J. T. (2019), “Using multinomial logistic regression for prediction of soil depth in an area of complex topography in Taiwan”, Catena, Vol.176, pp.419-429. 10.1016/j.catena.2019.01.030
4
Choi, E. -K., Kim, S. -W., Lee, Y. -C., Lee, K. -H. and Kim, I. -S. (2013), “Analyzing the Disaster Vulnerability of Mt. Baekdusan Area Using Terrain Factors”, Journal of the Korean Earth Science Society, 10.5467/jkess.2013.34.7.605.
5
Choi, E. -K., Kim, S. -W., Cho, J. -W. and Lee, J. -H. (2017), “GIS-based Subsidence Hazard Map in Urban Area”, Journal of the Korean Geotechnical Society, Vol.33, No.10, pp.5-14.
6
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.
7
Costa-Cabral, M. and Burges, S. T. (1994), “Digital elevation model networks (DEMON): A model of flow over hillslopes for computation of contributing and dispersal areas”, Water Resources Research, Vol.30, pp.1681-1692. 10.1029/93WR03512
8
Everitt, B. S., Landau, S., Leese, M. and Stahl, D. (2011), “Miscellaneous Clustering Methods, in Cluster Analysis”, 5th Edition, John Wiley & Sons, Ltd, Chichester, UK. 10.1002/9780470977811
9
Ho, J. -Y., Lee, K. T., Chang, T. -C., Wang, Z. -Y. and Lian, Y.-H. (2012), “Influence of spatial distribution of soil thickness on shallow landslide prediction”, Engineering Geology, Vol.124, pp.38-46. 10.1016/j.enggeo.2011.09.013
10
Karlsson, C. S. J., Jamali, I. A., Earon, R., Olofsson, B. and Mörtberg, U. (2014), “Comparison of methods for predicting regolith thickness in previously glaciated terrain, Stockholm”, Geoderma, 226-227, pp.116-129. 10.1016/j.geoderma.2014.03.003
11
Kim, H. -S., Moon, S. -W. and Seo, Y. -S. (2022), “Analysis of Factors Influencing Landslide Occurrence along a Forest Road Near Sangsan Village”, The Journal of Engineering Geology, Vol.32, No.1, pp.73-83.
12
Kim, J. and Shin, H. (2016), “Slope Stability Assessment on a Landslide Risk Area in Ulsan During Rainfall”, Journal of the Korean Geotechnical Society, Vol.32, No.6, pp.27-40. 10.7843/kgs.2016.32.6.27
13
Kim, M. S., Onda, Y., Uchida, T. and Kim, J. W. (2016), “Effects of soil depth and subsurface flow along the subsurface topography on shallow landslide predictions at the site of a small granitic hillslope”, Geomorphology, Vol.271, pp.40-54. 10.1016/j.geomorph.2016.07.031
14
Kingma, D. P. and Ba, J. L. (2015), “ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION”, International Conference on Learning Representations.
15
Kuriakose, S. K., Devkota, S., Rossiter, D. G. and Jetten, V. G. (2009), “Prediction of soil depth using environmental variables in an anthropogenic landscape”, A Case Study in the Western Ghats of Kerala, India, Catena, Vol.79, pp.27-38. 10.1016/j.catena.2009.05.005
16
Lee, S. W., Kim, G., Yune, C. -Y., Ryu, H. -J., and Hong, S. J. (2012), “Development of Landslide-Risk Prediction Model thorough Database Construction”, Journal of the Korean Geotechnical Society, Vol.28, No.4, pp.23-33. 10.7843/kgs.2012.28.4.23
17
Min, D. -H. and Yoon, H. -K. (2018), “Method for Establishment of High Reliable Soil Depth Modeling”, J. KoreanSoc. Hazard Mitig., Vol.18, No.2, pp.307-315. 10.9798/KOSHAM.2018.18.2.307
18
Penížek, V. and Borůvka, L. (2006), “Soil depth prediction supported by primary terrain attributes: a comparison of methods”, Plant and Soil Environment, Vol.52. 10.17221/3461-PSE
19
Hahnloser, R. H. R., Sarpeshkar, R., Mahowald, M. A., Douglas, R. J. and Seung, H. S. (2000), “Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit”, Nature, Vol.405, No.6789, pp.947-951. 10.1038/3501607210879535
Information
  • Publisher :Korean Geosythetics Society
  • Publisher(Ko) :한국지반신소재학회
  • Journal Title :Journal of the Korean Geosynthetics Society
  • Journal Title(Ko) :한국지반신소재학회 논문집
  • Volume : 22
  • No :2
  • Pages :1-12
  • Received Date : 2023-03-16
  • Revised Date : 2023-04-12
  • Accepted Date : 2023-04-17
  • DOI :https://doi.org/10.12814/jkgss.2023.22.2.001
Journal Informaiton Journal of the Korean Geosynthetics Society Journal of the Korean Geosynthetics Society
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close