Empirical Comparison of Supervised Learning Methods for Assessing the Stability of Slopes Adjacent to Military Operation Roads
The Civilian Access Control Zone (CACZ), south of the Demilitarized Zone (DMZ) separating North and South Korea, has functioned as a unique bio-reserve owing to restrictions on human use. However, it is now increasingly threatened by damaged land and slope failures. In this study, a machine-learning...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Forests |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4907/14/6/1237 |
_version_ | 1797594729662119936 |
---|---|
author | SeMyung Kwon Leilei Pan Yongrae Kim Sang In Lee Hyeongkeun Kweon Kyeongcheol Lee Kyujin Yeom Jung Il Seo |
author_facet | SeMyung Kwon Leilei Pan Yongrae Kim Sang In Lee Hyeongkeun Kweon Kyeongcheol Lee Kyujin Yeom Jung Il Seo |
author_sort | SeMyung Kwon |
collection | DOAJ |
description | The Civilian Access Control Zone (CACZ), south of the Demilitarized Zone (DMZ) separating North and South Korea, has functioned as a unique bio-reserve owing to restrictions on human use. However, it is now increasingly threatened by damaged land and slope failures. In this study, a machine-learning-based method was used to assess slope stability by introducing the random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and logistic regression (LR) approaches. These classification models were trained and evaluated on 393 slope stability cases from 2009 to 2019 to assess slope stability in the northern area of the Civilian Control Line, South Korea. For comparison, the performance of these classification models was measured by considering the accuracy, Cohen’s kappa, F1-score, recall rate, precision, and area under the ROC curve (AUC). Furthermore, 14 influencing factors (slope, vegetation, structure conditions, etc.) were considered to explore feature importance. The evaluation and comparison of the results showed that the performance of all classifier models was satisfactory for assessing the stability of the slope, the ability of LR was validated (accuracy = 0.847; AUC = 0.838), and XGBoost proved to be the most efficient method for predicting slope stability (accuracy = 0.903; AUC = 0.900). Among the 14 influencing factors, the external condition was the most important. The proposed supervised learning method offers a promising method for assessing slope status, may be beneficial for government agencies in early-stage risk mitigation, and provides a database for efficient restoration management. |
first_indexed | 2024-03-11T02:27:33Z |
format | Article |
id | doaj.art-589e86c032634068b44b01ae4b0b1275 |
institution | Directory Open Access Journal |
issn | 1999-4907 |
language | English |
last_indexed | 2024-03-11T02:27:33Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Forests |
spelling | doaj.art-589e86c032634068b44b01ae4b0b12752023-11-18T10:28:14ZengMDPI AGForests1999-49072023-06-01146123710.3390/f14061237Empirical Comparison of Supervised Learning Methods for Assessing the Stability of Slopes Adjacent to Military Operation RoadsSeMyung Kwon0Leilei Pan1Yongrae Kim2Sang In Lee3Hyeongkeun Kweon4Kyeongcheol Lee5Kyujin Yeom6Jung Il Seo7Division of Administration, Forest Restoration Center, Korea Association of Forest Enviro-Conservation Technology, 150 Osongsaengmyeong 3-ro, Osong-eup, Heungdeok-gu, Cheongju-si 28165, Chungcheongbuk-do, Republic of KoreaDepartment of Forest Science, Kongju National University, 54 Daehak-ro, Yesan-eup, Yesan-gun 32439, Chungcheongnam-do, Republic of KoreaInstitute of Ecological Restoration, Kongju National University, 54 Daehak-ro, Yesan-eup, Yesan-gun 32439, Chungcheongnam-do, Republic of KoreaInstitute of Ecological Restoration, Kongju National University, 54 Daehak-ro, Yesan-eup, Yesan-gun 32439, Chungcheongnam-do, Republic of KoreaDepartment of Crops and Forestry, Korea National University of Agriculture and Fisheries, 1515 Kongjwipatjwi-ro, Deokjin-gu, Jeonju-si 54874, Jeollabuk-do, Republic of KoreaDepartment of Crops and Forestry, Korea National University of Agriculture and Fisheries, 1515 Kongjwipatjwi-ro, Deokjin-gu, Jeonju-si 54874, Jeollabuk-do, Republic of KoreaCCZ Forest Land Management Office, Korea Forest Conservation Association, 51 Munjeong-ro 40beon-gil, Seo-gu, Daejeon-si 35262, Republic of KoreaDepartment of Forest Science, Kongju National University, 54 Daehak-ro, Yesan-eup, Yesan-gun 32439, Chungcheongnam-do, Republic of KoreaThe Civilian Access Control Zone (CACZ), south of the Demilitarized Zone (DMZ) separating North and South Korea, has functioned as a unique bio-reserve owing to restrictions on human use. However, it is now increasingly threatened by damaged land and slope failures. In this study, a machine-learning-based method was used to assess slope stability by introducing the random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and logistic regression (LR) approaches. These classification models were trained and evaluated on 393 slope stability cases from 2009 to 2019 to assess slope stability in the northern area of the Civilian Control Line, South Korea. For comparison, the performance of these classification models was measured by considering the accuracy, Cohen’s kappa, F1-score, recall rate, precision, and area under the ROC curve (AUC). Furthermore, 14 influencing factors (slope, vegetation, structure conditions, etc.) were considered to explore feature importance. The evaluation and comparison of the results showed that the performance of all classifier models was satisfactory for assessing the stability of the slope, the ability of LR was validated (accuracy = 0.847; AUC = 0.838), and XGBoost proved to be the most efficient method for predicting slope stability (accuracy = 0.903; AUC = 0.900). Among the 14 influencing factors, the external condition was the most important. The proposed supervised learning method offers a promising method for assessing slope status, may be beneficial for government agencies in early-stage risk mitigation, and provides a database for efficient restoration management.https://www.mdpi.com/1999-4907/14/6/1237machine learningslope stabilityvariable importanceforest restoration managementDMZ |
spellingShingle | SeMyung Kwon Leilei Pan Yongrae Kim Sang In Lee Hyeongkeun Kweon Kyeongcheol Lee Kyujin Yeom Jung Il Seo Empirical Comparison of Supervised Learning Methods for Assessing the Stability of Slopes Adjacent to Military Operation Roads Forests machine learning slope stability variable importance forest restoration management DMZ |
title | Empirical Comparison of Supervised Learning Methods for Assessing the Stability of Slopes Adjacent to Military Operation Roads |
title_full | Empirical Comparison of Supervised Learning Methods for Assessing the Stability of Slopes Adjacent to Military Operation Roads |
title_fullStr | Empirical Comparison of Supervised Learning Methods for Assessing the Stability of Slopes Adjacent to Military Operation Roads |
title_full_unstemmed | Empirical Comparison of Supervised Learning Methods for Assessing the Stability of Slopes Adjacent to Military Operation Roads |
title_short | Empirical Comparison of Supervised Learning Methods for Assessing the Stability of Slopes Adjacent to Military Operation Roads |
title_sort | empirical comparison of supervised learning methods for assessing the stability of slopes adjacent to military operation roads |
topic | machine learning slope stability variable importance forest restoration management DMZ |
url | https://www.mdpi.com/1999-4907/14/6/1237 |
work_keys_str_mv | AT semyungkwon empiricalcomparisonofsupervisedlearningmethodsforassessingthestabilityofslopesadjacenttomilitaryoperationroads AT leileipan empiricalcomparisonofsupervisedlearningmethodsforassessingthestabilityofslopesadjacenttomilitaryoperationroads AT yongraekim empiricalcomparisonofsupervisedlearningmethodsforassessingthestabilityofslopesadjacenttomilitaryoperationroads AT sanginlee empiricalcomparisonofsupervisedlearningmethodsforassessingthestabilityofslopesadjacenttomilitaryoperationroads AT hyeongkeunkweon empiricalcomparisonofsupervisedlearningmethodsforassessingthestabilityofslopesadjacenttomilitaryoperationroads AT kyeongcheollee empiricalcomparisonofsupervisedlearningmethodsforassessingthestabilityofslopesadjacenttomilitaryoperationroads AT kyujinyeom empiricalcomparisonofsupervisedlearningmethodsforassessingthestabilityofslopesadjacenttomilitaryoperationroads AT jungilseo empiricalcomparisonofsupervisedlearningmethodsforassessingthestabilityofslopesadjacenttomilitaryoperationroads |