Comparative Analysis of Prediction Performance of Mine Subsidence Using Machine Learning Techniques

Hosang Han; Kyoik Choi; Jangwon Suh

doi:10.32390/ksmer.2022.59.3.265

All Issue

2022 Vol.59, Issue 3 Next Page

Research Paper

Comparative Analysis of Prediction Performance of Mine Subsidence Using Machine Learning Techniques 머신러닝 기법을 이용한 광산 지반침하 예측 성능의 비교분석

30 June 2022. pp. 265-275

PDF XML

Abstract

In this study, the prediction of mining-induced subsidence is analyzed and compared using various machine learning models. Factors affecting the occurrence of subsidence are identified from eight and 1,730 sets of subsidence data. Five machine learning models are selected, i.e., Adaboost, artificial neural networks, the k-nearest neighbor, random forest, and the support vector machine, which are frequently used in studies related to geohazard prediction. In addition, the stacking technique is applied to five algorithms based on 10 combinations, and the predictive performance of each ensemble method is evaluated and compared. To evaluate the classification performance of the machine learning technique applied in this study, recall is used as an evaluation index, which describes the ratio of the predicted ground subsidence instead of the area under curve used previously. Based on the values of recall, the random forest demonstrates the best performance (with a recall of 0.955). The recall is expected to be a more reliable evaluation index for predicting subsidence occurrences compared with other indices.

Keywords

Mine subsidence

Machine learning

Random forest

Recall

Area Under the Curve

본 연구에서는 폐광 지역의 지반침하 발생 예측에 활용되는 다양한 머신러닝 기법의 예측 성능을 비교·분석하였다. 광산 지반침하 발생 여부에 영향을 미치는 인자는 총 8개로 구성하였고, 1,730개의 지반침하 데이터를 획득하였다. 머신러닝 기법은 지반재해 예측에 대한 문헌에서 주로 활용되는 Adaboost, ANN(Artificial Neural Network), kNN(k-Nearest Neighbor), RF(Random Forest), SVM(Support Vector Machine) 등 5개를 선정하였다. 또한, 5개 알고리즘에 Stacking 기법을 적용하여 10개 조합으로 나누어 각각의 앙상블 기법들의 예측 성능을 비교하였다. 본 연구에서 적용된 머신러닝 기법의 분류 성능 평가 지표로는 기존에 사용되던 AUC(area under the curve)가 아닌 실제로 발생된 지반침하를 맞게 예측하는 비율을 의미하는 Recall에 중점을 두었다. Recall에 기반한 결과, RF 기법이 0.955로 가장 높은 성능을 나타내었다. 이는 지반침하 발생 여부를 예측하는데 기존 기법보다 신뢰성 있는 평가 기준이 될 수 있을 것으로 기대된다.

키워드

광산 지반침하

머신러닝

랜덤포레스트

재현율

곡선하면적비율

References

Ahatonovic-Kustrin, S. and Beresford, R., 2000. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research, Journal of Pharmaceutical and Biomedical Analysis, 22(5), p.717-727. 10.1016/S0731-7085(99)00272-1

An, T.K. and Kim, M.H., 2010. A New Diverse AdaBoost Classifier, 2010 International Conference on Artificial Intelligence and Computational Intelligence, IEEE, Sanya, China, p.359-363. 10.1109/AICI.2010.8221244736

Breiman, L., 2001. Random forests, Machine Learning, 45(1), p.5-32. 10.1023/A:1010933404324

Bui, D.T., Shahabi, H., Shirzadi, A., Chapi, K., Pradhan, B., Chen, W., Khosravi, K., Panahi, M., Ahmad, B.B., and Lee, S., 2018. Land subsidence susceptibility mapping in south korea using machine learning algorithms, Sensors, 18(8), 2464p. 10.3390/s1808246430065216PMC6111310

Choi, J.K., Kim, K.D., Lee, S., and Won, J.S., 2010. Application of a fuzzy operator to susceptibility estimations of coal mine subsidence in Taebaek City, Korea, Environmental Earth Sciences, 59(5), p.1009-1022. 10.1007/s12665-009-0093-6

Choi, J.K., Kim, K.D., Lee, S., Kim, I.S., and Won, J.S., 2007. Prediction of ground subsidence hazard area using GIS and probability model near abandoned underground coal mine, Economic and Environmental Geology, 40(3), p.295-306.

Coal Industry Promotion Board, 2005. Detailed Investigation Report on the Ground Stability of Jeongseon Jeongam Area, p.2-9.

Ebrahimy, H., Feizizadeh, B., Salmani, S., and Azadi H., 2020. A comparative study of land subsidence susceptibility mapping of Tasuj plane, Iran, using boosted regression tree, random forest and classification and regression tree methods, Environmental Earth Sciences, 79(10), p.1-12. 10.1007/s12665-020-08953-0

Hakim, W.L., Achmad, A.R., and Lee, C.W., 2020. Land subsidence susceptibility mapping in Jakarta using functional and meta-ensemble machine learning algorithm based on time-series InSAR data, Remote Sensing, 12(21) 3627p. 10.3390/rs12213627

Jakkula, V. 2006. Tutorial on support vector machine (svm), School of EECS, Washington State University, 37(2.5), 3p.

Jung, D.H. and Choi, Y.S., 2021. Prediction of blast vibration in quarry using machine learning models, Tunnel and Underground Space, 31(6), p.508-519.

Kim, K.D., Lee, S., Oh, H.J., Choi, J.K., and Won, J.S., 2006. Assessment of ground subsidence hazard near an abandoned underground coal mine using GIS, Environmental Geology, 50(8), p.1183-1191. 10.1007/s00254-006-0290-5

Kim, K.D., Lee, S.R., and Oh, H.J., 2009. Prediction of ground subsidence in Samcheok City, Korea using artificial neural networks and GIS, Environmental Geology, 58(1), p.61-70. 10.1007/s00254-008-1492-9

Koo, Y.H., Kim, S.M., Oh, M., and Park, H.D., 2019. Estimation of solar irradiance at weather stations in Korea using regionally trained artificial neural network models, Journal of the Korean Society of Mineral and Energy Resources Engineers, 56(2), p.155-171. 10.32390/ksmer.2019.56.2.155

Kratzsch, H., 1983. Mining Subsidence Engineering, Springer, Berlin, Germany, p. 543. 10.1007/978-3-642-81923-0

Lee, S. and Park, I., 2013. Application of decision tree model for the ground subsidence hazard mapping near abandoned underground coal mines, Journal of environmental management, 127(1), p.166-176. 10.1016/j.jenvman.2013.04.01023702378

Lee, S., Park, I., and Choi, J.K., 2012. Spatial prediction of ground subsidence susceptibility using an artificial neural network, Environmental Management, 49(2), p.347-358. 10.1007/s00267-011-9766-522005969

Lobo, J.M., Jiménez-Valverde, A., and Real, R., 2008. AUC: a misleading measure of the performance of predictive distribution models, Global ecology and Biogeography, 17(2), p.145-151. 10.1111/j.1466-8238.2007.00358.x

Mine Reclamation Corporation, 2019. National mine statistics (Current status by mining species), 2022.04.13., http://www.komir.or.kr

Mohammady, M., Pourghasemi, H.R., and Amiri, M., 2019. Land subsidence susceptibility assessment using random forest machine learning algorithm, Environmental Earth Sciences, 78(16), p.1-12. 10.1007/s12665-019-8518-3

Nam, K.H., Lee, M.J., and Jeong, G.C., 2016. Landslide susceptibility analysis: SVM application of spatial databases considering clay mineral index values extracted from an ASTER satellite image, The Journal of Engineering Geology, 26(1), p.23-32. 10.9720/kseg.2016.1.23

Oh, H.J. and Lee, S., 2010. Assessment of ground subsidence using GIS and the weights-of-evidence model, Engineering Geology, 115(1-2), p.36-48. 10.1016/j.enggeo.2010.06.015

Oh, H.J. and Lee, S., 2011. Integration of ground subsidence hazard maps of abandoned coal mines in Samcheok, Korea, International Journal of Coal Geology, 86(1), p.58-72. 10.1016/j.coal.2010.11.009

Oh, H.J., Ahn, S.C., Choi, J.K., and Lee, S., 2011. Sensitivity analysis for the GIS-based mapping of the ground subsidence hazard near abandoned underground coal mines, Environmental Earth Sciences, 64(2), p.347-358. 10.1007/s12665-010-0855-1

Oh, H.J., Syifa, M., Lee, C.W., and Lee, S., 2019. Land subsidence susceptibility mapping using bayesian, functional, and meta-ensemble machine learning models, Applied Sciences, 9(6), 1248p. 10.3390/app9061248

Park, I., Choi, J., Lee, M J., and Lee, S., 2012. Application of an adaptive neuro-fuzzy inference system to ground subsidence hazard mapping, Computers & Geosciences, 48(1), p.228-238. 10.1016/j.cageo.2012.01.005

Park, I., Lee, J., and Lee, S., 2014. Ensemble of ground subsidence hazard maps using fuzzy logic, Central European Journal of Geosciences, 6(2), p.207-218. 10.2478/s13533-012-0175-y

Pourghasemi, H.R., and Saravi, M.M., 2019. Land-subsidence spatial modeling using the random forest data-mining technique, Spatial Modeling in GIS and R for Earth and Environmental Sciences, 6, p.147-159. 10.1016/B978-0-12-815226-3.00006-5

Sekkeravani, M.A., Bazrafshan, O., Pourghasemi, H.R., and Holisaz, A., 2022. Spatial modeling of land subsidence using machine learning models and statistical methods, Environmental Science and Pollution Research, 29, p.28866-28883. 10.1007/s11356-021-18037-634993808

Son, J., Suh, J., Yi, H., Park, H.D., and Lee, S., 2015. GIS-based subsidence hazard analysis on abandoned coal mine sites combining the frequency ratio and radius of influence, Journal of the Korean Society of Mineral and Energy Resources Engineers, 52(6), p.567-576. 10.12972/ksmer.2015.52.6.567

Suh, J., Choi, Y., and Park, H.D., 2016. GIS-based evaluation of mining-induced subsidence susceptibility considering 3D multiple mine drifts and estimated mined panels, Environmental Earth Sciences, 75(10), p.1-19. 10.1007/s12665-016-5695-1

Suh, J., Choi, Y., Park, H.D., Kwon, H.H., Yoon, S.H., and Go, W.R., 2010. Application of frequency ratio and analytic hierarchy process to subsidence hazard assessment around abandoned coal mine, Journal of the Korean Society for Geosystem Engineering, 47(5), p.690-704.

Suh, J., Choi, Y., Park, H.D., Yoon, S.H., and Go, W.R., 2013. Subsidence Hazard Assessment at the Samcheok Coalfield, South Korea: A Case Study Using GIS, Environmental and Engineering Geoscience, 19(1), p.69-83. 10.2113/gseegeosci.19.1.69

Waltham, T., Park, H.D., Suh, J. Yu, M.H., Kwon, H.H., and Bang, K.M., 2011. Collapses of old mines in Korea, Engineering Geology, 118, p.29-36. 10.1016/j.enggeo.2010.11.007

Yeon. K., 2020. Stacking based ensemble with instance selection in random KNN, Journal of The Korean Data Analysis Society, 22(4), p.1303-1312. 10.37727/jkdas.2020.22.4.1303

Zhang, S., Li, X., Zong, M., Zhu, X., and Cheng, D., 2017. Learning k for knn classification, ACM Transactions on Intelligent Systems and Technology (TIST), 8(3), p1-19. 10.1145/2990508

Information

Publisher :The Korean Society of Mineral and Energy Resources Engineers
Publisher(Ko) :한국자원공학회
Journal Title :Journal of the Korean Society of Mineral and Energy Resources Engineers
Journal Title(Ko) :한국자원공학회지
Volume : 59
No :3
Pages :265-275
Received Date : 2022-04-21
Revised Date : 2022-06-10
Accepted Date : 2022-06-27
DOI :https://doi.org/10.32390/ksmer.2022.59.3.265

Journal of the Korean Society of Mineral and Energy Resources EngineersISSN:2288-0291(Print) 2288-2790(Online)한국자원공학회

All Issue