머신러닝 기법을 이용한 광산 지반침하 예측 성능의 비교분석
Comparative Analysis of Prediction Performance of Mine Subsidence Using Machine Learning Techniques
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 연구에서는 폐광 지역의 지반침하 발생 예측에 활용되는 다양한 머신러닝 기법의 예측 성능을비교·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 적용된머신러닝 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 기존기법보다 신뢰성 있는 평가 기준이 될 수 있을 것으로 기대된다.
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.
참고문헌 (36)
- Ahatonovic-Kustrin, S., "Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research", Journal of Pharmaceutical and Biomedical Analysis, 22(5), pp.717~727 (2000)
- An, T.K., "A New Diverse AdaBoost Classifier", 2010 International Conference on Artificial Intelligence and Computational Intelligence, pp.359~363 (2010), IEEE
- Breiman, L., "Random forests", Machine Learning, 45(1), pp.5~32 (2001)
- Bui, D. T., "Land subsidence susceptibility mapping in south korea using machine learning algorithms", Sensors, 18(8), pp.2464~ (2018)
- Choi, J. K., "Application of a fuzzy operator to susceptibility estimations of coal mine subsidence in Taebaek City, Korea", Environmental Earth Sciences, 59(5), pp.1009~1022 (2010)
- 최종국, "GIS 및 확률모델을 이용한 폐탄광 지역의 지반침하 위험 예측", 자원환경지질, 40(3), pp.295~306 (2007), 대한자원환경지질학회
- Detailed Investigation Report on the Ground Stability of Jeongseon Jeongam Area, "Coal Industry Promotion Board", 2~9 (2005)
- Ebrahimy, H., "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), pp.1~12 (2020)
- Hakim, W. L., "Land subsidence susceptibility mapping in Jakarta using functional and meta-ensemble machine learning algorithm based on time-series InSAR data", Remote Sensing, 12(21), pp.3627~ (2020)
- Jakkula, V., "Tutorial on support vector machine (svm), 37(2.5)", School of EECS, Washington State University, 3~ (2006)
- 정다희, "머신러닝 모델을 이용한 석산 개발 발파진동 예측", 터널과 지하공간, 31(6), pp.508~519 (2021), 한국암반공학회
- Kim, K. D., "Assessment of ground subsidence hazard near an abandoned underground coal mine using GIS", Environmental Geology, 50(8), pp.1183~1191 (2006)
- Kim, K. D., "Prediction of ground subsidence in Samcheok City, Korea using artificial neural networks and GIS", Environmental Geology, 58(1), pp.61~70 (2009)
- 구영현, "권역별 인공신경망 모델을 이용한 전국 기상관측소의 일사량 추정", 한국자원공학회지, 56(2), pp.155~171 (2019), 한국자원공학회
- Kratzsch, H., "Mining Subsidence Engineering", pp.543~ (1983), Springer
- Lee, S., "Application of decision tree model for the ground subsidence hazard mapping near abandoned underground coal mines", Journal of environmental management, 127(1), pp.166~176 (2013)
- Lee, S., "Spatial prediction of ground subsidence susceptibility using an artificial neural network", Environmental Management, 49(2), pp.347~358 (2012)
- Lobo, J. M., "AUC: a misleading measure of the performance of predictive distribution models", Global ecology and Biogeography, 17(2), pp.145~151 (2008)
- "National mine statistics (Current status by mining species)" (2019)[URL]
- Mohammady, M., "Land subsidence susceptibility assessment using random forest machine learning algorithm", Environmental Earth Sciences, 78(16), pp.1~12 (2019)
- 남경훈, "산사태 취약성 분석 : ASTER 위성영상을 이용한 점토광물인자 추출 및 공간데이터베이스의 SVM 통계기법 적용", 지질공학, 26(1), pp.23~32 (2016), 대한지질공학회
- Oh, H.J., "Assessment of ground subsidence using GIS and the weights-of-evidence model", Engineering Geology, 115(1-2), pp.36~48 (2010)
- Oh, H.J., "Integration of ground subsidence hazard maps of abandoned coal mines in Samcheok, Korea", International Journal of Coal Geology, 86(1), pp.58~72 (2011)
- Oh, H. J., "Sensitivity analysis for the GIS-based mapping of the ground subsidence hazard near abandoned underground coal mines", Environmental Earth Sciences, 64(2), pp.347~358 (2011)
- Oh, H. J., "Land subsidence susceptibility mapping using bayesian, functional, and meta-ensemble machine learning models", Applied Sciences, 9(6), pp.1248~ (2019)
- Park, I., "Application of an adaptive neuro-fuzzy inference system to ground subsidence hazard mapping", Computers & Geosciences, 48(1), pp.228~238 (2012)
- Park, I., "Ensemble of ground subsidence hazard maps using fuzzy logic", Central European Journal of Geosciences, 6(2), pp.207~218 (2014)
- Pourghasemi, H. R., "Land-subsidence spatial modeling using the random forest data-mining technique", Spatial Modeling in GIS and R for Earth and Environmental Sciences, 6, pp.147~159 (2019)
- Sekkeravani, M. A., "Spatial modeling of land subsidence using machine learning models and statistical methods", Environmental Science and Pollution Research, 29, pp.28866~28883 (2022)
- 손진, "빈도비 모델과 지표 영향 반경을 결합한 GIS 기반의 폐탄광지역지반침하 위험도 분석기법 개발", 한국자원공학회지, 52(6), pp.567~576 (2015), 한국자원공학회
- Suh, J., "GIS-based evaluation of mining-induced subsidence susceptibility considering 3D multiple mine drifts and estimated mined panels", Environmental Earth Sciences, 75(10), pp.1~19 (2016)
- 서장원, "폐광산지역의 광역적 지반침하 위험도 평가를 위한 빈도비모델과 계층분석기법의 적용", 한국자원공학회지, 47(5), pp.690~704 (2010), 한국자원공학회
- Suh, J., "Subsidence Hazard Assessment at the Samcheok Coalfield, South Korea: A Case Study Using GIS", Environmental and Engineering Geoscience, 19(1), pp.69~83 (2013)
- Waltham, T., "Collapses of old mines in Korea", Engineering Geology, 118, pp.29~36 (2011)
- 연규필, "Stacking Based Ensemble with Instance Selection in Random KNN", Journal of The Korean Data Analysis Society, 22(4), pp.1303~1312 (2020), 한국자료분석학회[DOI]
- Zhang, S., "Learning k for knn classification", ACM Transactions on Intelligent Systems and Technology (TIST), 8(3), pp.1~19 (2017)
