Evidential Belief Function, Weight of Evidence 및 Artificial Neural Network 모델을 이용한 산사태 공간 취약성 예측 연구 = Landslide Susceptibility Prediction using Evidential Belief Function, Weight of Evidence and Artificial Neural Network Models

다국어 초록 (Multilingual Abstract)

The purpose of this study was to analyze landslide susceptibility in the Pyeongchang area using Weight of Evidence (WOE) and Evidential Belief Function (EBF) as probability models and Artificial Neural Networks (ANN) as a machine learning model in a geographic information system (GIS). This study examined the widespread shallow landslides triggered by heavy rainfall during Typhoon Ewiniar in 2006, which caused serious property damage and significant loss of life. For the landslide susceptibility mapping, 3,955 landslide occurrences were detected using aerial photographs, and environmental spatial data such as terrain, geology, soil, forest, and land use were collected and constructed in a spatial database. Seventeen factors that could affect landsliding were extracted from the spatial database. All landslides were randomly separated into two datasets, a training set (50%) and validation set (50%), to establish and validate the EBF, WOE, and ANN models. According to the validation results of the area under the curve (AUC) method, the accuracy was 74.73%, 75.03%, and 70.87% for WOE, EBF, and ANN, respectively. The EBF model had the highest accuracy. However, all models had predictive accuracy exceeding 70%, the level that is effective for landslide susceptibility mapping. These models can be applied to predict landslide susceptibility in an area where landslides have not occurred previously based on the relationships between landslide and environmental factors. This susceptibility map can help reduce landslide risk, provide guidance for policy and land use development, and save time and expense for landslide hazard prevention. In the future, more generalized models should be developed by applying landslide susceptibility mapping in various areas.

국문 초록 (Abstract)

본 연구는 지리정보시스템(GIS) 환경에서 확률 모델인 Weight Of Evidence (WOE)와 Evidential Belief Function (EBF), 기계학습 모델인 Artificial Neural Networks (ANN) 모델을 이용하여 평창지역의 산사태 취약성도를 공간적으로 분석하고 예측하였다. 본 연구지역은 2006년 태풍 에위니아에 의한 집중호우로 산사태가 많이 발생하여 많은 재산 및 인명피해가 발생하였다. 산사태 취약성도를 작성하기 위해 항공사진을 이용하여3,955개의 방대한 산사태 발생 위치를 탐지하였고, 환경공간정보인 지형, 지질, 토양, 산림 및 토지이용 등의 공간 데이터를 수집하여 공간데이터베이스에 구축하였다. 이러한 공간데이터베이스를 이용하여 산사태에 영향을 줄 수 있는 인자 17개를 추출하여 입력 인자와 EBF, WOE, ANN 모델을 이용하여 산사태 취약성도를 작성하고 검증하였다. 작성 및 검증을 위해 산사태 자료는 각각 50%씩 나누어서 훈련 및 검증을 실시하였고, 검증결과 WOE 모델의 경우는 74.73%, EBF 모델의 경우는 75.03%, ANN 모델의 경우는 70.87%의 예측 정확도를나타내었다. 본 연구에 사용된 모델 중 EBF 모델이 가장 높은 정확도를 나타냈으며, 모든 모델에서 70% 이상의 예측 정확도를 보여 본 연구에서 사용된 기법이 산사태 취약성도 작성에 유효함을 나타내었다. 본 연구에서제안된 WOE, EBF, ANN 모델과 산사태 취약성도는 이전에 산사태가 발생하지 않은 지역의 산사태를 예측하는 데 사용될 수 있다. 이러한 취약성도는 산사태 위험 감소를 촉진하고, 토지 이용 정책 및 개발을 위한 기초자료 역할을 할 수 있으며, 궁극적으로 산사태 재해 예방을 위한 시간과 비용을 절약할 수 있다. 향후 보다 많은지역에서 산사태 취약성도 작성 방법을 적용하여 산사태 위험 예측을 위한 일반화된 모델을 이끌어 내야 한다.

참고문헌 (Reference)

1 Dempster, A. P., "Upper and lower probabilities induced by a multivalued mapping" 38 (38): 325-339, 1967

2 Chen, W., "Spatial prediction of landslide susceptibility using an adaptive neuro-fuzzy inference system combined with frequency ratio, generalized additive model, and support vector machine techniques" 297 : 69-85, 2017

3 Lee, S., "Spatial Landslide Hazard Prediction Using Rainfall Probability and a Logistic Regression Model" 47 (47): 565-589, 2015

4 Edeso, J. M., "Soil erosion under different harvesting managements in steep forest lands from northern Spain" 10 (10): 79-88, 1999

5 Pham, B. T., "Rotation forest fuzzy rule-based classifier ensemble for spatial prediction of landslides using GIS" 83 (83): 97-127, 2016

6 Lee, S., "Probabilistic landslide hazards and risk mapping on Penang Island, Malaysia" 115 (115): 661-672, 2006

7 Pourghasemi, H. R., "Prediction of the landslide susceptibility : Which algorithm, which precision?" 162 : 177-192, 2018

8 Song, K. Y., "Prediction of landslides using ASTER imagery and data mining models" 49 (49): 978-993, 2012

9 Chen, W., "Performance evaluation of GIS-based new ensemble data mining techniques of adaptive neuro-fuzzy inference system (ANFIS) with genetic algorithm (GA), differential evolution (DE), and particle swarm optimization (PSO) for landslide spatial modelling" 157 : 310-324, 2017

10 Jebur, M. N., "Optimization of landslide conditioning factors using very high-resolution airborne laser scanning (LiDAR) data at catchment scale" 152 : 150-165, 2014

11 An, P., "On knowledge based approach to integrating remote sensing, geophysical and geological information" Center NASA 1 : 34-38, 1992

12 Kaab, A., "Monitoring high-mountain terrain deformation from repeated air- and spaceborne optical data: examples using digital aerial imagery and ASTER data" 57 (57): 39-52, 2002

13 Lee, J. H., "Modeling landslide susceptibility in data-scarce environments using optimized data mining and statistical methods" 303 : 284-298, 2018

14 Jaafari, A., "Meta optimization of an adaptive neuro-fuzzy inference system with grey wolf optimizer and biogeography-based optimization algorithms for spatial prediction of landslide susceptibility" 175 : 430-445, 2019

15 Felicisimo, A. M., "Mapping landslide susceptibility with logistic regression, multiple adaptive regression splines, classification and regression trees, and maximum entropy methods: A comparative study" 10 (10): 175-189, 2013

16 Razavizadeh, S., "Mapping landslide susceptibility with frequency ratio, statistical index, and weights of evidence models: a case study in northern Iran" 76 (76): 499-, 2017

17 Dhakal, A. S., "Long-term modeling of landslides for different forest management practices" 28 (28): 853-868, 2003

18 Chauhan, S., "Landslide susceptibility zonation of the Chamoli region, Garhwal Himalayas, using logistic regression model" 7 (7): 411-423, 2010

19 Pham, B. T., "Landslide susceptibility modeling using Reduced Error Pruning Trees and different ensemble techniques: Hybrid machine learning approaches" 175 : 203-218, 2019

20 Hong, H., "Landslide susceptibility mapping using J48 Decision Tree with AdaBoost, Bagging and Rotation Forest ensembles in the Guangchang area (China)" 163 : 399-413, 2018

21 Lee, S., "Landslide susceptibility mapping in the Damrei Romel area, Cambodia using frequency ratio and logistic regression models" 50 (50): 847-855, 2006

22 Chen, W., "Landslide susceptibility mapping based on GIS and support vector machine models for the Qianyang County, China" 75 (75): 474-, 2016

23 Anbalagan, R., "Landslide susceptibility evaluation and zonation mapping in mountainous terrain" 32 (32): 269-277, 1992

24 Kincal, C., "Landslide susceptibility assessment in the Izmir (West Anatolia, Turkey) city center and its near vicinity by the logistic regression method" 59 (59): 745-756, 2009

25 Hong, H., "Landslide susceptibility assessment in Lianhua County (China): A comparison between a random forest data mining technique and bivariate and multivariate statistical models" 259 : 105-118, 2016

26 Pradhan, B., "Landslide susceptibility assessment and factor effect analysis : backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling" 25 (25): 747-759, 2010

27 Lee, S., "Landslide detection and susceptibility mapping in the Sagimakri area, Korea using KOMPSAT-1 and weight of evidence technique" 70 (70): 3197-3215, 2013

28 Fatemi Aghda, S. M., "Landslide Susceptibility Mapping Using Fuzzy Logic System and Its Influences on Mainlines in Lashgarak Region, Tehran, Iran" 36 (36): 915-937, 2018

29 Oh, H. -J., "Landslide Susceptibility Assessment Using Frequency Ratio Technique with Iterative Random Sampling" 2017 : 21-, 2017

30 Moon, W. M., "Integration of remote sensing and geological/geophysical data using Dempster-Shafer approach" 2 : 838-841, 1989

31 Bonham-Carter, G. F., "Integration of geological datasets for gold exploration in Nova Scotia" 54 (54): 1585-1592, 1988

32 Bonham-Carter, G. F., "Geographic Information Systems for geoscientists, modeling with GIS" Pergamon Press 1994

33 Chen, W., "GIS-based landslide susceptibility evaluation using a novel hybrid integration approach of bivariate statistical based random forest method" 164 : 135-149, 2018

34 Hines, J. W., "Fuzzy and neural approaches in engineering" Wiley Press 1997

35 Lee, M. J., "Forecasting and validation of landslide susceptibility using an integration of frequency ratio and neuro-fuzzy models: a case study of Seorak mountain area in Korea" 74 (74): 413-429, 2015

36 Conoscenti, C., "Exploring the effect of absence selection on landslide susceptibility models : A case study in Sicily, Italy" 261 : 222-235, 2016

37 Feizizadeh, B., "Evaluating fuzzy operators of an object-based image analysis for detecting landslides and their changes" 293 : 240-254, 2017

38 Lee, M. J., "Ensemble-based landslide susceptibility maps in Jinbu area, Korea" 67 (67): 23-37, 2012

39 Wright, D.F., "EXTECH I, a multidisciplinary approach to massive sulphide research in the Rusty Lake-Snow Lake Greenstone Belts, Manitoba" Natural Resources Canada 402-, 1996

40 Moore, I. D., "Digital terrain modelling : a review of hydrological, geomorphological, and biological applications" 5 (5): 3-30, 1991

41 Florinsky, I. V., "Digital Terrain Analysis in Soil Science and Geology" Elsevier Press 2012

42 Lee, S., "Detection of landslides using web-based aerial photographs and landslide susceptibility mapping using geospatial analysis" 33 (33): 4937-4966, 2012

43 Saro Lee, "Current and Future Status of GIS-based Landslide Susceptibility Mapping: A Literature Review" 대한원격탐사학회 35 (35): 179-193, 2019

44 Zhu, A. X., "Comparison of the presence-only method and presence-absence method in landslide susceptibility mapping" 171 : 222-233, 2018

45 Lei Chu, "Comparison of landslide susceptibility maps using random forest and multivariate adaptive regression spline models in combination with catchment map units" 한국지질과학협의회 23 (23): 341-355, 2019

46 Choi, J., "Combining landslide susceptibility maps obtained from frequency ratio, logistic regression, and artificial neural network models using ASTER images and GIS" 124 (124): 12-23, 2012

47 Martha, T. R., "Characterising spectral, spatial and morphometric properties of landslides for semi-automatic detection using object-oriented methods" 116 (116): 24-36, 2010

48 Kalantar, B., "Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN)" 9 (9): 49-69, 2018

49 Tsangaratos, P., "Applying Information Theory and GIS-based quantitative methods to produce landslide susceptibility maps in Nancheng County, China" 14 (14): 1091-1111, 2017

50 Lee, S., "Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing data" 26 (26): 1477-1491, 2005

51 Pourghasemi, H. R., "Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed, Iran" 63 (63): 965-996, 2012

52 Carranza, E. J. M., "Application of data-driven evidential belief functions to prospectivity mapping for aquamarine-bearing pegmatites" 14 (14): 47-63, 2005

53 Lee, S., "Application of data-driven evidential belief functions to landslide susceptibility mapping in Jinbu, Korea" 100 : 15-30, 2013

54 Oh, H. J., "Application of a neuro-fuzzy model to landslide-susceptibility mapping for shallow landslides in a tropical hilly area" 37 (37): 1264-1276, 2011

55 Park, N. W., "Application of Dempster-Shafer theory of evidence to GIS-based landslide susceptibility analysis" 62 (62): 367-376, 2011

56 Lee, S., "Application and verification of fuzzy algebraic operators to landslide susceptibility mapping" 52 (52): 615-623, 2007

57 Dou, J., "An integrated artificial neural network model for the landslide susceptibility assessment of Osado Island, Japan" 78 (78): 1749-1776, 2015

58 Mezaal, M. R., "An improved algorithm for identifying shallow and deep-seated landslides in dense tropical forest from airborne laser scanning data" 167 : 147-159, 2018

59 Bui, D. T., "A novel hybrid evidential belief function-based fuzzy logic model in spatial prediction of rainfall-induced shallow landslides in the Lang Son city area (Vietnam)" 6 (6): 243-271, 2015

60 Althuwaynee, O. F., "A novel ensemble decision tree-based CHi-squared Automatic Interaction Detection (CHAID) and multivariate logistic regression models in landslide susceptibility mapping" 11 (11): 1063-1078, 2014

61 Pham, B. T., "A novel ensemble classifier of rotation forest and Naive Bayer for landslide susceptibility assessment at the Luc Yen district, Yen Bai Province (Viet Nam) using GIS" 8 (8): 649-671, 2017

62 Althuwaynee, O. F., "A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping" 114 : 21-36, 2014

63 Chen, W., "A novel ensemble approach of bivariate statistical-based logistic model tree classifier for landslide susceptibility assessment" 33 (33): 1398-1420, 2018

64 Li, L., "A modified frequency ratio method for landslide susceptibility assessment" 14 (14): 727-741, 2017

65 Dempster, A. P., "A generalization of Bayesian inference" 30 (30): 205-247, 1968

66 Pradhan, B., "A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS" 51 : 350-365, 2013

67 Shafer, G., "A Mathematical Theory of Evidence" Princeton University Press 1976

68 Chen, W., "A GIS-based comparative study of Dempster-Shafer, logistic regression and artificial neural network models for landslide susceptibility mapping" 32 (32): 367-385, 2017