神木市地处黄土丘陵沟壑区与毛乌素沙漠的过渡带，地质环境脆弱，滑坡灾害频发。基于多源异构空间数据挖掘的滑坡敏感性评价，旨在提升评价精度，为滑坡风险管理和国土规划利用等方面提供科学依据和理论指导。本文将五种分辨率的数字高程模型（DEM）数据划分为栅格单元和斜坡单元，分别建立包含19个影响因子和224个滑坡数据的数据库；再选用频率比（FR）模型进行滑坡与影响因子的空间相关性分析并基于相关属性评价（CAE）模型和模型属性评价方法的平均价值（AM）进行影响因子优选；再建立多组滑坡敏感性模型（ADT、RF-ADT、RS-ADT、FPA、RF-FPA、RS-FPA和RAF）后通过数据统计指标对比进行模型优选；最终建立神木市滑坡敏感性评价优化体系。主要研究内容如下：

（1）多源异构空间数据库建立。将滑坡按7：3比例随机分割成滑坡训练、验证数据；在12.5m、25m、50m、100m和200m五种空间分辨率下各提取19个影响因子，并应用相关属性评价方法（CAE）和模型属性评价方法分析因子都具有正的预测能力；分别基于ArcGIS软件和r.slopeunits模块划分评价单元，结合5组栅格单元和180组斜坡单元作为分区单元与滑坡数据和影响因子共同构成本研究体系的数据库。

（2）滑坡与影响因子的空间相关性分析。利用FR模型分析了滑坡与影响因子间的空间相关性，在每个影响因子中确定了空间相关性较高的范围，判定该范围有利于滑坡的发生。

（3）多源变粒度下基于栅格的区域滑坡敏感性模型优选。通过不同分辨率下七组模型的目标值与输出值误差得出各模型的可靠程度；经过统计指标和受试者工作特征（ROC）曲线分析，12.5m分辨率下的RS-ADT集成模型评价精度最好（ROC曲线下面积（AUROC）=0.907）；通过占比分析和Kappa对比发现，五种分辨率下七组模型的滑坡敏感性分区结果合理且具有一致性。

（4）多源变粒度下基于斜坡单元的区域滑坡敏感性模型优选。从180组斜坡单元中采用综合指标S值经过初选和再优选确定在200m空间分辨率、最小圆方差（c）为0.1、最小斜坡单元面积（a）为290000m²的参数下为最优斜坡单元进行斜坡单元滑坡敏感性建模；采用与栅格建模相同方式得出该最优斜坡单元所用七组模型的可靠程度，通过统计指标和ROC曲线认为最优斜坡单元的各模型性能较稳定，RF-ADT集成模型性能相对较好（AUROC=0.791）；得出的滑坡敏感性分区图从其结果判定各模型的分区结果具有一致性，且其在不同模型下各分区中滑坡点密度比例合理可靠。

（5）基于栅格与斜坡单元的区域滑坡敏感性评价对比。滑坡数据在多源变粒度下基于栅格或斜坡单元的区域滑坡敏感性分区和滑坡点密度都呈现占比趋势相似规律；各模型在不同条件下都表现突出、性能良好，且集成模型优于单一模型；在本研究中，12.5m分辨率下的RS-ADT集成模型在神木市表现最优，其分区图可为政府管理者和工程师进行土地设计和规划提供帮助。

Shenmu City is located in the transition zone between the Loess Plateau and Maowusu Desert, with fragile geological environment and frequent landslide disasters. The landslide susceptibility assessment based on multi-source heterogeneous spatial data mining aims to improve the evaluation accuracy, serve for landslide risk management and landuse planning in Shenmu City, and provide scientific basis and theoretical guidance. In this paper, the digital elevation model (DEM) data with five resolutions are divided into grid units and slope units in the Shenmu City, to establish a landlside database containing 19 conditioning factors and 224 landslides data. Then, the Frequency Ratio (FR) model is used to analyze the spatial correlation between landslides and conditioning factors, and the conditioning factors are optimized based on the AM value of Correlation Attribute Evaluation (CAE) and model attribute evaluation method. After establishing multiple groups landslide susceptibility models (ADT, RF-ADT, RS-ADT, FPA, RF-FPA, RS-FPA and RAF), the models are optimized through the comparison of statistical indicators. Finally, the optimization system of landslide susceptibility evaluation in Shenmu city is established. The main research contents and results are as follows:

(1) Establishment of multi-source heterogeneous spatial database. The landslides are randomly divided into landslide training and validation data according to the ratio of 7:3. Using DEM data of five resolutions and geological and hydrological maps to extract 19 conditioning factors, and applying the CAE and model attribute evaluation method to analyze the factors have positive predictive ability. Based on ArcGIS software and r.slopeunits module, the evaluation units were divided, and 5 grid units and 180 slope units were extracted as zoning units, together with landslide data and connditioning factors, to form the database of this research system.

(2) Spatial correlation analysis between landslide occurrence and conditioning factors. The FR model was used to analyze the spatial correlation distribution relationship between landslide occurrence and conditioning factors, and a range with high spatial correlation was determined in each conditioning factor, which was judged to be unfavorable to the stability of landslides.

(3) Optimization of the regional landslide susceptibility model based on grid units under multi-source variable granularity. The reliability of each model is obtained by the error between the target value and the output value of the seven models at different resolutions. After statistical indicators and Receiver Operating Characteristic (ROC) curve analysis, the RS-ADT integrated model with a resolution of 12.5m has the best evaluation accuracy (the area under the ROC curve (AUROC)=0.907). Through the proportion analysis and Kappa comparison, it is found that the landslide susceptibility zoning of all models at five resolutions are reasonable and consistent.

(4) Optimization of the regional landslide susceptibility model based on slope units under multi-source variable granularity. Using the comprehensive index S value from 180 slope units, through preliminary selection and re-optimization, it is determined that the parameters of the optimal slope unit is 200m resolution, the c value of 0.1, and the a value of 290000m², to the slope unit landslide susceptibility model. The reliability of the seven models used in the optimal slope unit is obtained in the same way as the grid modeling. According to statistical indicators and ROC curves, it is considered that the performance of each model of the optimal slope unit is relatively stable, and the performance of the RF-ADT integrated model is relatively good (AUROC=0.791). The obtained landslide susceptibility maps can be judged from the results that its zoning area proportion and landslide proportion under different models are reasonable and reliable, and the zoning results among the models are consistent.

(5) Comparison of regional landslide susceptibility evaluation based on grid and slope units. The landslide susceptibility zoning and landslide point density based on grid or slope units all show a similar area trend in the landslide data under the multi-source variable granularity. Each model has outstanding performance and good performance under different conditions, and the integrated model is better than the single model. In this study, the RS-ADT integrated model with 12.5m resolution performs best in Shenmu City, and its zoning map can provide help for government managers and engineers in land design and planning.

[1] 史玲, 吕涛.地质灾害风险评价与风险管理[J]. 四川建材, 2017, 43(06): 73-74.

[2] 向喜琼, 黄润秋. 地质灾害风险评价与风险管理[J]. 地质灾害与环境保护, 2000, 11(1): 38-41.

[3] 刘传正. 重大地质灾害防治理论与实践[M]. 北京: 科学出版社, 2009: 57-64.

[4] 文宝萍. 滑坡预测预报研究现状与发展趋势[J]. 地学前缘, 1996, (1): 86-92.

[5] 麻凤海, 陈霞, 季峰,等. 滑坡预测预报研究现状与发展趋势[J]. 徐州工程学院学报(自然科学版), 2018, 33(02): 30-33+63.

[6] 晏同乾. 滑坡学[M]. 武汉: 中国地质大学出版社, 2010: 25-58.

[7] 陈涛. 滑坡引发的次生与衍生灾害危险性评估研究[D]. 宁波: 宁波大学, 2012.

[8] 中华人民共和国国家统计局. 中国统计年鉴-2020[M]. 北京: 中国统计出版社, 2020: 54-58.

[9] Pradhan B, Youssef A M. Manifestation of remote sensing data and GIS on landslide hazard analysis using spatial-based statistical models[J]. Arabian Journal of Geosciences, 2010, 3(3): 319-326.

[10] 殷坤龙, 韩再生, 李志中. 国际滑坡研究的新进展[J]. 水文地质工程地质, 2000, 27(5): 1-4.

[11] 黄润秋. 20世纪以来中国的大型滑坡及其发生机制[J]. 岩石力学与工程学报, 2007, (03): 433-454.

[12] Moosavi V, Niazi Y. Development of hybrid wavelet packet-statistical models (WP-SM) for landslide susceptibility mapping[J]. Landslides, 2016, 13(1): 97-114.

[13] 唐杰. 基于GIS的川藏铁路加查—朗县段滑坡易发性评价[D]. 北京: 中国地质大学(北京), 2018.

[14] 阮沈勇, 黄润秋. 基于GIS的信息量法模型在地质灾害危险性区划中的应用[J]. 成都理工大学学报(自然科学版), 2001, 28(1): 89-92.

[15] 殷坤龙, 朱良峰. 滑坡灾害空间区划及GIS应用研究[J]. 地学前缘, 2001, 8(2): 279-284.

[16] 丛威青, 潘懋, 李铁锋,等. 基于GIS的滑坡,泥石流灾害危险性区划关键问题研究[J]. 地学前缘, 2006, 13(1): 185-185.

[17] 胡德勇, 李京, 陈云浩,等. GIS支持下滑坡灾害空间预测方法研究[J]. 遥感学报, 2007, 11(6): 852-859.

[18] 娄丹丹, 徐刚. GIS在地质灾害风险评价中的应用研究进展[J]. 四川地质学报, 2008, 28(4): 335-338.

[19] 王惠中, 彭安群. 数据挖掘研究现状及发展趋势[J]. 工矿自动化, 2011, (02): 33-36.

[20] 李德仁, 李德毅. 论空间数据挖掘和知识发现的理论与方法[J]. 武汉大学学报: 信息科学版, 2002, 27(3): 221-233.

[21] Li D, Cheng T. KDG - Knowledge Discovery from GIS: propositions on the use of KDD in an Intelligent GIS[J]. 1994, (June6-10): 1001-1012.

[22] 霍艾迪, 张骏, 卢玉东,等. 地质灾害易发性评价单元划分方法——以陕西省黄陵县为例[J]. 吉林大学学报, 2011, 41(2): 523-528.

[23] Chung C-J F, Fabbri A G. Validation of Spatial Prediction Models for Landslide Hazard Mapping[J]. Natural Hazards, 2003, 30(3): 451-472.

[24] 尚慧, 倪万魁, 程花. 斜坡单元划分在彭阳县地质灾害危险性区划中的应用[J]. 中国水土保持, 2011, 3: 48-50.

[25] Youssef A M, Pourghasemi H R, Pourtaghi Z S, et al. Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia[J]. Landslides, 2016, 13(5): 839-856.

[26] Peng J, Wang S, Wang Q, et al. Distribution and genetic types of loess landslides in China[J]. Journal of Asian Earth Sciences, 2019, 170: 329-350.

[27] 刘吉平, 刘汉青, 曾忠平,等. 基于粗糙集理论滑坡影响因子评价研究——以三峡库区青干河流域为例[J]. 水文地质工程地质, 2010, 37(5): 118-122.

[28] Chen W, Zhao X, Tsangaratos P, et al. Evaluating the usage of tree-based ensemble methods in groundwater spring potential mapping[J]. Journal of Hydrology, 2020, 583: 124602.

[29] Zhao X, Chen W. Optimization of Computational Intelligence Models for Landslide Susceptibility Evaluation[J]. Remote Sensing, 2020, 12(14): 2180.

[30] Chen W, Shirzadi A, Shahabi H, et al. A novel hybrid artificial intelligence approach based on the rotation forest ensemble and naïve Bayes tree classifiers for a landslide susceptibility assessment in Langao County, China[J]. Geomatics, Natural Hazards and Risk, 2017, 8(2): 1955-1977.

[31] 刘辰, 刘修国, 陈启浩,等. 面向对象滑坡信息提取中DEM空间分辨率影响分析[J]. 遥感技术与应用, 2014, 29(04): 631-638.

[32] 辛星. 黄土沟壑区浅层滑坡的制图和危险性评价研究[D]. 兰州: 兰州大学, 2018.

[33] Schlogel R, Marchesini I, Alvioli M, et al. Optimizing landslide susceptibility zonation: Effects of DEM spatial resolution and slope unit delineation on logistic regression models[J]. Geomorphology, 2018, 301: 10–20.

[34] 马思远,许冲. 基于斜坡单元与栅格单元的地震滑坡易发性评价研究: 以2013年岷县地震为例[C]//.2019年中国地球科学联合学术年会论文集（十）——专题25: 地震波衰减与深部成像、专题26: 强地面运动与地震灾害、专题27: 区域地震构造及其地震危险性与地震地质灾害, 2019: 30-33.

[35] 刘壮, 李远耀, 张为,等. 基于改进斜坡单元法的山区城镇建设用地适宜性评价[J]. 安全与环境工程, 2019, v.26;No.126(6): 46-53+59.

[36] Tsai H Y, Tsai C C, Chang W C. Slope unit-based approach for assessing regional seismic landslide displacement for deep and shallow failure[J]. Engineering Geology, 2019, 248: 124-139.

[37] Alvioli M, Guzzetti F, Marchesini I. Parameter-free delineation of slope units and terrain subdivision of Italy[J]. Geomorphology, 2020, 358: 107124.

[38] Ramani S E, Pitchaimani K, Gnanamanickam V R. GIS based landslide susceptibility mapping of Tevankarai Ar sub-watershed, Kodaikkanal, India using binary logistic regression analysis[J]. Journal of Mountain Science, 2011, 8(4): 505-517.

[39] Rawat P K, Sharma A K. Geo-diversity and its hydrological response in relation to landslide susceptibility in the Himalaya: a GIS-based case study[J]. Georisk: Assessment and Management of Risk for Engineered Systems Geohazards, 2012, 6(4): 229-251.

[40] 徐文刚, 邱恩喜. 基于统计数据的滑坡敏感性因子分析[J]. 四川地质学报, 2014, 34(3): 429-432.

[41] 范强,巨能攀,向喜琼,黄健.基于结果验证的信息量法地质灾害易发性评价——以贵州省开阳县为例[J].人民长江,2015,46(15):65-68.

[42] 于宪煜. 基于多源数据和多尺度分析的滑坡易发性评价方法研究[D]. 中国地质大学, 2016.

[43] Pandey V K, Sharma M C. Probabilistic Landslide Susceptibility Mapping along Tipri to Ghuttu highway Corridor, Garhwal Himalaya (India)[J]. Remote Sensing Applications: Society Environmental Earth Sciences, 2017, 8: 1-11.

[44] Zhang T, Han L, Zhang H, et al. GIS-based landslide susceptibility mapping using hybrid integration approaches of fractal dimension with index of entropy and support vector machine[J]. Journal of Mountain Science, 2019, 16(6): 1275-1288.

[45] Hong H, Liu J, Zhu A X. Landslide susceptibility evaluating using artificial intelligence method in the Youfang district (China)[J]. Environmental Earth Sciences, 2019, 78(15): 488.

[46] Zhao X, Chen W. GIS-Based Evaluation of Landslide Susceptibility Models Using Certainty Factors and Functional Trees-Based Ensemble Techniques[J]. Applied Sciences, 2019, 10(1): 16.

[47] Razavi-Termeh S V, Shirani K, Pasandi M. Mapping of landslide susceptibility using the combination of neuro-fuzzy inference system (ANFIS), ant colony (ANFIS-ACOR), and differential evolution (ANFIS-DE) models[J]. Bulletin of Engineering Geology and the Environment, 2021, 2045–2067.

[48] Zêzere J L, Pereira S, Melo R, et al. Mapping landslide susceptibility using data-driven methods[J]. Science of the Total Environment, 2017, 589: 250-267.

[49] Pham B T, Prakash I. A Novel Hybrid Intelligent Approach of Random Subspace Ensemble and Reduced Error Pruning Trees for Landslide Susceptibility Modeling: A Case Study at Mu Cang Chai District, Yen Bai Province, Viet Nam[C]. //Dieu Tien Bui, Anh Ngoc Do, Hoang-Bac Bui and Nhat-Duc Hoang. Springer International Publishing, 2018:255-269.

[50] Mathew J J, V.K.; Rawat, G.S. Application of binary logistic regression analysis and its validation for landslide susceptibility mapping in part of garhwal himalaya, India[J]. International Journal of Remote Sensing, 2007, 28: 2257-2275.

[51] Mathew J, Jha V K, Rawat G S. Landslide susceptibility zonation mapping and its validation in part of Garhwal Lesser Himalaya, India, using binary logistic regression analysis and receiver operating characteristic curve method[J]. Landslides, 2009, 6(1): 17-26.

[52] Pham B T, Bui D T, Pourghasemi H R, et al. Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods[J]. Theor. Appl. Climatol., 2015, 122(3): 1-19.

[53] Sadighi M, Motamedvaziri B, Ahmadi H, et al. Assessing landslide susceptibility using machine learning models: a comparison between ANN, ANFIS, and ANFIS-ICA[J]. Environmental Earth Sciences, 2020, 79(24): 536.

[54] Liu H, Li X, Meng T, et al. Susceptibility mapping of damming landslide based on slope unit using frequency ratio model[J]. Arabian Journal of Geosciences, 2020, 13(16): 790.

[55] Lee J-H, Sameen M I, Pradhan B, et al. Modeling landslide susceptibility in data-scarce environments using optimized data mining and statistical methods[J]. Geomorphology, 2018, 303: 284-298.

[56] Zhou C, Yin K, Cao Y, et al. Landslide susceptibility modeling applying machine learning methods: A case study from Longju in the Three Gorges Reservoir area, China[J]. Computers and Geotechnics, 2018, 112: 23-37.

[57] Wang H J, Xiao T, Li X Y, et al. A novel physically-based model for updating landslide susceptibility[J]. Engineering Geology, 2019, 251: 71-80.

[58] Thanh L N, De Smedt F. Slope stability analysis using a physically based model: a case study from A Luoi district in Thua Thien-Hue Province, Vietnam[J]. Landslides, 2014, 11(5): 897-907.

[59] Pourghasemi H R, Rahmati O. Prediction of the landslide susceptibility: Which algorithm, which precision?[J]. Catena, 2017, 162: 177-192.

[60] Jia N, Mitani Y, Xie M, et al. Shallow landslide hazard assessment using a three-dimensional deterministic model in a mountainous area[J]. Computers and Geotechnics, 2012, 45: 1-10.

[61] Pourghasemi H R, Kerle N. Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran[J]. Environmental Earth Sciences, 2016, 75(3): 185.

[62] Hong H, Chen W, Xu C, et al. Rainfall-induced landslide susceptibility assessment at the Chongren area (China) using frequency ratio, certainty factor, and index of entropy[J]. Geocarto International, 2017, 32(2): 16.

[63] Chen W, Li W, Chai H, et al. GIS-based landslide susceptibility mapping using analytical hierarchy process (AHP) and certainty factor (CF) models for the Baozhong region of Baoji City, China[J]. Environmental Earth Sciences, 2016, 75(1): 63.

[64] Milaghardan A H, Delavar M, Chehreghan A. Uncertainty in landslide occurrence prediction using Dempster–Shafer theory[J]. Modeling Earth Systems & Environment, 2016, 2(4): 188.

[65] Mezaal M, Pradhan B, Rizeei H. Improving Landslide Detection from Airborne Laser Scanning Data Using Optimized Dempster–Shafer[J]. Remote Sensing, 2018, 10(7): 1029.

[66] Feizizadeh B, Blaschke T, Nazmfar H. GIS-based ordered weighted averaging and Dempster–Shafer methods for landslide susceptibility mapping in the Urmia Lake Basin, Iran[J]. International Journal of Digital Earth, 2014, 7(8): 688-708.

[67] Jaafari A, Najafi A, Pourghasemi H R, et al. GIS-based frequency ratio and index of entropy models for landslide susceptibility assessment in the Caspian forest, northern Iran[J]. International Journal of Environmental Science & Technology, 2014, 11(4): 909-926.

[68] Devkota K C, Regmi A D, Pourghasemi H R, et al. Landslide susceptibility mapping using certainty factor, index of entropy and logistic regression models in GIS and their comparison at Mugling–Narayanghat road section in Nepal Himalaya[J]. Natural Hazards, 2013, 65(1): 135-165.

[69] Gayen A, Saha S. Application of weights-of-evidence (WoE) and evidential belief function (EBF) models for the delineation of soil erosion vulnerable zones: a study on Pathro river basin, Jharkhand, India[J]. Modeling Earth Systems & Environment, 2017, 3(3): 1123-1139.

[70] Zhang Z, Fan Y, Han C, et al. GIS-based landslide susceptibility analysis using frequency ratio and evidential belief function models[J]. Environmental Earth Sciences, 2016, 75(11): 948.

[71] Ma S, Qiu H, Hu S, et al. Quantitative assessment of landslide susceptibility on the Loess Plateau in China[J]. Physical Geography, 2019, 41(6): 489-516.

[72] Rahman G, Rahman A-U, Bacha A, et al. Assessment of Landslide Susceptibility using Weight of Evidence and Frequency Ratio Model in Shahpur Valley, Eastern Hindu Kush[M]. 2020.

[73] Bui D T, Bui Q T, Nguyen Q P, et al. A hybrid artificial intelligence approach using GIS-based neural-fuzzy inference system and particle swarm optimization for forest fire susceptibility modeling at a tropical area[J]. Agricultural & Forest Meteorology, 2017, 233(Complete): 32-44.

[74] Chen W, Hong H, Panahi M, et al. Spatial Prediction of Landslide Susceptibility Using GIS-Based Data Mining Techniques of ANFIS with Whale Optimization Algorithm (WOA) and Grey Wolf Optimizer (GWO)[J]. Applied Sciences, 2019, 9: 3755.

[75] Elith J, Leathwick J R, Hastie T. A working guide to boosted regression trees[J]. Journal of Animal Ecology, 2008, 77(4): 802-813.

[76] Pham B T, Bui D T, Dholakia M B, et al. A novel ensemble classifier of rotation forest and Naïve Bayer for landslide susceptibility assessment at the Luc Yen district, Yen Bai Province (Viet Nam) using GIS[J]. Geomatics, Natural Hazards and Risk, 2016: 1-23.

[77] Goetz J N, Brenning A, Petschko H, et al. Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling[J]. Computers and Geotechnics, 2015, 81: 1-11.

[78] Lin G-F, Chang M-J, Huang Y-C, et al. Assessment of susceptibility to rainfall-induced landslides using improved self-organizing linear output map, support vector machine, and logistic regression[J]. Computers and Geotechnics, 2017, 224: 62-74.

[79] 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[J]. Computers and Geotechnics, 2013, 51(2): 350-365.

[80] Abbaszadeh Shahri A, Spross J, Johansson F, et al. Landslide susceptibility hazard map in southwest Sweden using artificial neural network[J]. Catena, 2019, 183: 104225.

[81] Can A, Dagdelenler G, Ercanoglu M, et al. Landslide susceptibility mapping at Ovacık-Karabük (Turkey) using different artificial neural network models: comparison of training algorithms[J]. Bulletin of Engineering Geology and the Environment, 2017, (1): 1-14.

[82] Hong H, Pradhan B, Xu C, et al. Spatial prediction of landslide hazard at the Yihuang area (China) using two-class kernel logistic regression, alternating decision tree and support vector machines[J]. Catena, 2015, 133: 266-281.

[83] Chen W, Peng J, Hong H, et al. Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China[J]. Science of The Total Environment, 2018, 626: 230.

[84] Zhang K, Wu X, Niu R, et al. The assessment of landslide susceptibility mapping using random forest and decision tree methods in the Three Gorges Reservoir area, China[J]. Environmental Earth Sciences, 2017, 76(11): 405.

[85] Provost F, Hibert C, Malet J. Automatic classification of endogenous landslide seismicity using the Random Forest supervised classifier[J]. Geophysical Research Letters, 2017, 44(1): 113-120.

[86] Ghorbanzadeh O, Rostamzadeh H, Blaschke T, et al. A new GIS-based data mining technique using an adaptive neuro-fuzzy inference system (ANFIS) and k-fold cross-validation approach for land subsidence susceptibility mapping[J]. Natural Hazards, 2018, 94: 497–517.

[87] Chen W, Shahabi H, Shirzadi A, et al. Novel hybrid artificial intelligence approach of bivariate statistical-methods-based kernel logistic regression classifier for landslide susceptibility modeling[J]. Bulletin of Engineering Geology and the Environment, 2019, 78(6): 4397-4419.

[88] Aghdam I N, Pradhan B. Landslide susceptibility mapping using an ensemble statistical index (Wi) and adaptive neuro-fuzzy inference system (ANFIS) model at Alborz Mountains (Iran)[J]. Environmental Earth Sciences, 2016, 75(7): 553.

[89] Nguyen V, Pham B, Vu T, et al. Hybrid Machine Learning Approaches for Landslide Susceptibility Modeling[J]. Forests, 2019, 10: 1-27.

[90] Paryani S, Neshat A, Javadi S, et al. Comparative performance of new hybrid ANFIS models in landslide susceptibility mapping[J]. Natural Hazards, 2020, 103(2): 1961-1988.

[91] Panahi M, Gayen A, Pourghasemi H R, et al. Spatial prediction of landslide susceptibility using hybrid support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS) with various metaheuristic algorithms[J]. Science of The Total Environment, 2020, 741.

[92] Althuwaynee O F, Pradhan B, Lee S. A novel integrated model for assessing landslide susceptibility mapping using CHAID and AHP pair-wise comparison[J]. International Journal of Remote Sensing, 2016, 37(5): 1190-1209.

[93] Chen W, Pourghasemi H R, Kornejady A, et al. Landslide spatial modeling: Introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques[J]. Geofisica Internacional, 2017, 305: 314-327.

[94] Arabameri A, Pradhan B, Rezaei K, et al. GIS-based landslide susceptibility mapping using numerical risk factor bivariate model and its ensemble with linear multivariate regression and boosted regression tree algorithms[J]. Journal of Mountain Science, 2019, 16(3): 595-618.

[95] Pham B T, Jaafari A, Prakash I, et al. A novel hybrid intelligent model of support vector machines and the MultiBoost ensemble for landslide susceptibility modeling[J]. Bulletin of Engineering Geology and the Environment, 2019, 78(4): 2865-2886.

[96] Abedini M, Ghasemian B, Shirzadi A, et al. A novel hybrid approach of Bayesian Logistic Regression and its ensembles for landslide susceptibility assessment[J]. Geocarto International, 2019, 34(13): 1427-1457.

[97] Wu Y, Ke Y, Chen Z, et al. Application of alternating decision tree with AdaBoost and bagging ensembles for landslide susceptibility mapping[J]. Catena, 2020, 187: 104396.

[98] Hong H, Liu J, Zhu A X. Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble[J]. Science of The Total Environment, 2020, 718: 137231.

[99] Kalantar B, Ueda N, Saeidi V, et al. Landslide Susceptibility Mapping: Machine and Ensemble Learning Based on Remote Sensing Big Data[J]. Remote Sensing, 2020, 12: 1737.

[100]陕西省地质环境监测总站. 陕西省神木县地质灾害详细调查报告[R].西安:陕西省地质环境监测总站, 2014.

[101] Alvioli M, Marchesini I, Paola R, et al. Automatic delineation of geomorphological slope units with r.slopeunits v1.0 and their optimization for landslide susceptibility modeling[J]. Geoscientific Model Development, 2016, 9: 3975.

[102] Freund Y, Mason L. The alternating decision tree learning algorithm[C]. 1999: 124-133.

[103] Kuang Y, Po-Leen Ooi M. Complex feature alternating decision tree[M]. Vol. 9, 2010, pp. 335-353.

[104] Sok H K, Ooi M P-L, Kuang Y C. Sparse alternating decision tree[J]. Pattern Recognition Letters, 2015, 60-61: 57-64.

[105] Chen W, Pourghasemi H R, Kornejady A, et al., 'GIS-Based Landslide Susceptibility Evaluation Using Certainty Factor and Index of Entropy Ensembled with Alternating Decision Tree Models', in Natural Hazards GIS-Based Spatial Modeling Using Data Mining Techniques, ed. by Hamid Reza Pourghasemi and Mauro Rossi (Cham: Springer International Publishing, 2019), pp. 225-251.

[106] Pham B T, Tien Bui D, Dholakia M B, et al. A Comparative Study of Least Square Support Vector Machines and Multiclass Alternating Decision Trees for Spatial Prediction of Rainfall-Induced Landslides in a Tropical Cyclones Area[J]. Geotechnical and Geological Engineering, 2016, 34(6): 1807-1824.

[107] Pfahringer B, Holmes G, Kirkby R. Optimizing the Induction of Alternating Decision Trees[C]. //David Cheung, Graham J. Williams and Qing Li. Springer Berlin Heidelberg, 2001: 477-487.

[108] Adnan M N, Islam M Z. Forest PA: Constructing a decision forest by penalizing attributes used in previous trees[J]. Expert Systems with Applications, 2017: 389-403.

[109] Alsariera Y A, Adeyemo V, Balogun A. Phishing Website Detection: Forest by Penalizing Attributes Algorithm and Its Enhanced Variations[J]. Arabian Journal for Science and Engineering, 2020, 45: 10459–10470.

[110] Pardo C, Diez-Pastor J F, García-Osorio C, et al. Rotation Forests for regression[J]. Applied Mathematics and Computation, 2013, 219(19): 9914-9924.

[111] Lasota T, Telec Z, Trawiński B, et al. Investigation of Rotation Forest Ensemble Method Using Genetic Fuzzy Systems for a Regression Problem[C]. //Jeng-Shyang Pan, Shyi-Ming Chen and Ngoc Thanh Nguyen. Springer Berlin Heidelberg, 2012: 393-402.

[112] Zhang C-X, Zhang J-S. RotBoost: A technique for combining Rotation Forest and AdaBoost[J]. Pattern Recognition Letters, 2008, 29(10): 1524-1536.

[113] Du P, Samat A, Waske B, et al. Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 105: 38-53.

[114] Ho T K. The random subspace method for constructing decision forests[J]. IEEE transactions on pattern analysis and machine intelligence, 1998, 20(8): 832-844.

[115] Tao D, Tang X, Li X, et al. Asymmetric Bagging and Random Subspace for Support Vector Machines-Based Relevance Feedback in Image Retrieval[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2006, 28(7): 1088-1099.

[116] Skurichina M, Duin R P W. Bagging, Boosting and the Random Subspace Method for Linear Classifiers[J]. Pattern Analysis & Applications, 2002, 5(2): 121-135.

[117] Breiman L. Bagging predictors[J]. Machine learning, 1996, 24(2): 123-140.

[118] Breiman L. Random forests[J]. Machine learning, 2001, 45(1): 5-32.

[119] Deng C, Guo M Z. A new co-training-style random forest for computer aided diagnosis[J]. Journal of Intelligent Information Systems, 2011, 36(3): 253-281.

[120] Dang V-H, Dieu T B, Tran X-L, et al. Enhancing the accuracy of rainfall-induced landslide prediction along mountain roads with a GIS-based random forest classifier[J]. Bulletin of Engineering Geology and the Environment, 2018, 78: 2835–2849.

[121] Chen W, Li Y, Xue W, et al. Modeling flood susceptibility using data-driven approaches of na ve bayes tree, alternating decision tree, and random forest methods[J]. Science of The Total Environment, 2020, 701: 134979.

[122] Oh H J, Kim Y S, Choi J K, et al. GIS mapping of regional probabilistic groundwater potential in the area of Pohang City, Korea[J]. Journal of Hydrology, 2011, 399(3-4): 158-172.

[123] Razavizadeh S, Solaimani K, Massironi M, et al. Mapping landslide susceptibility with frequency ratio, statistical index, and weights of evidence models: a case study in northern Iran[J]. 2017, 76(14): 499.

[124] Yilmaz I K J. GIS based susceptibility mapping of karst depression in gypsum: A case study from Sivas basin (Turkey)[J]. Engineering Geology, 2007, 90(1-2): 89-103.

[125] Lee S, Talib J A. Probabilistic landslide susceptibility and factor effect analysis[J]. Environmental Geology, 2005, 47(7): 982-990.

[126] Pradhan B, Lee S. Landslide susceptibility assessment and factor effect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling[J]. Environmental Modelling & Software, 2010, 25(6): 747-759.

[127] Rasyid A R, Bhandary N P, Yatabe R. Performance of frequency ratio and logistic regression model in creating GIS based landslides susceptibility map at Lompobattang Mountain, Indonesia[J]. Geoenvironmental Disasters, 2016, 3(1): 19.

[128] Lee S, Pradhan B. Landslide hazard mapping at Selangor, Malaysia using frequency ratio and logistic regression models[J]. Landslides, 2007, 4(1): 33-41.

[129] Mind’je R, Li L, Nsengiyumva J B, et al. Landslide susceptibility and influencing factors analysis in Rwanda[J]. Environment, Development and Sustainability, 2019.

[130] Witten I H, Frank E. Data mining: practical machine learning tools and techniques with Java implementations[J]. Sigmod Record, 2002, 31(1): 76–77.

[131] Tien Bui D, Ho T-C, Pradhan B, et al. GIS-based modeling of rainfall-induced landslides using data mining-based functional trees classifier with AdaBoost, Bagging, and MultiBoost ensemble frameworks[J]. Environmental Earth Sciences, 2016, 75(14): 1101.

[132] Chen W, Shahabi H, Zhang S, et al. Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression[J]. Applied Sciences, 2018, 8(12): 2540.

[133] Bui D T, Pradhan B, Lofman O, et al. Spatial prediction of landslide hazards in Hoa Binh province (Vietnam): a comparative assessment of the efficacy of evidential belief functions and fuzzy logic models[J]. Catena, 2012, 96: 28-40.

[134] Bennett N D, Croke B F, Guariso G, et al. Characterising performance of environmental models[J]. Environmental Modelling & Software, 2013, 40: 1-20.

[135] Althuwaynee O F, Pradhan B, Park H-J, et al. A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping[J]. Catena, 2014, 114: 21-36.

[136] Shirzadi A, Chapi K, Shahabi H, et al. Rock fall susceptibility assessment along a mountainous road: an evaluation of bivariate statistic, analytical hierarchy process and frequency ratio[J]. Environmental Earth Sciences, 2017, 76(4): 152.

[137] Shahabi H, Khezri S, Ahmad B B, et al. Landslide susceptibility mapping at central Zab basin, Iran: A comparison between analytical hierarchy process, frequency ratio and logistic regression models[J]. Catena, 2014, 115: 55-70.

[138] Chapi K, Singh V P, Shirzadi A, et al. A novel hybrid artificial intelligence approach for flood susceptibility assessment[J]. Environmental modelling & software, 2017, 95: 229-245.

[139] Youssef A M, Pradhan B, Jebur M N, et al. Landslide susceptibility mapping using ensemble bivariate and multivariate statistical models in Fayfa area, Saudi Arabia[J]. Environmental Earth Sciences, 2015, 73(7): 3745-3761.

[140] Ciurleo M C, L.; Calvello, M. A comparison of statistical and deterministic methods for shallow landslide susceptibility zoning in clayey soils[J]. Engineering Geology, 2017, 223: 71-81.

[141] Arabameri A, Rezaei K, Cerd A, et al. A comparison of statistical methods and multi-criteria decision making to map flood hazard susceptibility in Northern Iran[J]. Science of the Total Environment, 2019, 660: 443-458.

[142] Khosravi K, Shahabi H, Pham B T, et al. A comparative assessment of flood susceptibility modeling using Multi-Criteria Decision-Making Analysis and Machine Learning Methods[J]. 2019, 573: 311-323.

[143] Ko F W Y, Lo F L C. From landslide susceptibility to landslide frequency: A territory-wide study in Hong Kong[J]. Engineering Geology, 2018, 242: 12-22.

[144] Tang W, Jun H U, Zhang H, et al. Kappa coefficient: a popular measure of rater agreement[J]. General Psychiatry, 2015, 27(1).

[145] Bai S-B, Wang J, Lü G-N, et al. GIS-based logistic regression for landslide susceptibility mapping of the Zhongxian segment in the Three Gorges area, China[J]. Geomorphology, 2010, 115(1): 23-31.

[146] Pradhan B, Lee S. Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models[J]. Environmental Earth Sciences, 2010, 60(5): 1037-1054.