滑坡灾害严重影响社会发展和稳定，在所有地质灾害中占据主导作用，所造成的危害不容忽视。目前国内滑坡防治形势依然严峻，防灾减灾措施仍以预防为主，因此对其进行易发性评价研究是防患于未然的首要选择。

本文以陕西省洛南县为研究区，以地质灾害详细调查资料为基础资料，选取滑坡为研究对象，在全面分析研究区滑坡发育特征及分布规律的基础上，以ArcGIS、MATLAB、SPSS等软件为研究工具，开展了不同评价单元条件下（30m栅格单元、60m栅格单元和斜坡单元）基于经典机器学习（NBC模型、LDA模型、SVM模型和KNN模型）与集成学习（Bagging模型、AdaBoost模型和RF模型）的研究区滑坡易发性评价方法对比研究。针对选择的三个评价单元，开展了模型适用性及评价精度分析工作，对政府制订滑坡灾害防治规划以及滑坡易发性区划等宏观决策具有指导意义。取得主要成果如下：

（1）在分析研究区滑坡发育特征及分布规律的基础上，选取2处典型的堆积层滑坡，重点剖析了其基本特征及影响因素。结果表明：研究区滑坡发育类型以堆积层滑坡为主；规模以中、小型为主；受降雨和人类工程活动作用明显；并在地域和时间上分别表现出了显著的规律。

（2）通过主成分分析、相关性分析以及多重共线性分析对初步选取的评价因子进行了分析，依据分析结果剔除了权重较小或相关性较强的评价因子，保留剩余评价因子统计分析了滑坡与各评价因子之间的关系。结果表明：保留的剩余评价因子对滑坡的控制作用明显，并基于此建立了研究区滑坡易发性评价因子指标体系。

（3）分别建立了基于三种不同评价单元的上述7种滑坡易发性评价模型，生成了相应的滑坡易发性评价分区图，并通过数学统计法对评价结果进行了合理性检验。结果表明：三种评价单元在上述7种模型均表现出了较高的预测准确率，并均符合合理性检验的相关标准，说明本次研究所选的评价单元和评价模型均起到了较好的效果且分区合理。

（4）分别采用ROC曲线和Kappa系数对三种不同评价单元在上述所选7种模型的预测精度和一致性检验程度进行了对比分析。综合对比得到，本次研究最优的评价单元与评价模型组合为基于30m栅格单元的RF模型，该组合的滑坡易发性分区效果最显著，且预测精度与一致性检验程度均达到了非常高的水平（AUC=0.916，k=0.923），可作为本次研究预测准确率最高且分区最合理的评价单元与评价模型组合。

Landslide disaster seriously affects social development and stability, plays a leading role in all geological disasters, and the harm caused by it cannot be ignored. At present, the situation of landslide prevention and control in China is still grim, and the measures of disaster prevention and mitigation still focus on prevention. Therefore, it is the first choice to evaluate the susceptibility of landslide prevention.

In this study, Luonan County of Shaanxi Province is taken as the research area. Based on the detailed investigation data of geological disasters, landslides are selected as the research object. On the basis of comprehensive analysis of the developmental characteristics and rules of landslides in the research area, ArcGIS, MATLAB, SPSS and other software are used as the research tools. Carried out a comparative study on the landslide Susceptibility evaluation method in the study area under the condition of different evaluation units (30 m grid unit, 60 m grid unit and the slope unit) based on the classical machine learning model (NBC, LDA, SVM and KNN) and integrated learning (Bagging, AdaBoost and RF) model. For the three selected evaluation units, the applicability and evaluation accuracy of the model were analyzed, which is of guiding significance for the government to formulate the planning of landslide disaster prevention and control and the zoning of landslide susceptibility. The main achievements are as follows:

(1) Based on the analysis of the development characteristics and distribution of landslides in the study area, two typical accumulation layer landslides were selected, and their basic characteristics and influencing factors were analyzed emphatically. The results show that: the landslide development type in the study area is mainly accumulation landslide; the scale is mainly medium and small; it is affected by rainfall and human engineering activities obviously; and it shows significant rules in region and time.

(2) Through the principal component analysis, correlation analysis and the multicollinearity analysis of preliminary selection of evaluation factors, on the basis of the analysis results to cut out the small weight, or the strong correlation factors and keep the rest of the evaluation factors for its using statistical analysis of the relationship between the landslide and each evaluation factor, the analysis indicates that retain the residual evaluation factor control of the landslide, landslide liability in the study area was established evaluation index system of factors.

(3) The evaluation models of the above seven kinds of landslide susceptibility based on three different evaluation units were established respectively, and the partition maps of the landslide susceptibility degree of each method were generated. The rationality of the evaluation results was tested by mathematical statistical method. The results show that the three evaluation units show high prediction accuracy in the above seven models, and all meet the relevant standards of rationality test, which indicates that the evaluation units and evaluation models selected in this study have played a good effect and the partition is reasonable.

(4) The ROC curve and Kappa coefficient were used to compare and test the prediction accuracy and consistency testing degree of the three different evaluation units in the 7 models selected above. The comprehensive comparison shows that the optimal combination of evaluation unit and evaluation model in this study is the RF model based on 30m grid element. This combination has the most significant effect on the partition of landslide susceptibility, and the prediction accuracy and consistency test degree both reach a very high level (AUC=0.916, k=0.923), which can be used as the combination of evaluation unit and evaluation model with the highest prediction accuracy and the most reasonable partition in this study.

[1]王哲, 易发成. 我国地质灾害区划及其研究现状[J]. 中国矿业, 2006(10): 47-50.

[2]中华人民共和国统计局.中国统计年鉴[M]. 北京中国统计出版社, 2019.

[3]中华人民共和国国土资源部.全国地质灾害通报[R]. 北京:中国地质环境监测院, 2020.

[4]A.Nemčok, J.Pašek, J.Rybář. Classification of landslides and other mass movements[J]. Rock Mechanics and Rock Engineering, 1972, 4(2): 71-78.

[5]晏同珍. 滑坡学[M]. 中国地质大学出版社, 2000.

[6]高华喜. 滑坡灾害风险区划与预测研究综述[J]. 灾害学, 2010, 25(2):124-128.

[7]周静静, 张晓敏, 赵法锁, 等. 陕南秦巴山区地质灾害危险性评价研究[J]. 地质力学学报, 2019, 25(04): 544-553.

[8]马寅生, 张业成, 张春山, 等. 地质灾害风险评价的理论与方法[J]. 地质力学学报, 2004, 10(01): 7-18.

[9]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(01): 38-41.

[10]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): 185-190．

[11]Zhao Shuai, Zhao Zhou, Garg Akhil. A Comparative Study of Landslide Susceptibility Mapping Using SVM and PSO-SVM Models Based on Grid and Slope Units[J]. Mathematical Problems in Engineering, 2021, 2021.

[12]薛强, 张茂省, 李林. 基于斜坡单元与信息量法结合的宝塔区黄土滑坡易发性评价[J]. 地质通报, 2015, 34(11): 2108-2115.

[13]陈飞, 蔡超, 李小双, 等. 基于信息量与神经网络模型的滑坡易发性评价[J]. 岩石力学与工程学报, 2020, 39(S1): 2859-2870.

[14]Hanhu Liu, Xinggong Li, Tian Meng, et al. Susceptibility mapping of damming landslide based on slope unit using frequency ratio model[J]. Arabian Journal of Geosciences, 2020,13(16): 405-111.

[15]孟田, 许晓露, 刘汉湖. 基于斜坡单元优化的高海拔地区滑坡危险性评价——以金沙江白格滑坡为例[J]. 河南理工大学学报(自然科学版), 2021, 40(01): 65-73.

[16]陈伟. 山区村镇滑坡灾害风险评估研究[D]. 武汉大学, 2019.

[17]唐川, 马国超. 基于地貌单元的小区域地质灾害易发性分区方法研究[J]. 地理科学, 2015, 35(01): 91-98.

[18]黄发明, 陈佳武, 唐志鹏, 等.不同空间分辨率和训练测试集比例下的滑坡易发性预测不确定性[J/OL]. 岩石力学与工程学报: 1-14[2021-03-17].https://doi.org/10.13722/j.cnki.jrme.2020.1119.

[19]Yu Chenglong, Chen Jianping. Application of a GIS-Based Slope Unit Method for Landslide Susceptibility Mapping in Helong City: Comparative Assessment of ICM, AHP, and RF Model[J]. Symmetry, 2020, 12(11): 1848-1848.

[20]Li Langping, Lan Hengxing. Integration of Spatial Probability and Size in Slope-Unit-Based Landslide Susceptibility Assessment: A Case Study.[J]. International journal of environmental research and public health, 2020, 17(21): 8055.

[21]Xiaohui Sun, Jianping Chen, Xudong Han, et al. Application of a GIS-based slope unit method for landslide susceptibility mapping along the rapidly uplifting section of the upper Jinsha River, South-Western China[J]. Bulletin of Engineering Geology and the Environment: The official journal of the IAEG, 2020, 79(11) : 533-549.

[22]Beaty C B. Landslides and slope exposure[J]. The Journal of Geology, 1956, 64(01): 70-74.

[23]张向营, 张春山, 孟华君, 等. 基于GIS和信息量模型的京张高铁滑坡易发性评价[J]. 地质力学学报, 2018, 24(01): 96-105.

[24]Aditian A, Kubota T, Shinohara Y. Comparison of GIS-based landslide susceptibility models using frequency ratio, logistic regression, and artificial neural network in a tertiary[J]. Geomorphology, 2018, 318:101-111.

[25]任敬, 范宣梅, 赵程, 等. 贵州省都匀市滑坡易发性评价研究[J]. 水文地质工程地质, 2018, 45(05): 165-172.

[26]Ioanna Ilia, Paraskevas Tsangaratos. Applying weight of evidence method and sensitivity analysis to produce a landslide susceptibility map[J]. Landslide, 2016, 13(02): 379- 397.

[27]胡燕, 李德营, 孟颂颂, 等. 基于证据权法的巴东县城滑坡灾害易发性评价[J]. 地质科技通报, 2020, 39(03): 187-194.

[28]Demir G, Aytekin M, Akgun A, et al. A comparison of landslide susceptibility mapping of the eastern part of the North Anatolian Fault Zone (Turkey) by likelihood-frequency ratio;and analytic hierarchy process methods[J]. Natural Hazards, 2013, 65(03): 1481-1506.

[29]许冲, 戴福初, 姚鑫, 等. GIS支持下基于层次分析法的汶川地震区滑坡易发性评价[J]. 岩石力学与工程学报, 2009, 28(S2): 3978-3985.

[30]V. Vakhshoori, M. Zare. Landslide susceptibility mapping by comparing weight of evidence, fuzzy logic, and frequency ratio methods[J]. Geomatics, 2016, 7(05): 1731-1752.

[31]郭子正, 殷坤龙, 黄发明, 等. 基于滑坡分类和加权频率比模型的滑坡易发性评价[J]. 岩石力学与工程学报, 2019, 38(02): 287-300.

[32]Shirani K, Pasandi M, Arabameri A. Landslide susceptibility assessment by Dempster–Shafer and Index of Entropy models, Sarkhoun basin, Southwestern Iran[J]. Natural Hazards, 2018, 93(03): 1379-1418.

[33]Yoo, Youngwoo, Baek, Taekyung, Kim, Jinsoo, et al. A Comparative Study of the Frequency Ratio and Evidential Belief Function Models for Landslide Susceptibility Mapping[J]. Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 2016, 34(6): 597-607.

[34]Nguyen Thi To Ngan, Liu Cheng-Chien. A New Approach Using AHP to Generate Landslide Susceptibility Maps in the Chen-Yu-Lan Watershed, Taiwan.[J]. Sensors (Basel, Switzerland), 2019, 19(3): 505.

[35]Sujoy Kumar Jana, Tingneyuc Sekac, Dilip Kumar Pal. Geo-spatial approach with frequency ratio method in landslide susceptibility mapping in the Busu River catchment, Papua New Guinea[J]. Spatial Information Research, 2019, 27(1) : 49-62.

[36]袁湘秦, 赵法锁, 陈新建, 等. 陕西省绥德县地质灾害易发性区划[J]. 灾害学, 2017, 32(01):117-120+125.

[37]胡涛, 樊鑫, 王硕, 等. 基于逻辑回归模型和3S技术的思南县滑坡易发性评价[J]. 地质科技通报, 2020, 39(02): 113-121.

[38]Pece V. Gorsevski, M. Kenneth Brown, Kurt Panter, et al. Landslide detection and susceptibility mapping using LiDAR and an artificial neural network approach: a case study in the Cuyahoga Valley National Park, Ohio[J]. Landslides, 2016, 13(03): 467-484.

[39]向喜琼, 黄润秋. 基于GIS的人工神经网络模型在地质灾害危险性区划中的应用[J]. 中国地质灾害与防治学报, 2000, 11(03):26-30.

[40]Behnia P, Blais-Stevens A. Landslide susceptibility modelling using the quantitative random forest method along the northern portion of the Yukon Alaska Highway Corridor, Canada[J]. Natural Hazards, 2018, 90(01): 1407-1426.

[41]刘睿, 施婌娴, 孙德亮, 等. 基于GIS与随机森林的巫山县滑坡易发性区划[J]. 重庆师范大学学报(自然科学版), 2020, 37(03): 86-96.

[42]Kavzoglu T, Sahin E K, Colkesen I. Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression[J]. Landslides, 2014, 11(03): 425-439.

[43]王卫东, 刘攀, 龚陆. 基于支持向量机模型的四川省滑坡灾害易发性区划[J]. 铁道科学与工程学报, 2019, 16(05): 1194-1200.

[44]Pham B T, Bui D T, Pourghasemi H R, et al. Landslide susceptibility assessment 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]. Theoretical & Applied Climatology. 2017, 128(01-02): 255-273.

[45]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 & Risk. 2017, 8(02): 1955-1977.

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

[47]胡旭东. 基于集成学习的地质灾害易发性评价研究[D]. 中国地质大学, 2019.

[48]郭有金. 基于集成学习算法的西安市滑坡灾害易发性评价[D]. 西安科技大学, 2020.

[49]Yingxu Song, Ruiqing Niu, Shiluo Xu, et al. Landslide Susceptibility Mapping Based on Weighted Gradient Boosting Decision Tree in Wanzhou Section of the Three Gorges Reservoir Area (China)[J]. ISPRS International Journal of Geo-Information, 2018, 8(1).

[50]Chen Wei, Chen Yunzhi, Tsangaratos Paraskevas, et al. Combining Evolutionary Algorithms and Machine Learning Models in Landslide Susceptibility Assessments[J]. Remote Sensing, 2020, 12(23): 3854-3854.

[51]Badal Pokharel, Omar F. Althuwaynee, Ali Aydda, et al. Spatial clustering and modelling for landslide susceptibility mapping in the north of the Kathmandu Valley, Nepal[J]. Landslides, 2020: 1-17.

[52]Wei Chen, Hamid Reza Pourghasemi, Mahdi Panahi, et al. Spatial prediction of landslide susceptibility using an adaptive neuro-fuzzy inference system combined with frequency ratio, generalized additive model, and support vector machine techniques[J]. Geomorphology. 2017, 297: 69-85.

[53]Ting-yu Zhang, Ling Han, Heng Zhang, 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(06): 1275-1288.

[54]郭天颂, 张菊清, 韩煜, 等. 基于粒子群优化支持向量机的延长县滑坡易发性评价[J]. 地质科技情报, 2019, 38(03): 236-243.

[55]罗路广, 裴向军, 黄润秋, 等. GIS支持下CF与Logistic回归模型耦合的九寨沟景区滑坡易发性评价[J/OL]. 工程地质学报: 1-11[2021-03-17].https://doi.org/10.13544/j.cnki.jeg.2019-202.

[56]邓念东, 崔阳阳, 郭有金. 基于频率比-随机森林模型的滑坡易发性评价[J]. 科学技术与工程, 2020, 20(34): 13990-13996.

[57]周超, 殷坤龙, 曹颖, 等. 基于集成学习与径向基神经网络耦合模型的三峡库区滑坡易发性评价[J]. 地球科学, 2020, 45(06): 1865-1876.

[58]Hoang Nguyen, Mohammad Mehrabi, Bahareh Kalantar, et al. Potential of hybrid evolutionary approaches for assessment of geo-hazard landslide susceptibility mapping[J]. Geomatics, Natural Hazards and Risk, 2019, 10(1): 1667-1693.

[59]郑迎凯, 陈建国, 王成彬, 等. 确定性系数与随机森林模型在云南芒市滑坡易发性评价中的应用[J]. 地质科技通报, 2020, 39(06): 131-144.

[60]武雪玲, 沈少青, 牛瑞卿. GIS支持下应用PSO-SVM模型预测滑坡易发性[J]. 武汉大学学报(信息科学版), 2016, 41(05): 665-671.

[61]安凯强, 牛瑞卿. 信息量支持下SVM模型滑坡灾害易发性评价[J]. 长江科学院院报, 2016, 33(08): 47-51.

[62]田述军, 张珊珊, 唐青松, 等. 基于不同评价单元的滑坡易发性评价对比研究[J]. 自然灾害学报, 2019, 28(06): 137-145.

[63]汤国安, 刘学军, 间国年. 数字高程模型及地学分析的原理与方法[M]. 北京：科学出版社, 2006：198.

[64]王凯, 张少杰, 韦方强. 斜坡单元提取方法研究进展和展望[J]. 长江科学院院报, 2020, 37(06): 85-93.

[65]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(03): 48-50.

[66]颜阁, 梁收运, 赵红亮. 基于GIS的斜坡单元划分方法改进与实现[J]. 地理科学, 2017, 37(11): 1764-1770.

[67]Massimiliano Alvioli, Ivan Marchesini, Paola Reichenbach, 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(11): 3975-3991.

[68]Kai Wang, Shaojie Zhang, Ricardo DelgadoTéllez, et al. A new slope unit extraction method for regional landslide analysis based on morphological image analysis[J]. Bulletin of Engineering Geology and the Environment, 2019, 78(06): 4139-4151.

[69]宋腾蛟. 金沙江奔子栏水源地库区单体滑坡稳定性智能评估及滑坡灾害区域风险分析[D]. 吉林大学, 2015.

[70]洪增林, 李永红, 张玲玉, 等. 一种基于主成分分析法的区域性地质灾害危险性评估方法[J]. 灾害学, 2020, 35(01): 118-124.

[71]尚敏, 廖芬, 马锐, 等.白家包滑坡变形与库水位、降雨相关性定量化分析研究[J/OL]. 工程地质学报: 1-8[2021-03-17].https://doi.org/10.13544/j.cnki.jeg.2020-045.

[72]王岩, 王聪英, 申艳梅. 改进蜂群优化聚类集成联合相似度推荐算法[J]. 计算机工程, 2020, 46(10): 88-94+102.

[73]贾科, 杨哲, 魏超, 等. 基于斯皮曼等级相关系数的新能源送出线路纵联保护[J]. 电力系统自动化, 2020, 44(15): 103-111.

[74]高华喜, 殷坤龙. 降雨与滑坡灾害相关性分析及预警预报阀值之探讨[J]. 岩土力学, 2007, 28(05): 1055-1060.

[75]朱钰, 郑屹然, 尹默. 统计学意义下的多重共线性检验方法[J]. 统计与决策, 2020, 36(07): 34-36.

[76]许冲, 戴福初, 姚鑫, 等. 基于GIS与确定性系数分析方法的汶川地震滑坡易发性评价[J]. 工程地质学报, 2010, 18(01): 15-26.

[77]张俊, 殷坤龙, 王佳佳, 等. 三峡库区万州区滑坡灾害易发性评价研究[J]. 岩石力学与工程学报, 2016, 35(02): 284-296.

[78]蒋德明, 李益敏, 鲍华姝. 泸水县滑坡孕灾环境因素敏感性研究[J]. 自然灾害学报, 2016, 25(04): 109-119.

[79]李明波, 陈平, 陈植华. 湖南省降雨型滑坡灾害发生的关键性因子研究[J]. 东华理工大学学报(自然科学版), 2018, 41(01): 36-40.

[80]周超. 集成时间序列InSAR技术的滑坡早期识别与预测研究[D]. 中国地质大学, 2018.

[81]冯杭建, 周爱国, 唐小明, 等. 基于确定性系数的降雨型滑坡影响因子敏感性分析[J]. 工程地质学报, 2017, 25(02): 436-446.

[82]曾令科, 许模, 方琼, 等. 植被与地质灾害发育分布关系初探[J]. 地质灾害与环境保护, 2010, 21(03): 97-100.

[83]孙小凡, 张鹏, 党超. 基于GIS的城市滑坡灾害易发性评价——以湖北省宜昌市城区为例[J]. 水土保持通报, 2018, 38(06): 304-309.

[84]李益敏, 谢亚亚, 蒋德明, 等. 怒江州斜坡地质灾害孕灾环境因素敏感性研究[J]. 水土保持研究, 2018, 25(05): 300-305.

[85]崔阳阳, 邓念东, 曹晓凡, 等. 基于集成学习的地质灾害危险性评价[J]. 水力发电, 2020, 46(10): 36-41.

[86]刘希林, 庙成, 田春山. 区域滑坡和泥石流灾害两种危险性评价方法的比较分析[J]. 防灾减灾工程学报, 2017, 37(01): 71-78.