府谷镇地处陕西省榆林市府谷县东南部，与山西省保德县隔黄河相望，地势西北高东南低，地质环境脆弱，近年来随着城镇经济社会的快速发展，城区挖山填沟造地活动强烈，导致原有斜坡稳定性遭到破坏，崩塌等地质灾害频发，给城镇社会经济发展造成严重困扰。因此，开展府谷镇地质灾害易发性分析和风险评价，对城镇地质灾害防灾减灾、国土空间利用规划等具有重要的理论和实际意义。

本文结合府谷镇地质灾害大比例尺调查和勘查工作，分析总结研究区地质灾害发育特征及形成机理，开展了基于不同分辨率数据下多模型的府谷镇地质灾害易发性评价，在此基础上对府谷镇地质灾害风险进行了分析预测。论文研究取得的主要成果如下：

（1）研究区地质灾害类型主要有崩塌、滑坡和泥石流，崩塌、滑坡主要集中于老城区高石崖村—新安村—新府村以及沿黄公路沿线，泥石流分布于孤山川河支流的沟谷区域；地质灾害多发生于人类工程活动强烈时期、汛期和冻融期。

（2）分别建立了2m、6m、15m、30m和60m不同分辨率数据下的评价单元模型样本数据库，进行了基于信息量（IV）、随机森林（RF)、卷积神经网络(CNN)、信息量-随机森林耦合（IV-RF）和信息量-卷积神经网络（IV-CNN）耦合的多种不同空间模型的训练和测试，完成了不同分辨率数据、不同评价模型下的府谷镇地质灾害易发性评价对比研究。结果表明，基于6m空间分辨率的RF模型为府谷镇易发性评价的最优模型。

（3）以降雨为诱发因素开展了府谷镇地质灾害危险性评价，采用Pearson-Ⅲ型模型计算不同降雨重现期下的降雨极值，引入危险性指数，在易发性的基础上选取二十年降雨重现期作为时间动态因素完成府谷镇极端降雨条件下的地质灾害危险性评价研究。结果表明，研究区危险性等级随着易发性等级的增加而增加。

（4）选择受威胁人口密度、建筑密度、道路密度为承灾体易损性评价指标，以行政村为评价单元，采用CRITIC确定指标权重，完成了府谷镇地质灾害易损性评价研究。结果表明，极高易损区有8个行政村，占府谷镇总面积的11.52%。

（5）府谷镇地质灾害风险评价结果显示，高风险和极高风险区主要分布于研究区北部和中部的峡谷丘陵地区，面积分别占总面积的6.37%和1.48%。

Fugu Town is located in the southeast of Fugu County, Yulin City, Shaanxi Province. It is across the Yellow River from Baode County, Shanxi Province. The terrain is high in the northwest and low in the southeast, and the geological environment is fragile. In recent years, with the rapid development of urban economy and society, the activity of digging mountains and filling ditches in urban areas is strong, which leads to the destruction of the original slope stability and the frequent occurrence of geological disasters such as collapse. Based on the large-scale investigation and exploration of geological disasters in Fugu Town, this paper analyzes and summarizes the development characteristics and formation mechanism of geological disasters in the study area, and carries out the susceptibility evaluation and risk analysis of geological disasters in Fugu Town based on multi-model under different spatial resolution data. The purpose of this paper is to provide reference for the risk prediction of urban-scale geological disasters with similar geological conditions through the discussion of the risk assessment model of geological disasters in Fugu Town. The main achievements of this paper are as follows :

( 1 ) The main types of geological disasters in the study area are collapse, landslide and debris flow. Collapse and landslide are mainly concentrated in Gaoshiya Village-Xin 'an Village-Xinfu Village in the old city and along the Yellow Road. Debris flow is distributed in the gully area of Gushanchuan River tributary. Geological disasters mostly occur in the period of strong human engineering activities, flood season and freeze-thaw period.

( 2 ) A sample database of evaluation unit models under different spatial resolution data of 2m, 6m, 15m, 30m and 60m was established, and a variety of different spatial models based on information content ( IV ), random forest ( RF ), convolutional neural network ( CNN ), information content-random forest coupling ( IV-RF ) and information content-convolutional neural network ( IV-CNN ) were trained and tested. The comparative study of geological hazard susceptibility evaluation in Fugu Town under different resolution data and different evaluation models was completed. The results show that the RF model based on 6m spatial resolution is the optimal model for the susceptibility evaluation of Fugu Town.

( 3 ) The risk assessment of geological disasters in Fugu Town was carried out with rainfall as the inducing factor. The Pearson-III model was used to calculate the rainfall extremes under different rainfall recurrence periods, and the risk index was introduced. On the basis of susceptibility, the 20-year rainfall recurrence period was selected as the time dynamic factor to complete the risk assessment of geological disasters under extreme rainfall conditions in Fugu Town. The results show that the risk level of the study area increases with the increase of the susceptibility level.

( 4 ) Selecting the threatened population density, building density and road density as the vulnerability evaluation index of the disaster-bearing body, taking the administrative village as the evaluation unit, and using CRITIC to determine the index weight, the vulnerability evaluation of geological disasters in Fugu Town was completed. The results show that there are 8 administrative villages in the extremely vulnerable area, accounting for 11.52 % of the total area of Fugu Town.

( 5 ) The results of risk assessment based on multiple models and spatial resolution data show that high-risk and extremely high-risk areas are mainly distributed in the canyon and hilly areas in the northern and central parts of the study area, accounting for 6.37 % and 1.48 % of the total area, respectively.

[1]许强, 黄润秋, 王来贵. 外界扰动诱发地质灾害的机理分析 [J]. 岩石力学与工程学报, 2002, (02): 280-4.

[2]潘懋, 李铁锋. 灾害地质学[M]. 北京大学出版社, 2002.

[3]Bui D T , Pradhan B , Lofman O , et al. Regional prediction of landslide hazard using probability analysis of intense rainfall in the Hoa Binh province, Vietnam[J]. Natural Hazards, 2013, 66(2):707-730.

[4]BEATY C B. Landslides and Slope Exposure [J]. Journal of Geology, 1956, 64(1): 70-4.

[5]Hemasinghe H , Rangali R , Deshapriya N L , et al. Landslide susceptibility mapping using logistic regression model (a case study in Badulla District, Sri Lanka)[J]. Procedia Engineering, 2018, 212:1046-1053.

[6]高泽民,丁明涛,杨国辉,等. 川藏铁路孜热—波密段泥石流灾害危险性评价[J]. 工程地质学报,2021,29(02):478-485.

[7]Shen H, Huang F, Fan X, et al. Improving the performance of artificial intelligence models using the rotation forest technique for landslide susceptibility mapping[J]. International Journal of Environmental Science and Technology, 2023, 20(10): 11239-11254.

[8]Ullah K, Wang Y, Fang Z, et al. Multi-hazard susceptibility mapping based on Convolutional Neural Networks[J]. Geoscience Frontiers, 2022, 13(5): 101425.

[9]王世宝,庄建琦,郑佳,等.基于深度学习的CZ铁路康定—理塘段滑坡易发性评价[J].工程地质学报,2022,30(03):908-919.

[10]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].岩石力学与工程学报,2021,40(06):1155-1169.

[11]Shirzadi A,Solaimani K,Roshan H M, et al. Uncertainties of prediction accuracy in shallow landslide modeling: Sample size and raster resolution[J]. Catena,2019,178.

[12]Schlögel 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.

[13]Palamakumbure D,Flentje P,Stirling D. Consideration of optimal pixel resolution in deriving landslide susceptibility zoning within the Sydney Basin, New South Wales, Australia[J]. Computers & Geosciences,2015,82.

[14]Azemeraw W. The impact of DEM resolution on landslide susceptibility modeling[J]. Arabian Journal of Geosciences,2022,15(10).

[15]Tian Y, XiaO C C, Liu Y, et al. Effects of raster resolution on landslide susceptibility mapping: A case study of Shenzhen[J]. Science in China Series E: Technological Sciences, 2008, 51(Suppl 2): 188-198.

[16]Varnes D J . Landslide hazard zonation: a review of principles and practice[J]. Natural Hazards, 1984, 3.

[17]Wang F, Xu P, Wang C, et al. Application of a GIS-based slope unit method for landslide susceptibility mapping along the Longzi River, Southeastern Tibetan Plateau, China[J]. ISPRS International Journal of Geo-Information, 2017, 6(6): 172.

[18]邱海军.区域滑坡崩塌地质灾害特征分析及其易发性和危险性评价研究[D].西北大学,2012.

[19]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,(01):185-190.

[20]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+69.

[21]Massimiliano A , Ivan M , 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 Discussions, 2016, 9(11):3975.

[22]徐继维,张茂省,范文.地质灾害风险评估综述[J].灾害学,2015,30(04):130-134.

[23]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,(01):7-18.

[24]Blaikie P, Cannon T, Davis I, et al. At risk: Natural hazards, people's vulnerability and disasters[J]. 1994.

[25]卢全中,彭建兵,赵法锁.地质灾害风险评估(价)研究综述[J].灾害学,2003,(04):60-64.

[26]Gary, Shook. An assessment of Disaster Risk and its Management in Thailand[J]. Disasters, 1997

[27]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.

[28]Guzzetti F, Carrara A, Cardinali M, et al. Landslide hazard evaluation: a review of current techniques and their application in a multi-scale study, Central Italy[J]. Geomorphology, 1999, 31(1-4): 181-216.

[29]夏辉.三峡库区重庆库段区域滑坡风险评价[D].中国地质大学,2018.

[30]杜国梁.喜马拉雅东构造结地区滑坡发育特征及危险性评价[D].中国地质科学院,2017.

[31]Guzzetti F, Malamud B D, Turcotte D L, et al. Power-law correlations of landslide areas in central Italy[J]. Earth and Planetary Science Letters, 2002, 195(3-4): 169-183.

[32]Picarelli L, Oboni F, Evans S G, et al. Hazard characterization and quantification[M]//Landslide risk management. CRC Press, 2005: 37-72.

[33]Das I, Stein A, Kerle N, et al. Probabilistic landslide hazard assessment using homogeneous susceptible units (HSU) along a national highway corridor in the northern Himalayas, India[J]. Landslides, 2011, 8: 293-308.

[34]桂蕾.三峡库区万州区滑坡发育规律及风险研究[D].中国地质大学,2014.

[35]管新邦.云南省滑坡地质灾害危险性评价研究[D].中国矿业大学(北京),2018.

[36]Guzzetti F, Reichenbach P, Cardinali M, et al. Probabilistic landslide hazard assessment at the basin scale[J]. Geomorphology, 2005, 72(1-4): 272-299.

[37]周超,常鸣,徐璐,等.贵州省典型城镇矿山地质灾害风险评价[J].武汉大学学报(信息科学版),2020,45(11):1782-1791.

[38]陈丽霞,殷坤龙,刘长春.降雨重现期及其用于滑坡概率分析的探讨[J].工程地质学报,2012,20(05):745-750.

[39]宋宇飞,范文,李军,等.不同降雨条件下不稳定斜坡财产损失风险评价——以镇巴县兴隆镇为例[J].工程地质学报,2020,28(02):401-411.

[40]Cardinali M, Reichenbach P, Guzzetti F, et al. A geomorphological approach to the estimation of landslide hazards and risks in Umbria, Central Italy[J]. Natural Hazards and Earth System Sciences, 2002, 2(1/2): 57-72.

[41]Landslide hazard and risk[M]. Chichester: Wiley, 2005.

[42]王涛,吴树仁,石菊松,等.滑坡强度与能级的概念辨析及评估方法探讨[J].水文地质工程地质,2013,40(02):92-100.

[43]Timmerman P. Vulnerability. resilience and the collapse of socieiy: a review of models and possible climatic applications[J].Environmental Monograph,Institute for Environmental Studies, 1981.

[44]丁锐.昌吉市南部山区崩塌滑坡灾害风险性评价[D].吉林大学,2023.

[45]Akgun A, Kıncal C, Pradhan B. Application of remote sensing data and GIS for landslide risk assessment as an environmental threat to Izmir city (west Turkey)[J]. Environmental monitoring and assessment, 2012, 184: 5453-5470.

[46]彭令,徐素宁,彭军还.多源遥感数据支持下区域滑坡灾害风险评价[J].吉林大学学报(地球科学版),2016,46(01):175-186.

[47]杨华,赵纯勇,张永兴.基于3S技术的地质灾害易损性面评价方法研究[J].中国地质灾害与防治学报,2004,(03):100-105+129.

[48]汪洋,郭跃,赵纯勇,等.基于3S技术的地质灾害易损性面评价研究[J].灾害学,2003(04):18-24.

[49]Leone F, Asté J P, Leroi E. Vulnerability assessment of elements exposed to mass-movement: working toward a better risk perception[J]. Landslides-Glissements de Terrain. Balkema, Rotterdam, 1996: 263-270.

[50]Mejia-Navarro M, Wohl E E. Geological hazard and risk evaluation using GIS: methodology and model applied to Medellin, Colombia[J]. Bulletin of the association of engineering geologists, 1994, 31(4): 459-481.

[51]张春山,何淑军,辛鹏,等.陕西省宝鸡市渭滨区地质灾害风险评价[J].地质通报,2009,28(08):1053-1063.

[52]蔡向阳,铁永波.我国山区城镇地质灾害易损性评价研究现状与趋势[J].灾害学,2016,31(04):200-204.

[53]张群,易靖松,张勇,等.西南山区县域单元的地质灾害风险评价——以怒江流域泸水市为例[J].自然灾害学报,2022,31(05):212-221..

[54]丁明涛,庙成.基于GIS的芦山地震灾区滑坡灾害风险评价[J].自然灾害学报,2014,23(04):81-90.

[55]武斌. 金沙江流域宁南小流域地质灾害风险评价[D].长安大学,2016.

[56]罗路广,裴向军,谷虎,等.基于GIS的“8.8”九寨沟地震景区地质灾害风险评价[J].自然灾害学报,2020,29(03):193-202.

[57]李冠宇,李鹏,郭敏,等.基于聚类分析法的地质灾害风险评价——以韩城市为例[J].科学技术与工程,2021,21(25):10629-10638.

[58]冯凡,唐亚明,潘学树,等.不同尺度下地质灾害风险评价方法探讨——以陕西吴堡县为例[J].中国地质灾害与防治学报,2022,33(02):115-124

[59]Corominas J ,Moya J. A review of assessing landslide frequency for hazard zoning purposes[J]. Engineering Geology, 2008, 102(3-4):193-213.

[60]Kawagoe S , Kazama S , Sarukkalige P R . Assessment of snowmelt triggered landslide hazard and risk in Japan[J]. Cold Regions Science and Technology, 2009, 58(3):120-129

[61]Zhou Z,Yuan Z L,Chong X. Slope Unit-Based Landslide Susceptibility Mapping Using Certainty Factor, Support Vector Machine, Random Forest, CF-SVM and CF-RF Models [J]. Frontiers in Earth Science,2021,9.

[62]张曦,陈丽霞,徐勇,等.两种斜坡单元划分方法对滑坡灾害易发性评价的对比研究[J].安全与环境工程,2018,25(01):12-17+50.

[63]孔嘉旭,庄建琦,彭建兵,等.基于信息量和卷积神经网络的黄土高原滑坡易发性评价[J].地球科学,2023,48(05):1711-1729.

[64]杨康,薛喜成,李识博.信息量融入GA优化SVM模型下的地质灾害易发性评价[J].安全与环境工程,2022,29(03):109-118.

[65]刘坚,李树林,陈涛.基于优化随机森林模型的滑坡易发性评价[J].武汉大学学报(信息科学版),2018,43(07):1085-1091.

[66]武雪玲,杨经宇,牛瑞卿.一种结合SMOTE和卷积神经网络的滑坡易发性评价方法[J].武汉大学学报(信息科学版),2020,45(08):1223-1232.

[67]Yi Y, Zhang Z, Zhang W, et al. Landslide susceptibility mapping using multiscale sampling strategy and convolutional neural network: A case study in Jiuzhaigou region[J]. Catena, 2020, 195: 104851.

[68]Wang Y, Fang Z, Hong H. Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China[J]. Science of the total environment, 2019, 666: 975-993.

[69]Hakim W L, Rezaie F, Nur A S, et al. Convolutional neural network (CNN) with metaheuristic optimization algorithms for landslide susceptibility mapping in Icheon, South Korea[J]. Journal of environmental management, 2022, 305: 114367.

[70]Liu R,Yang X, Xu C,et al. Comparative study of convolutional neural network and conventional machine learning methods for landslide susceptibility mapping[J]. Remote Sensing, 2022, 14(2): 321.

[71]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].工程地质学报,2021,29(02):526-535.

[72]Chen W,Sun Z,Han J. Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models[J]. Applied Sciences,2019,9(1).

[73]Quinn P E, Hutchinson D J, Diederichs M S, et al. Characteristics of large landslides in sensitive clay in relation to susceptibility, hazard, and risk[J]. Canadian Geotechnical Journal, 2011, 48(8): 1212-1232.

邹迁.云南省兰坪县县城区地质灾害风险评价[D].昆明理工大学,2022