基于CF-SVM模型的沿河县滑坡易发性评价

莫思; 江攀和

doi:10.11932/karst2026y025

基于CF-SVM模型的沿河县滑坡易发性评价

doi: 10.11932/karst2026y025

莫思^1,,
江攀和^2, ,

1.
贵州省地矿局一0六地质大队, 贵州遵义 563000
2.
贵州省地矿局一0二地质大队, 贵州遵义 563000

基金项目: 黔北高位台地碎屑岩层滑坡蠕滑变形机制与多情景风险研究（黔地质科合[2025]14号）

详细信息

作者简介:
莫思（1989－），男，高级工程师。主要从事水工环地质研究。E-mail：346074391@qq.com

通讯作者:
江攀和（1994－），男，高级工程师，注册岩土工程师。主要从事水工环地质研究。E-mail：843895115@qq.com。

计量
- 文章访问数: 21
- HTML浏览量: 8
- PDF下载量: 17
- 被引次数: 0
出版历程
- 收稿日期: 2025-07-28
- 录用日期: 2025-10-24
- 修回日期: 2025-10-20
- 网络出版日期: 2026-06-23

Landslide susceptibility assessment of Yanhe County based on CF-SVM model

MO Si^1
,,
JIANG Panhe^{2
, ,}

1.
No. 106 Geological Team, Guizhou Bureau of Geology and Mineral Resources, Guizhou Zunyi 563000, China
2.
No. 102 Geological Team, Guizhou Bureau of Geology and Mineral Resources, Guizhou Zunyi 563000, China

摘要

摘要: 沿河县地处贵州高原向湘西丘陵和四川盆地过渡的斜坡地带，区内地质环境条件复杂，在内外动力地质作用的共同影响下，滑坡地质灾害极其发育。通过相关性与多重共线性分析筛选出坡度、坡向、高程、地形起伏度、工程岩组、距水系距离、距道路距离、距构造距离及植被覆盖等9项评价因子。结合确定性系数（CF）与支持向量机（SVM）在定量分析与非线形拟合方面的优势，构建CF-SVM耦合模型进行滑坡易发性评价。结果显示，CF-SVM模型识别出的极高和高易发区主要集中于和平街道、客田镇及新景镇附近山区、黑水镇及淇滩镇东侧，覆盖90.3%的滑坡点，相较单独CF模型和SVM模型具有更高的预测效能。ROC曲线验证表明，CF-SVM模型的AUC值为0.889，优于SVM模型和CF模型的0.871和0.790。表明CF-SVM模型具有更高的拟合优度和更强的预测能力，能够更准确地反映沿河县滑坡地质灾害的易发性分布特征，可为区域地质灾害风险评估与防控提供有力的技术支持。
- 滑坡 /
- CF /
- SVM /
- CF-SVM /
- 易发性评价 /
- 沿河县
Abstract: Yanhe County is situated within the transitional slope zone connecting the Guizhou Plateau, the Xiangxi Hilly Region, and the Sichuan Basin. The overall topography of the county exhibits a pattern of higher elevations in the northwest and southeast, with a lower central area. The landform is characterized by a distinct, narrow, and elongated belt that is wider in the south and tapers towards the north. This region features highly undulating terrain, intense geomorphological incision, complex geological structures, and consequently, a fragile geological environment. Under the combined influence of both endogenic and exogenic geological processes, the area exhibits a relatively high degree of landslide development, making geological disaster risks particularly prominent.To establish a scientifically sound and rational landslide susceptibility evaluation system, this study employed the Pearson correlation coefficient, Tolerance (TOL), and Variance Inflation Factor (VIF) to conduct correlation and multicollinearity analyses on candidate influencing factors. Through this process, nine key evaluation factors were ultimately selected: slope gradient, slope aspect, elevation, topographic relief, engineering rock group, distance to river system, distance to roads, distance to geological structures, and vegetation coverage. To address the issue of spatial bias inherent in the selection of non-landslide samples, negative samples were randomly distributed in areas outside predefined buffers surrounding known landslide points. This methodology effectively enhanced the spatial representativeness and overall rationality of the sample selection.Based on raster data units, and leveraging the respective strengths of different models, a combined approach was adopted. The Certainty Factor (CF) model offers advantages in quantitative analysis and indicator weight calculation, while the Support Vector Machine (SVM) model demonstrates excellent performance in handling non-linear relationships and complex pattern recognition. By integrating historical landslide distribution data, the nine selected evaluation factors, and the optimized non-landslide samples, a comprehensive training dataset suitable for the combined machine learning model was constructed. The study area was subsequently classified into four susceptibility grades—Low, Medium, High, and Very High—using the Natural Breaks classification method. The accuracy of the model predictions was determined based on the number of known landslide points falling within the Medium, High, and Very High susceptibility zones.The results revealed that the CF, SVM, and combined CF-SVM models successfully predicted 383, 389, and 392 landslide points, respectively. These figures account for 97.70%, 99.50%, and 99.74% of the total recorded landslides. The corresponding areal proportions designated as high-risk zones (encompassing High and Very High susceptibility classes) were 76.34%, 69.95%, and 60.96%, respectively. A key observation is that as the areal extent of the high-risk classification progressively decreased across the models, the concentration of landslide points within these zones significantly increased. This trend demonstrates a enhanced spatial aggregation of predicted hazard, indicating an improvement in the model's precision in pinpointing the most vulnerable areas.An analysis of the landslide susceptibility zoning results from the various models shows that the Very High and High susceptibility areas predominantly exhibit a belt-like distribution pattern. This pattern shows a significant spatial coupling relationship with the major surface water systems and geological structures. These high-risk zones are primarily concentrated in the mountainous areas near Heping Street, Ketian Town, and Xinjing Town, as well as the eastern sides of Heishui Town and Qitan Town. These regions are typically characterized by low mountain valley topography, well-developed geological structures, dense river networks, intensive transportation infrastructure, a high degree of urbanization, and frequent human activities—all factors contributing to the high frequency of landslide occurrences.In contrast, the Medium and Low susceptibility areas are mainly distributed in patchy and scattered patterns, though they are present in all townships. The Medium susceptibility zone generally forms a peripheral belt around the Very High and High susceptibility cores. These medium and low susceptibility areas are primarily located in mid-mountain valleys and high-altitude mountainous regions. Their geological environmental conditions are complex, but they feature lower population density, relatively scarce transportation facilities, lower levels of urbanization, and moderate to weak intensity of human engineering activities. While landslide hazards are still present in these areas, their developmental degree is relatively limited.The high-risk zones (combined High and Very High) identified by the CF-SVM model covered 90.3% of the historical landslide points. This distribution shows a high degree of consistency with the spatial pattern of actual recorded geological disaster hazards. Conversely, the proportion of disaster points located within the Low susceptibility area was merely 0.26%. This stark contrast further verifies the model's excellent discriminatory capability and predictive accuracy.The confusion matrix results for the three models indicate that the CF-SVM model performed the best, achieving a True Negative Rate of 91.45% and a True Positive Rate of 83.05%. The CF model, in comparison, demonstrated relatively weaker performance, with a True Negative Rate of 85.47% and a True Positive Rate of 68.64%. Overall, all models exhibited high classification performance in terms of both True Negative and True Positive Rates, reflecting their strong ability to discriminate unseen samples. However, when dealing with the complex and heterogeneous distribution of landslide and non-landslide samples, significant differences emerged between the models. Among them, the CF-SVM model demonstrated superior learning capability and produced the most effective classification results.The Receiver Operating Characteristic (ROC) curve analysis showed that the CF-SVM model achieved an Area Under the Curve (AUC) value of 0.889. This was significantly higher than the AUC values of the individually applied SVM model (0.871) and the CF model (0.790). This result indicates that the integrated CF-SVM model possesses a better goodness-of-fit and stronger generalization ability. It can more accurately delineate the spatial susceptibility characteristics of landslide geological disasters in Yanhe County. Therefore, this approach provides a scientific basis and reliable technical support for regional geological disaster risk assessment, monitoring and early warning systems, and prevention and control decision-making.
- landslide /
- CF /
- SVM /
- CF-SVM /
- susceptibility evaluation /
- Yanhe County

HTML

图 1 研究区地势特征及地灾点空间分布

Figure 1. Topographic features of the study area and spatial distribution of geological hazard points

下载: 全尺寸图片幻灯片

图 2 各因子相关性分析热图

a. 地形坡度；b. 坡向；c. 高程；d. 地形起伏度；e. 工程岩组；f.距水系距离；g. 距道路距离；h. 距地质构造距离；i. 植被覆盖率

Figure 2. Heatmap of correlation analysis of each factor

下载: 全尺寸图片幻灯片

图 3 滑坡评价因子分级图

a. 地形坡度；b. 坡向；c. 高程；d. 地形起伏度；e. 工程岩组；f.距水系距离；g. 距道路距离；h. 距地质构造距离；i. 植被覆盖率

Figure 3. Grading diagram of landslide evaluation factors

下载: 全尺寸图片幻灯片

图 4 滑坡易发性分区结果

a. CF模型；b. SVM模型；c. CF-SVM模型

Figure 4. Results of landslide susceptibility zoning

下载: 全尺寸图片幻灯片

图 5 混淆矩阵

Figure 5. Confusion matrix

下载: 全尺寸图片幻灯片

图 6 ROC 曲线及AUC值

Figure 6. ROCcurve and AUC value

下载: 全尺寸图片幻灯片

表 1 研究区数据来源

Table 1. Data Sources of the Study Area

数据名称	数据来源	数据类型	数据时间	分辨率
DEM	地理空间数据云平台提供的ASTER GDEM V003数据集（https://www.gscloud.cn/）	栅格	2000—2013年	30 m
地形坡度、坡向、地形起伏度	DEM提取	栅格	/	30 m
工程岩组、地表水系、道路及地质构造	《贵州省沿河县地质灾害风险普查报告》	矢量	2022年	/
植被覆盖率	国家对地观测科学数据中心（https://www.noda.ac.cn/）MODIS	栅格	2020年	1 km
现状及历史地质灾害点	《贵州省沿河土家族自治县地质灾害调查与区划报告》、《乌江流域（沿河县）地质灾害详细调查报告》、《沿河县高位隐蔽性地质灾害隐患专业排查报告》及《贵州省沿河县地质灾害风险普查报告》	矢量	2002—2022年	/

下载: 导出CSV

表 2 因子共线性分析

Table 2. Factor collinearity analysis

评价因子	TOL	VIF
地形坡度	0.223	4.474
坡向	0.982	1.018
高程	0.750	1.333
地形起伏度	0.224	4.470
工程岩组	0.898	1.114
距水系距离	0.894	1.118
距道路距离	0.903	1.107
距地质构造距离	0.936	1.068
植被覆盖率	0.868	1.152

下载: 导出CSV

表 3 滑坡评价因子分级CF值统计

Table 3. Statistical data of CF Values for grading of landslide evaluation factors

评价因子	因子分级	滑坡点/个	CF值	评价因子	因子分级	滑坡点/个	CF值
地形坡度	＜15	101	−0.341	工程岩组	硬质岩组	40	−0.819
	[15,25)	186	0.264		软质岩组	256	0.647
	[25,35)	82	0.103		软硬相间岩组	96	0.159
	[35,45)	21	−0.069	距水系距离	＜100	44	−0.186
	≥45	2	−0.651		[100,300)	145	0.357
坡向	平面	1	−0.761		[300,500)	92	0.150
	北	54	0.193		[500,1000)	94	−0.177
	东北	50	−0.102		＞1000	17	−0.674
	东	74	0.124	距道路距离	＜200	83	0.474
	东南	37	−0.130		[200,500)	48	0.041
	南	44	0.091		[500,1000)	75	0.122
	西南	50	0.044		[1000,2000)	87	−0.122
	西	41	−0.223		＞2000	99	−0.279
	西北	41	0.010	距地质构造距离	＜200	62	0.173
高程	＜500	109	0.534		[200,500)	67	0.091
	[500,750)	191	0.162		[500,1000)	53	−0.298
	[750,1000)	77	−0.346		[1000,2000)	118	0.175
	＞1000	15	−0.763		＞2000	92	−0.140
地形起伏度	＜15	64	−0.444	植被覆盖率	＜25%	0	−1.000
	[15,30)	209	0.226		[25%,45%)	7	0.522
	[30,60)	110	0.048		[45%,65%)	35	0.648
	≥60	9	−0.139		[65%,85%)	235	0.227
					＞85%	115	−0.409

下载: 导出CSV

表 4 训练样本空间分布统计

Table 4. Statisticaldistribution of training sample space

评价因子	因子分级	正样本/%	负样本/%	评价因子	因子分级	正样本/%	负样本/%
地形坡度	＜15	25.77	30.36	工程岩组	硬质岩组	10.20	14.03
	[15,25)	47.45	44.39		软质岩组	65.31	63.01
	[25,35)	20.92	19.39		软硬相间岩组	24.49	22.96
	[35,45)	5.36	4.34	距水系距离	＜100	11.22	13.52
	≥45	0.51	1.53		[100,300)	36.99	32.91
坡向	平面	0.26	1.28		[300,500)	23.47	23.21
	北	13.78	12.24		[500,1000)	23.98	21.68
	东北	12.76	12.24		＞1000	4.34	8.67
	东	18.88	15.05	距道路距离	＜200	21.17	17.09
	东南	9.44	10.97		[200,500)	12.24	17.09
	南	11.22	9.69		[500,1000)	19.13	17.35
	西南	12.76	13.78		[1000,2000)	22.19	25.26
	西	10.46	14.03		＞2000	25.26	23.21
	西北	10.46	10.71	距地质构造距离	＜200	15.82	12.76
高程	＜500	27.81	29.85		[200,500)	17.09	17.86
	[500,750)	48.72	43.88		[500,1000)	13.52	16.84
	[750,1000)	19.64	20.92		[1000,2000)	30.10	30.87
	＞1000	3.83	5.36		＞2000	23.47	21.68
地形起伏度	＜15	16.33	17.60	植被覆盖度	＜25%	0.00	0.26
	[15,30)	53.32	54.85		[25%,45%)	1.79	0.26
	[30,60)	28.06	23.72		[45%,65%)	8.93	6.89
	≥60	2.30	3.83		[65%,85%)	59.95	62.24
					＞85%	29.34	30.36

下载: 导出CSV

表 5 地质灾害易发性分区统计汇总表

Table 5. Summary of statistical data on the division of geological hazard prone areas

模型	易发性等级	栅格数据	栅格比例/%	滑坡个数	滑坡比例/%	频率比值
CF	低易发区	648204	23.66	9	2.30	0.10
	中易发区	1287423	47.00	187	47.70	1.01
	高易发区	605442	22.10	123	31.38	1.42
	极高易发区	198132	7.23	73	18.62	2.57
SVM	低易发区	829240	30.05	3	0.77	0.03
	中易发区	800947	29.02	39	9.95	0.34
	高易发区	838678	30.39	200	51.02	1.68
	极高易发区	290669	10.53	150	38.27	3.63
CF-SVM	低易发区	1077193	39.04	1	0.26	0.01
	中易发区	745320	27.01	37	9.44	0.35
	高易发区	638575	23.14	198	50.51	2.18
	极高易发区	298446	10.82	156	39.80	3.68

下载: 导出CSV

表 6 模型精度评价结果

Table 6. Evaluation results of model accuracy

模型	总体准确率	精确率	召回率	F1分数	Kappa	AUC
CF	0.787	0.862	0.686	0.764	0.449	0.790
SVM	0.855	0.889	0.814	0.850	0.572	0.871
CF-SVM	0.872	0.907	0.831	0.867	0.613	0.889

下载: 导出CSV

参考文献(41)

[1]	Moziihrii Ado, Khwairakpam Amitab, Arnab Kumar Maji, Elżbieta Jasińska, Radomir Gono, Zbigniew Leonowicz, Michał Jasiński. Landslide susceptibility mapping using machine learning: a literature survey[J]. Remote Sensing, 2022, 14(13): 3029-3029. doi: 10.3390/rs14133029
[2]	王守华, 王睿菘, 孙希延, 刘小明, 卢伟萍, 林子安. 基于CF-CNN-LSTM模型的滑坡易发性评价[J]. 自然灾害学报, 2024, 33(5): 84-95. WANG Shouhua, WANG Ruisong, SUN Xiyan, LlU Xiaoming, LU Weiping, LIN Zian. Landslide susceptibility evaluation based on CF-CNN-LSTM model[J]. Journal Of Natural Disasters, 2024, 33(5): 84-95.
[3]	殷跃平. 中国地质灾害减灾战略初步研究[J]. 中国地质灾害与防治学报, 2004(2): 4-11. YIN Yueping. Initial study on the hazard relief strategy ofgeological hazard in China[J]. The Chinese Journal Of Geolcgical Hazard And Control, 2004(2): 4-11.
[4]	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, (3): 433-454. HUANG Runqiu. Large-scale landslides and their sliding mechanisms in China since the 20th century[J]. Chinese . Joural Ofrock Mechanics And Engineering, 2007, (3): 433-454.
[5]	屠水云, 张钟远, 付弘流, 徐世光, 邓明国, 何例春, 刘金字. 基于CF与CF-LR模型的地质灾害易发性评价[J]. 中国地质灾害与防治学报, 2022, 33(2): 96-104. TU Shuiyun, ZHANG Zhongyuan, FU Hongliu, XU Shiguang, DENG Mingguo, HE Lichun, LlU Jinyu. Geological hazard susceptibility evaluation based on CF and CF-LR model[J]. The Chinese Journal Of Geolcgical Hazard And Control, 2022, 33(2): 96-104.
[6]	杨晶晶, 肖玉, 安泉, 刘浩, 公斌. 黔东北地区地质灾害时空分布规律及孕灾地质环境研究[J]. 中国煤炭地质, 2024, 36(2): 64-68. YANG Jingjing , XIAO Yu, AN Quan, LlU Hao, GONG Bin. Study on the Spatio-temporal Distribution Law of Geological Hazards and the Disaster-inducingEnvironment in the Northeastern Guizhou. [J]. Coal Geology Of China, 2024, 36(2): 64-68.
[7]	周苏华, 付宇航, 徐智文, 杨明辉, 韩文杰. 基于主客观赋权法的福建省地质灾害易发性评价[J]. 安全与环境学报, 2023, 23(9): 3204-3214. ZHOU Suhua, FU Yuhang, XU Zhiwen, YANG Minghui, HAN Wenjie. Geological disasters susceptibilitymapping in Fujian Province based onsubjective and objective weighting[J]. Joumal Of Safety And Environment, 2023, 23(9): 3204-3214.
[8]	李彧磊, 熊启华, 龙婧, 王芮琼, 陈标典, 曾嘉. 基于斜坡单元鄂西山区典型集镇地质灾害风险评价[J]. 科学技术与工程, 2023, 23(6): 2326-2338. LI Yulei, XIONG Qihua, LONG Jing, WANG Ruiqiong, CHEN Biaodian, ZENG Jia. Risk Assessment of geohazards based on slope units in a typical mountainous county town of western Hubei Province[J]. Science Technology And Engineering, 2023, 23(6): 2326-2338.
[9]	张静, 崔健, 马诗敏, 代雅建, 朱巍. 基于层次分析法与频率比模型的采空塌陷危险性评价[J]. 地质与勘探, 2024, 60(1): 88-94. ZHANG Jing, CUl Jian, MA Shimin, DAl Yajian, ZHU Wei. Risk assessment of goaf collapse based on analytic hierarchy process and frequeney ratio model[J]. Geology and Exploration, 2024, 60(1): 88-94.
[10]	王恒恒, 张发旺, 郭纯青, 苏春田. 基于层次分析法的城市岩溶塌陷危险性评价: 以武汉市南部为例[J]. 中国岩溶, 2016, 35(06): 667-673. WANG Hengheng, ZHANG Fawang, GUO Chunqing, SU Chuntian. Urban karst collapse hazard assessment based on analytic hierarchy process: an example of southern Wuhan City[J]. Carsologica Sinica, 2016, 35(06): 667-673.
[11]	吴远斌, 刘之葵, 殷仁朝, 雷明堂, 戴建玲, 罗伟权, 潘宗源. 基于AHP和GIS技术的湖南怀化地区岩溶塌陷易发性评价[J]. 中国岩溶, 2022, 41(1): 21-33. WU Yuanbin, LlU Zhikui, YlN Renchao, LEl Mingtang, DAl Jianling, LUO Weiquan, PAN Zongyuan. Evaluation of karst collapse susceptibility in Huaihua area, Hunan Province based on AHP and GIS[J]. Carsologica Sinica, 2022, 41(1): 21-33.
[12]	曹洪洋, 任晓莹, 李志强. 基于GIS的分形理论和信息量法的区域滑坡易发性评价[J]. 中国安全科学学报, 2025, 35(1): 178-185. CAO Hongyang, REN Xiaoying, LI Zhiqiang. Assessment of regional landslide susceptibility based on fractal theoryand iinformation amount method of CIS[J]. China Safety Science Journa, 2025, 35(1): 178-185.
[13]	王新伟, 张漓黎, 莫德科, 叶宗达, 江凡. 基于信息量和多层感知机分类器模型耦合的平果市斜坡类地质灾害易发性评价[J]. 中国岩溶, 2023, 42(2): 370-381. WANG Xinwei, ZHANG Lili, MO Deke, YE Zongda, JANG Fan. Hillslope geo-hazard susceptibility assessment in Pingguo City based on coupling of CF information value and MLPC classifier model[J]. Carsologica Sinica, 2023, 42(2): 370-381.
[14]	谢斯琴, 栾崧, 周大海. 基于GIS和信息量模型方法的地质灾害危险性评价[J/OL]. 中国岩溶, 1-9 2025-07-25]. XIE Siqin, LUAN Song, ZHOU Dahai. Risk Assessment of geological hazard based on GIS and information modeling methods[J/OL]. Carsologica Sinica, 1-9[2025-07-25].
[15]	江攀和, 张明思, 梁劲松, 陈磊. 信息量模型在山地斜坡地质灾害风险评价中的应用: 以贵定县宝山盘江重点区为例[J]. 贵州地质, 2022, 39(2): 159-166. JIANG Panhe, ZHANG Mingsi, LIANG Jinsong, CHEN Lei. Application of information quantity model in risk assessment of geological hazards in mountain slopes: Taking the key area of Panjiang in Baoshan, Guiding County as an example[J]. Guizhou Geology, 2022, 39(2): 159-166.
[16]	李信, 薛桂澄, 柳长柱, 马波, 杨永鹏, 杨峰, 王晓林, 李洁玉. 基于IV、CF、LRIV和LRCF模型的海南昌江县地质灾害易发性评价研究[J]. 地震工程学报, 2025, 47(2): 319-330+341. LI Xin, XUE Guicheng , LlU Changzhu, MA Bo, YANG Yongpeng, YANG Feng, WANG Xiaolin , Ll Jieyu. Susceptibility assessment of geological hazards in Changjiang County. Hainan Island, based on IV, CF, LRIV, and LRCF models[J]. China Earthquake Engineering Journal , 2025, 47(2): 319-330+341.
[17]	咸利民, 季民, 刘法军, 李强. 基于CF与优化RF模型耦合的泰山地区地质灾害易发性评价[J]. 水土保持通报, 2024, 44(5): 134-143. XIAN Limin , JI Min, LIU Fajun, LI Qiang. Assessing Geological Disaster Susceptibility in Taishan Area by CouplingCertainty Factor Model with Optimized Random Forest Model[J]. Bulletin Of Soil And Water Conservation, 2024, 44(5): 134-143.
[18]	于喜坤, 张紫昭, 史光明, 李崇博, 刘毅业, 朱建华, 陈伟楠. 基于确定性系数与信息量耦合模型的新疆额敏县地质灾害易发性评价[J]. 工程地质学报, 2023, 31(4): 1333-1349. YU Xikun, ZHANG Zizhao, SHI Guangming, LI Chongbo, LlU Yiye, ZHU Jianhua, CHEN Weinan. Evaluation of Geological Hazard Susceptibility in Emin County, Xinjiang Based on Deterministic Coefficient and Information Coupling Model[J]. Journal Of Engineering Geology, 2023, 31(4): 1333-1349.
[19]	梁峰, 江攀和. 基于IVM-CF耦合模型的贵定县滑坡地质灾害易发性评价[J]. 水利水电技术(中英文), 2024, 55(S2): 669-677. LIANG Feng, JIANG Panhe. Evaluation of Landslide Geological Hazard Susceptibility in Guiding County Based on IVM-CF Coupling Model[J]. Water Resources And Hydropower Engineering, 2024, 55(S2): 669-677.
[20]	邹富宝, 付卓, 樊风雷, 吴华, 郭治兴. 基于频率比与AHP模型的西藏东部地区滑坡易发性评价[J]. 自然灾害学报, 2023, 32(2): 235-242. ZOU Fubao, FU Zhuo, FAN Fenglei, WU Hua, GUO Zhixing. Evaluation of landslide susceptibility in eastern Tibet based on frequency ratio and AHP model[J]. Journal Of Natural Disasters, 2023, 32(2): 235-242.
[21]	吴常润, 角媛梅, 王金亮, 许汉华, 张华, 徐秋娥. 基于频率比-逻辑回归耦合模型的双柏县滑坡易发性评价[J]. 自然灾害学报, 2021, 30(4): 213-224. WU Changrun, JIAO Yuanmei, WANG Jinliang, XU Hanhua, ZHANG Hua, XU Oiue. Frequency Ratio and Logistic Regression Models Based Coupling Analysis Forsusceptibility of Landslide in Shuangbai County[J]. Journal Of Natural Disasters, 2021, 30(4): 213-224.
[22]	胡涛. 贵州省思南县地质灾害危险性评价研究[D]. 中国地质大学, 2020. HU Tao. Study of geological disasters hazard assessment in Sinan County of Guizhou Province[D]. China University of Geosciences, 2020.
[23]	田怡帆, 梁皓, 陈亮, 王立朝, 李志清, 冯振. 基于机器学习的崩滑灾害易发性评价模型研究—以白龙江流域为例[J/OL]. 工程地质学报, 1-10 2025-07-24]. TIAN Yifan, LIANG Hao , CHEN Liang, WANG Lichao , Ll Zhiqing, FENG Zhen. Research on Susceptibility Assessment of Landslide and Collapse Disasters Based on Machine Learning Models: A Case Study of Bailong River Basin[J/OL]. Journal Of Engineering Geology, 1-10[2025-07-24].
[24]	邢昭, 孟小军, 袁晶晶, 张迪, 刘力, 陈彦美. 信息量支持下SVM-GBDT模型的滑坡危险性评价[J]. 科学技术与工程, 2025, 25(7): 2712-2720. XING Zhao, MENG Xiaojun, YUAN Jingjing, ZHANG Di , LIU Li, CHEN Yanmei. Landslides Hazard Assessment Based on SVM-GBDT and GradientBoosting Decision Tree Model Supported by Information Quantity[J]. Science Technology And Engineering, 2025, 25(7): 2712-2720.
[25]	屈鹏鑫, 谢婉丽, 刘琦琦, 王昱琛. 基于机器学习方法改进IVM-RF耦合模型的崩滑灾害危险性评价: 以延安市志丹县为例[J]. 地质科技通报, 2025, 44(3): 280-295. QU Pengxin , XlE Wanli, LIU Qiqi, WANG Yuchen. Collapse and Landslide Risk Assessment Based on Machine Learning Improved IVM-RF Coupling Method: A Case Study of Zhidan County, Yan'an City[J]. Bulletin of Geological Science and Technology, 2025, 44(3): 280-295.
[26]	黄成, 晏祥省, 梅红波, 周翠琼, 黄格. 基于随机森林赋权信息量模型的地质灾害易发性评价——以云南省施甸县为例[J]. 中国地质灾害与防治学报, 2025, 36(3): 151-159. HUANG Cheng, YAN Xiangsheng, MEI Hongbo, ZHOU Cuiqiong, HUANG Ge. Susceptibility Analysis of Geological Hazards Based on The Random Forest Weighted Information Value Model: A Case Study of Shidian County, Yunnan Province[J]. The Chinese Journal Of Geological Hazard And Control, 2025, 36(3): 151-159.
[27]	Angelina Ageenko, Lærke Christina Hansen, Kevin Lundholm Lyng, Lars Bodum, Jamal Jokar Arsanjani. Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study[J]. ISPRS International Journal of Geo-Information, 2022, 11(6): 324-324. doi: 10.3390/ijgi11060324
[28]	张林梵, 王佳运, 张茂省, 陈社斌, 王涛. 基于BP神经网络的区域滑坡易发性评价[J]. 西北地质, 2022, 55(2): 260-270. ZHANG Linfan, WANG Jiayun, ZHANG Maosheng, CHEN Shebin, WANG Tao. Evaluation of Regional Landslide Susceptibility Assessment Based on BP Neural Network[J]. Northwestern Geology, 2022, 55(2): 260-270.
[29]	陈航, 刘惠军, 王韬, 孙悦. 基于频率比-深度神经网络耦合模型的滑坡易发性评价——以盐源县为例[J]. 水文地质工程地质, 2024, 51(5): 161-171. CHEN Hang, LIU Huijun, WANG Tao, SUN Yue. Landslide Susceptibility Evaluation Based on FR-DNN Couplingmodel: A Case Study on Yanyuan County[J]. Hydrogeology & Engineering Geology, 2024, 51(5): 161-171.
[30]	杨强, 王高峰, 丁伟翠, 李荣建, 高幼龙, 邓兵. 多种组合模型的区域滑坡易发性及精度评价[J]. 自然灾害学报, 2021, 30(2): 36-51. YANG Qiang, WANG Gaofeng , DING Weicui, Ll Rongjian, GAO Youlong , DENG Bing. Susceptibility and Accuracy Evaluation of Regional Landslide Based on Multiple Hybrid Models[J]. Journal Of Natural Disasters, 2021, 30(2): 36-51.
[31]	陈芯宇, 师芸, 温永啸, 史瑞遥, 米晓梅. 基于确定性系数与支持向量机的滑坡易发性评价[J]. 科学技术与工程, 2023, 23(2): 518-527. CHEN Xinyu, SHI Yun, WEN Yongxiao, SHI Ruiyao, Ml Xiaomei. Landslide Susceptibility Evaluation Based on Certainty Factor and Support Vector Machines[J]. Science Technology And Engineering, 2023, 23(2): 518-527.
[32]	YANG Guang, XU Peihua, CAO Chen, ZHANAG Wen, LAN Zhiguang, CHEN Junqi, DONG Xiujun. Assessment of Regional Landslide Susceptibility Based on Combined Model of Certainty Factor Method[J]. Journal of Engineering Geology, 2019, 27(5): 1153-1163.
[33]	黄成, 邓云龙, 晏祥省, 周鑫城. 基于多模型的滑坡易发性评估研究[J]. 中国岩溶, 2024, 43(6): 1386-1397. HUANG Cheng, DENG Yunlong, YAN Xiangsheng, ZHOU Xincheng. A Study on Multiple-model Evaluation of Landslide Susceptibility[J]. Carsologica Sinica, 2024, 43(6): 1386-1397.
[34]	邓乃扬田英杰. 数据挖掘中的新方法: 支持向量机[M]. 科学出版社, 2004. DENG Naiyang, TIAN Yingjie. New Methods in Data Mining: Support Vector Machines[M]. Science Press, 2004.
[35]	PENG Ling, NIU Ruiqing, BO Huang, WU Xueling, ZHAO Yannan, YE Runqing. Landslide susceptibility mapping based on rough set theory and support vector machines: A case of the Three Gorges area, China[J]. Geomorphology, 2014, 204: 287-301. doi: 10.1016/j.geomorph.2013.08.013
[36]	张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, (1): 36-46. ZHANG Xuegong. Introduction to Statistical Learning Theory and Support Vector Machines[J]Acta Autom Atic a Sinica, 2000, (1): 36-46.
[37]	WANG Yi, FANG Zhice, WANG Mao, LING Peng, HONG Hong. Comparative Study of Landslide Susceptibility Mapping with Different Recurrent Neural Networks[J]. Computers and Geosciences, 2020, 138: 104445. doi: 10.1016/j.cageo.2020.104445
[38]	王洁, 林诚杰, 梁峰铭, 季静静, 谈松林, 刘字. 基于不同机器学习模型的滑坡易发性分析及适应性评估[J]. 科学技术与工程, 2025, 25(2): 513-520. WANG Jie , LIN Chengjie, LlANG Fengming, JI Jingjing, TAN Songlin, LlU Yu. Landslide Susceptibility Analysis and Adaptability Evaluation Basedon Different Machine Learning Models[J]. Science Technology And Engineering, 2025, 25(2): 513-520.
[39]	LIU Yanrong, MENG Zhongqiu, ZHU Lei, HU Di, HE Handong. Optimizing the Sample Selection of Machine Learning Models for Landslide Susceptibility Prediction Using Information Value Models in the Dabie Mountain Area of Anhui, China[J]. Sustainability, 2023, 15(3): 1971-1971. doi: 10.3390/su15031971
[40]	焦伟之, 张明, 谢鑫鹏, 李成文, 刘涛, 庞海松. 基于GIS与加权信息量模型的城镇地质灾害易发性评价——以大新镇为例[J]. 安全与环境工程, 2022, 29(4): 119-128. JIAO Weizhi, ZHANG Ming, XIE Xinpeng, Ll Chengwen, LIU Tao, PANG Haisong. Susceptibility Evaluation of Urban Geological Disaster Based on GIS and Weighted Information Value Model—A Case Study of Daxin Town[J]. Safety And Environmental Engineering, 2022, 29(4): 119-128.
[41]	温鑫, 范宣梅, 陈兰, 刘世康. 基于信息量模型的地质灾害易发性评价: 以川东南古蔺县为例[J]. 地质科技通报, 2022, 41(2): 290-299. WEN Xin, FAN Xuanmei, CHEN Lan, LIU Shikang. Susceptibility Assessment of Geological Disasters Based on an Information Value Model: A Case of Gulin County in Southeast Sichuan[J]. Bulletin Of Geological Science And Technology, 2022, 41(2): 290-299.