基于机器学习的滑坡易发性预测建模及其主控因子识别

黄发明; 胡松雁; 闫学涯; 李明; 王俊宇; 李文彬; 郭子正; 范文彦

doi:10.19509/j.cnki.dzkq.2021.0087

基于机器学习的滑坡易发性预测建模及其主控因子识别

doi: 10.19509/j.cnki.dzkq.2021.0087

基金项目:

国家自然科学基金项目 41807285

国家重点研发计划项目 2019YFC0605001

中国博士后基金项目 2019M652287

中国博士后基金项目 2020T130274

江西省博士后基金项目 2019KY08

详细信息

作者简介:
黄发明(1988—)，男，副教授，主要从事滑坡易发性预测研究工作。E-mail: faminghuang@ncu.edu.cn

通讯作者:
李文彬(1986—)，女，讲师，主要从事滑坡易发性建模研究工作。E-mail: 351113619004@email.ncu.edu.cn

中图分类号: P642.22
计量
- 文章访问数: 2555
- PDF下载量: 306
- 被引次数: 0
出版历程
- 收稿日期: 2021-04-08

Landslide susceptibility prediction and identification of its main environmental factors based on machine learning models

摘要

摘要: 不同机器学习预测滑坡易发性的建模过程及其不确定性有所差异, 另外如何有效识别滑坡易发性的主控因子意义重大。针对上述问题, 以支持向量机(support vector machine, 简称SVM)和随机森林(random forest, 简称RF)为例探讨了基于机器学习的滑坡易发性预测及其不确定性, 创新地提出了"权重均值法"来综合计算出更准确的滑坡主控因子。首先获取陕西省延长县滑坡编录和10类基础环境因子, 将因子频率比值作为SVM和RF的输入变量; 再将滑坡与随机选择的非滑坡样本划分为训练集和测试集, 用训练好的机器学习预测出滑坡易发性并制图; 最后用受试者工作曲线、均值和标准差等来评估建模不确定性, 并计算滑坡主控因子。结果表明: ①机器学习能有效预测出区域滑坡易发性, RF预测的滑坡易发性精度高于SVM, 而其不确定性低于SVM, 但两者的易发性分布规律整体相似; ②权重均值法计算出延长县滑坡主控因子依次是坡度、高程和岩性。实例分析和文献综述显示RF模型相较于其他机器学习模型属于可靠性较高的易发性模型。
- 滑坡易发性预测 /
- 不确定性分析 /
- 主控因子识别 /
- 支持向量机 /
- 随机森林
Abstract: The modelling processes and uncertainties of various machine learning models for landslide susceptibility prediction (LSP) are different, and effectively identifying the main conditioning factors of landslide susceptibility is of great significance. Aiming at these problems, this study aims to discuss the LSP processes and the uncertainties of landslide susceptibility based on machine learning models, namely, support vector machine (SVM) and random forest (RF), and then to innovatively propose the "weighted mean method" for calculating more accurate landslide main control factors. First, the landslide inventories and 10 basic environmental factors of Yanchang County in Shaanxi Province are obtained, and the frequency ratios (FRs) of the environmental factors are taken as the input variables of the SVM and RF models.Then, the landslide and randomly selected nonlandslide samples are divided into model training and testing datasets. Furthermore, the trained RF and SVM models are used to predict the landslide susceptibility and draw the landslide susceptibility prediction (LSP) map.Finally, the uncertainties of LSP modelling are evaluated by the receiver operating characteristic (ROC) curve, mean value and standard deviation, and the main landslide control factors are calculated.The results show that ① Machine learning models can effectively predict the susceptibility of regional landslides. The accuracy of RF in LSP is higher, and its uncertainties are lower than those of SVM. As a whole, the landslide susceptibility distribution rules of the two models are similar.②The main control factors of landslide susceptibility in Yanchang County calculated by the weighted mean method are slope, elevation and lithology.③Case studies and literature reviews show that the RF model is a more reliable susceptibility model than other types of machine learning models.
- landslide susceptibility prediction /
- uncertainties analysis /
- identification of the main control factors /
- support vector machine /
- random forest

HTML全文

图 1 机器学习模型预测滑坡易发性的流程图

Figure 1. Flowchart of the machine learning model for predicting landslide susceptibility

下载: 全尺寸图片幻灯片

图 2 研究区概况及滑坡编录

Figure 2. Overview of the study area and landslide catalog

下载: 全尺寸图片幻灯片

图 3 延长县滑坡基础环境因子(剖面曲率省略)

Figure 3. Basic environmental factors of landslide in Yanchang County

下载: 全尺寸图片幻灯片

图 4 滑坡易发性分级图

Figure 4. Classification diagram of landslide susceptibility

下载: 全尺寸图片幻灯片

图 5 RF和SVM模型预测滑坡易发性的ROC曲线

Figure 5. ROC curves of the RF and SVM models predicting landslide susceptibility

下载: 全尺寸图片幻灯片

图 6 RF和SVM模型预测滑坡易发性指数分布规律

Figure 6. Distribution rule of the RF and SVM models predicting landslide susceptibility indexes

下载: 全尺寸图片幻灯片

图 7 滑坡环境因子重要性排名

Figure 7. Importance ranking of landslide environmental factor

下载: 全尺寸图片幻灯片

图 8 滑坡环境因子平均重要性排名

Figure 8. Means importance ranking of landslide environmental factor

下载: 全尺寸图片幻灯片

表 1 各基础环境因子的属性区间分级及其频率比值

Table 1. Attribute interval and frequency ratio of each evaluation factor

基础环境因子	变量值	全区栅格/个	栅格比例/%	滑坡栅格/个	滑坡栅格比例/%	频率比
坡向/(°) (连续型)	-1	190	0.007	0	0.000	0.000
	[0, 22.5)	222 188	8.472	211	6.200	0.732
	[22.5, 67.5)	304 138	11.597	576	16.926	1.459
	[67.5, 112.5)	484 681	18.482	481	14.135	0.765
	[112.5, 157.5)	345 859	13.188	636	18.689	1.417
	[157.5, 202.5)	254 226	9.694	430	12.636	1.303
	[202.5, 247.5)	333 472	12.716	451	13.253	1.042
	[247.5, 292.5)	382 265	14.576	241	7.082	0.486
	[292.5, 337.5)	295 463	11.267	377	11.078	0.983
	[337.5, 360]	222 188	8.472	211	6.200	0.732
坡度/(°) (连续型)	[0, 6.10)	262 663	10.016	38	1.117	0.111
	[6.10, 10.45)	420 175	16.022	148	4.349	0.271
	[10.45, 14.20)	485 296	18.505	369	10.843	0.586
	[14.20, 17.55)	477 773	18.218	638	18.748	1.029
	[17.55, 20.70)	417 670	15.927	803	23.597	1.482
	[20.70, 23.86)	309 745	11.811	741	21.775	1.844
	[23.86, 27.61)	186 825	7.124	540	15.868	2.227
	[27.61, 50.29]	62 335	2.377	126	3.703	1.558
平面曲率(连续型)	[0, 9.91)	531 824	20.279	1028	30.209	1.490
	[9.91, 18.21)	536 386	20.453	938	27.564	1.348
	[18.21, 27.48)	415 938	15.860	563	16.544	1.043
	[27.48, 37.39)	298 275	11.374	338	9.932	0.873
	[37.39, 47.93)	229 817	8.763	194	5.701	0.651
	[47.93, 59.12)	188 588	7.191	154	4.525	0.629
	[59.12, 70.62)	160 843	6.133	78	2.292	0.374
	[70.62, 81.49]	260 811	9.945	110	3.232	0.325
剖面曲率(连续型)	[0, 2.46)	518 211	19.760	691	20.306	1.028
	[2.46, 4.34)	614 610	23.436	839	24.655	1.052
	[4.34, 6.33)	531 797	20.278	736	21.628	1.067
	[6.33, 8.33)	377 404	14.391	492	14.458	1.005
	[8.33, 10.44)	264 686	10.093	294	8.639	0.856
	[10.44, 12.90)	181 130	6.907	223	6.553	0.949
	[12.90, 15.95)	99 956	3.812	94	2.762	0.725
	[15.95, 29.90]	34 688	1.323	34	0.999	0.755
高程/m (连续型)	[473.14, 656.00)	65 566	2.500	0	0.000	0.000
	[656.00, 772.04)	162 922	6.213	0	0.000	0.000
	[772.04, 866.99)	282 304	10.765	336	9.874	0.917
	[866.99, 944.35)	422 849	16.124	1 078	31.678	1.965
	[944.35, 1 014.68)	552 133	21.054	1 068	31.384	1.491
	[1 014.68, 1 085.01)	551 281	21.021	605	17.778	0.846
	[1 085.01, 1 165.89)	395 921	15.097	207	6.083	0.403
	[1 165.89, 1 369.84]	189 506	7.226	109	3.203	0.443
NDVI (连续型)	[0.054, 0.161)	4 323	0.165	0	0.000	0.000
	[0.161, 0.222)	222 528	8.485	346	10.167	1.198
	[0.222, 0.248)	347 566	13.253	503	14.781	1.115
	[0.248, 0.271)	522 175	19.911	590	17.338	0.871
	[0.271, 0.290)	651 814	24.855	837	24.596	0.990
	[0.290, 0.316)	726 302	27.695	958	28.152	1.016
	[0.316, 0.514)	147 748	5.634	169	4.966	0.881
	[0.514, 0.880]	26	0.001	0	0.000	0.000
NDBI (连续型)	[0.015, 0.032)	166	0.006	0	0.000	0.000
	[0.032, 0.523)	20 500	0.782	3	0.088	0.113
	[0.523, 0.550)	144 671	5.517	263	7.728	1.401
	[0.550, 0.569)	328 825	12.539	477	14.017	1.118
	[0.569, 0.585)	461 789	17.609	517	15.192	0.863
	[0.585, 0.601)	638 451	24.345	610	17.925	0.736
	[0.601, 0.617)	636 591	24.274	816	23.979	0.988
	[0.617, 0.701]	391 489	14.928	717	21.070	1.411
MNDWI (连续型)	[0.192, 0.328)	414 411	15.802	749	22.010	1.393
	[0.328, 0.356)	732 165	27.919	866	25.448	0.912
	[0.356, 0.384)	565 063	21.547	559	16.427	0.762
	[0.384, 0.418)	421 031	16.055	479	14.076	0.877
	[0.418, 0.455)	292 549	11.155	421	12.371	1.109
	[0.455, 0.513)	192 388	7.336	329	9.668	1.318
	[0.513, 0.640)	4 737	0.181	0	0.000	0.000
	[0.640, 0.981]	138	0.005	0	0.000	0.000
总辐射(连续型)	[0, 90)	6 815	0.260	0	0.000	0.000
	[90, 170)	68 498	2.612	98	2.880	1.103
	[170, 185)	187 607	7.154	456	13.400	1.873
	[185, 198)	276 782	10.554	448	13.165	1.247
	[198, 211)	339 667	12.952	507	14.899	1.150
	[211, 225)	424 230	16.177	589	17.308	1.070
	[225, 239)	537 676	20.503	567	16.662	0.813
	[239, 255]	781 207	29.789	738	21.687	0.728
岩性(离散型)	泥岩和油页岩	179 598	6.848	0	0.000	0.000
	单独泥岩	140 332	5.351	364	10.696	1.999
	砂岩与泥岩	134 435	5.126	425	12.489	2.436
	石英砂岩	2 231	0.085	0	0.000	0.000
	风积和洪积黄土	2 165 886	82.589	2 614	76.815	0.930

下载: 导出CSV

表 2 RF和SVM模型易发性图的频率比精度分析

Table 2. Frequency ratio precision analysis of susceptibility graphs of RF and SVM models

模型	易发性等级	全区栅格/个	全区栅格比例/%	滑坡栅格/个	滑坡栅格比例/%	频率比(FR)
RF	极低	695 561	26.52	9	0.26	0.010
	低	641 183	24.45	39	1.15	0.047
	中	575 729	21.95	153	4.50	0.205
	高	428 719	16.35	478	14.05	0.859
	极高	281 290	10.73	2 724	80.05	7.463
SVM	极低	773 173	29.48	84	2.47	0.084
	低	699 525	26.67	346	10.17	0.381
	中	388 165	14.80	357	10.49	0.709
	高	337 687	12.88	568	16.69	1.296
	极高	423 932	16.17	2 048	60.18	3.723

下载: 导出CSV

参考文献(36)

[1]	郭子正, 殷坤龙, 唐扬, 等. 库水位下降及降雨作用下麻柳林滑坡稳定性评价与预测[J]. 地质科技情报, 2017, 36(4): 260-265, 270. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201704035.htm Guo Z Z, Yin K L, Tang Y, et al. Stability evaluation and prediction of maliulin landslide under reservoir water level decline and rainfall[J]. Geological Science and Technology Information, 2017, 36(4): 260-265, 270(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201704035.htm
[2]	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(2): 284-296. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201404018.htm Zhang J, Yin K L, Wang J J, et al. Evaluation of landslide susceptibility for Wanzhou district of Three Gorges Reservoir[J]. Chinese Journal of Rock Mechanics and Engineering, 2016, 35(2): 284-296(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201404018.htm
[3]	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(3): 236-243. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201903025.htm Guo T S, Zhang J Q, Han Y, et al. Evaluation of landslide susceptibility in Yanchang County based on particle swarm optimization-based support vector machine[J]. Geological Science and Technology Information, 2019, 38(3): 236-243(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201903025.htm
[4]	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(8): 1223-1232. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202008013.htm Wu X L, Yang J Y, Niu R Q. A Landslide susceptibility assessment method using SMOTE and convolutional neural network[J]. Geomatics and Information Science of Wuhan University, 2020, 45(8): 1223-1232(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202008013.htm
[5]	Dou J, Yunus A P, Bui D T, et al. Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan[J]. Science of the Total Environment, 2019, 662: 332-346. doi: 10.1016/j.scitotenv.2019.01.221
[6]	Tsangaratos P, Ilia I, Hong H Y, et al. Applying information theory and GIS-based quantitative methods to produce landslide susceptibility maps in Nancheng County, China[J]. Landslides, 2017, 14(3): 1091-1111. doi: 10.1007/s10346-016-0769-4
[7]	Reichenbach P, Rossi M, Malamud B D, et al. A review of statistically-based landslide susceptibility models[J]. Earth-Science Reviews, 2018, 180: 60-91. doi: 10.1016/j.earscirev.2018.03.001
[8]	Zezere 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. doi: 10.1016/j.scitotenv.2017.02.188
[9]	Zhu L, Huang L H, Fan L Y, et al. Landslide susceptibility prediction modeling based on remote sensing and a novel deep learning algorithm of a cascade-parallel recurrent neural network[J]. Sensors, 2020, 20(6): 1576. doi: 10.3390/s20061576
[10]	Chen W, Chen X, Peng J B, et al. Landslide susceptibility modeling based on ANFIS with teaching-learning-based optimization and satin bowerbird optimizer[J]. Geoscience Frontiers, 2021, 12(1): 93-107. doi: 10.1016/j.gsf.2020.07.012
[11]	Bui D T, Tsangaratos P, Nguyen V T, et al. Comparing the prediction performance of a Deep Learning Neural Network model with conventional machine learning models in landslide susceptibility assessment[J]. Catena, 2020, 188: 104426. doi: 10.1016/j.catena.2019.104426
[12]	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(2): 113-121. doi: 10.19509/j.cnki.dzkq.2020.0212 Hu T, Fan X, Wang S, et al. Landslide susceptibility evaluation of Sinan County using logistics regression model and 3S technology[J]. Bulletin of Geological Science and Technology, 2020, 39(2): 113-121(in Chinese with English abstract). doi: 10.19509/j.cnki.dzkq.2020.0212
[13]	冯杭建, 周爱国, 俞剑君, 等. 浙西梅雨滑坡易发性评价模型对比[J]. 地球科学: 中国地质大学学报, 2016, 41(3): 403-415. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX201603006.htm Feng H J, Zhou A G, Yu J J, et al. A Comparative study on plum-rain-triggered landslide susceptibility assessment models in west Zhejiang Province[J]. Earth Science: Journal of China University of Geosciences, 2016, 41(3): 403-415(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX201603006.htm
[14]	Li D Y, Huang F M, Yan L X, et al. Landslide susceptibility prediction using particle-swarm-optimized multilayer perceptron: Comparisons with multilayer-perceptron-only, BP neural network, and information value models[J]. Applied Sciences, 2019, 9(18): 3664. doi: 10.3390/app9183664
[15]	Merghadi A, Yunus A P, Dou J, et al. Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance[J]. Earth-Science Reviews, 2020, 7(20): 10325.
[16]	郭子正, 殷坤龙, 付圣, 等. 基于GIS与WOE-BP模型的滑坡易发性评价[J]. 地球科学, 2019, 44(12): 4299-4312. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX201912040.htm Guo Z Z, Yin K L, Fu S, et al. Evaluation of landslide susceptibility based on GIS and WOE-BP model[J]. Earth Science, 2019, 44(12): 4299-4312(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX201912040.htm
[17]	Huang F M, Cao Z S, Jiang S H, et al. Landslide susceptibility prediction based on a semi-supervised multiple-layer perceptron model[J]. Landslides, 2020, 17(12): 2919-2930. doi: 10.1007/s10346-020-01473-9
[18]	马瑶, 赵江南. 机器学习方法在矿产资源定量预测应用研究进展[J]. 地质科技通报, 2021, 40(1): 132-141. doi: 10.19509/j.cnki.dzkq.2021.0108 Ma Y, Zhao J N. Advances in the application of machine learning methods in mineral prospectivity mapping[J]. Bulletin of Geological Science and Technology, 2021, 40(1): 132-141(in Chinese with English abstract). doi: 10.19509/j.cnki.dzkq.2021.0108
[19]	黄发明, 殷坤龙, 张桂荣, 等. 基于相空间重构和小波分析-粒子群向量机的滑坡地下水位预测[J]. 地球科学: 中国地质大学学报, 2015, 40(7): 1254-1265. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX201507013.htm Huang F M, Yin K L, Zhang G R, et al. Landslide groundwater level time series prediction based on phase space reconstruction and wavelet analysis-support vector machine optimized by PSO algorithm[J]. Earth Science: Journal of China University of Geosciences, 2015, 40(7): 1254-1265(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX201507013.htm
[20]	Huang F M, Yin K L, Zhang G R, et al. Prediction of groundwater level in landslide using multivariable PSO-SVM model[J]. Journal of Zhejiang University: Engineering Science Edition, 2015, 49(6): 1193-1200.
[21]	杨永刚, 殷坤龙, 赵海燕, 等. 基于C5.0决策树-快速聚类模型的万州区库岸段乡镇滑坡易发性区划[J]. 地质科技情报, 2019, 38(6): 189-197. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201906023.htm Yang Y G, Yin K L, Zhao H Y, et al. Landslide susceptibility evaluation for township units of bank section in Wanzhou district based on C5.0 decision tree and K-means cluster model[J]. Geological Science and Technology Information, 2019, 38(6): 189-197(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201906023.htm
[22]	吴润泽, 胡旭东, 梅红波, 等. 基于随机森林的滑坡空间易发性评价: 以三峡库区湖北段为例[J]. 地球科学, 2021, 46(1): 321-330. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202101025.htm Wu R Z, Hu X D, Mei H B, et al. Spatial susceptibility assessment of landslides based on random forest: A case study from Hubei section in the Three Gorges Reservoir area[J]. Earth Science, 2021, 46(1): 321-330(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202101025.htm
[23]	张书豪, 吴光. 随机森林与GIS的泥石流易发性及可靠性[J]. 地球科学, 2019, 44(9): 3115-3134. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX201909025.htm Zhang S H, Wu G. Debris flow susceptibility and its reliability based on random forest and GIS[J]. Earth Science, 2019, 44(9): 3115-3134(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX201909025.htm
[24]	Ahmed B. Landslide susceptibility mapping using multi-criteria evaluation techniques in Chittagong metropolitan area, Bangladesh[J]. Landslides, 2015, 12(6): 1077-1095.
[25]	Chang Z L, Du Z, Zhang F, et al. Landslide susceptibility prediction based on remote sensing images and GIS: Comparisons of supervised and unsupervised machine learning models[J]. Remote Sensing, 2020, 12(3): 502.
[26]	Huang Y, Zhao L. Review on landslide susceptibility mapping using support vector machines[J]. Catena, 2018, 165: 520-529.
[27]	Luo X G, Lin F K, Chen Y H, et al. Coupling logistic model tree and random subspace to predict the landslide susceptibility areas with considering the uncertainty of environmental features[J]. Scientific Reports, 2019, 9(1): 15369.
[28]	赵忠国, 张峰, 郑江华. 多元自适应回归样条法的滑坡敏感性评价[J]. 武汉大学学报: 信息科学版, 2021, 46(3): 442-450. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202103018.htm Zhao Z G, Zhang F, Zheng J H. Evaluation of landslide susceptibility by multiple adaptive regression spline method[J]. Geomatics and Information Science of Wuhan University, 2021, 46(3): 442-450(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202103018.htm
[29]	屈新星, 李道安, 何云玲, 等. 基于MaxEnt模型的滑坡易发性评价: 以攀枝花市为例[J]. 水土保持研究, 2021, 28(2): 224-229. https://www.cnki.com.cn/Article/CJFDTOTAL-STBY202102034.htm Qu X X, Li D A, He Y L, et al. Evaluation of landslide susceptibility based on MaxEnt model: Taking Panzhihua City as an example[J]. Research of Soil and Water Conservation, 2021, 28(2): 224-229(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-STBY202102034.htm
[30]	Chang M, Zhou Y, Zhou C, et al. Coseismic landslides induced by the 2018 Mw 6.6 Iburi, Japan, Earthquake: Spatial distribution, key factors weight, and susceptibility regionalization[J]. Landslides, 2021, 18(2): 755-772.
[31]	Huang F M, Chen J W, Du Z, et al. Landslide susceptibility prediction considering regional soil erosion based on machine-learning models[J]. ISPRS International Journal of Geo-Information, 2020, 9(6): 377.
[32]	张玘恺, 凌斯祥, 李晓宁, 等. 九寨沟县滑坡灾害易发性快速评估模型对比研究[J]. 岩石力学与工程学报, 2020, 39(8): 1595-1610. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX202008009.htm Zhang Q K, Ling S X, Li X N, et al. Comparison of landslide susceptibility mapping rapid assessment models in Jiuzhaigou County, Sichuan Province, China[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(8): 1595-1610(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX202008009.htm
[33]	Huang F M, Wang Y, Dong Z L, et al. Regional landslide susceptibility mapping based on grey relational degree model[J]. Earth Science, 2019, 44(2): 664-676.
[34]	Liu W P, Luo X Y, Huang F M, et al. Prediction of soil water retention curve using Bayesian updating from limited measurement data[J]. Applied Mathematical Modelling, 2019, 76: 380-395.
[35]	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(7): 1085-1091. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201807017.htm Liu J, Li S L, Chen T. Landslide susceptibility assesment based on optimized random forest model[J]. Geomatics and Information Science of Wuhan University, 2018, 43(7): 1085-1091(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201807017.htm
[36]	Park S, Kim J. Landslide susceptibility mapping based on random forest and boosted regression tree models, and a comparison of their performance[J]. Applied Sciences, 2019, 9(5): 942.