基于环境因子优化TSES法选择负样本及其在滑坡易发性评价中的应用

崔玉龙; 朱路路; 徐敏; 缪海波

doi:10.19509/j.cnki.dzkq.tb20230400

基于环境因子优化TSES法选择负样本及其在滑坡易发性评价中的应用

doi: 10.19509/j.cnki.dzkq.tb20230400

安徽理工大学土木建筑学院, 安徽淮南 232001

基金项目:

国家自然科学基金项目 42277136

安徽省高校自然科学优秀青年科研项目 2023AH030041

详细信息

通讯作者:
崔玉龙，E-mail：ylcui@aust.edu.cn

中图分类号: P642.22
计量
- 文章访问数: 308
- PDF下载量: 27
- 被引次数: 0
出版历程
- 收稿日期: 2023-07-14
- 录用日期: 2023-09-08
- 修回日期: 2023-09-07

Optimizing TSES method based on the environmental factors to select negative samples and its application in landslide susceptibility evaluation

School of Civil Engineering and Architecture, Anhui University of Science and Technology, Huainan Anhui 232001, China

More Information

Corresponding author: CUI Yulong, E-mail: ylcui@aust.edu.cn

摘要

摘要:
滑坡易发性评价是滑坡灾害防治的重要手段之一, 而不合理的滑坡负样本会影响滑坡易发性评价, 从而影响到滑坡灾害的防治, 因此提供一种合理的负样本选取方法变得尤为关键。以西藏米林市的古滑坡为例, 选择高程、坡度、坡向、坡位、距道路距离、距断层距离、距水系距离、地形起伏度、地层岩性、土地利用类型10类环境因子, 使用Relief算法计算环境因子的贡献值并依据贡献值优化选择环境因子; 基于环境因子优化的目标空间外向化采样法(target space exteriorization sampling, 简称TSES)选择负样本, 作为性能优异的随机森林模型的输入变量; 之后结合优化的环境因子和正或负样本预测米林市的滑坡易发性, 并用混淆矩阵和ROC曲线评价构建模型的性能。为检验环境因子优化的TSES法的有效性和先进性, 采用耦合信息量法和TSES法选择滑坡负样本并构建随机森林模型, 与环境因子优化的TSES法构建的随机森林模型进行对比研究。结果表明, 环境因子优化的TSES法构建的随机森林模型的评价效果较好, 其ACC为93.7%、AUC为0.987, 均高于耦合信息量、TSES法构成的模型。环境因子优化的TSES法能够提高模型的精度, 解决多因子作为约束条件取样中因子选取的问题, 为滑坡易发性评价采集负样本提供了新的思路。
- 滑坡易发性评价 /
- Relief算法 /
- 负样本 /
- 环境因子优化TSES法 /
- 随机森林 /
- 古滑坡
Abstract: Objective
Landslide susceptibility evaluation is an important means for landslide disaster prevention and control. Unreasonable negative landslide samples will affect landslide susceptibility evaluation, thereby affecting landslide disaster prevention and control. Therefore, it is particularly critical to provide a reasonable negative sample selection method.
Methods
In view of the selection of negative landslide samples, the ancient landslides in Milin City, Xizang are taken as an example, and 10 environmental factors, including elevation, slope, slope aspect, slope position, distance to road, distance to fault, distance to water system, topographic relief, lithology and land use type, are selected. The Relief algorithm is used to calculate the contribution values of environmental factors and to select the optimized environmental factors. The target space exteriorization sampling (TSES) method based on the optimization of environmental factors is applied to select negative samples as the input variables of the random forest (RF)model with excellent performance.Then, the optimized environmental factors and positive/negative samples are combined to predict the landslide susceptibility of Milin city, and the confusion matrix and receiver operating characteristic (ROC) curve are used to evaluate the prediction performance.To test the effectiveness and advancement of the TSES method optimized by environmental factors, the coupled information method and TSES method are respectively used to select negative landslide samples and constructs RF models to conduct comparative research with the RF model constructed by the TSES method optimized by environmental factors.
Results
The results show that the evaluation effect of the RF model constructed by the optimized TSES method based on environmental factors is better with an ACC value of 93.7% and an AUC value of 0.987, both of which are greater than those of the RF models constructed by the coupling information method and the TSES method.
Conclusion
The TSES optimized by environmental factors can improve the accuracy of the RF model, solve the problems of environmental factor selection in multifactor constrained sampling, and provide a new approach to collect negative landslide samples for landslide susceptibility evaluation.
- landslide susceptibility evaluation /
- Relief algorithm /
- negative sample /
- TSES method based on the optimixation of environmental factor /
- random forest /
- ancient landslide
注释:

所有作者声明不存在利益冲突。

HTML全文

图 1 技术路线图

Figure 1. Technology roadmap

下载: 全尺寸图片幻灯片

图 2 目标空间外向化采样法

Figure 2. Target space exteriorization sampling method

下载: 全尺寸图片幻灯片

图 3 研究区地理位置

Figure 3. Geographical location of the study area

下载: 全尺寸图片幻灯片

图 4 滑坡解译实例

a.沿江的大型岩质滑坡；b.由风化引起的岩质滑坡；c.解译滑坡分布图

Figure 4. Examples of landslide interpretation

下载: 全尺寸图片幻灯片

图 5 影响因子分类

a.高程；b.坡度；c.坡向；d.坡位；e.距道路距离；f.距断层距离；g.距水系距离；h.地形起伏度；i.地层岩性；j.土地利用类型

Figure 5. Classification of influencing factors

下载: 全尺寸图片幻灯片

图 6 影响因子贡献值

Figure 6. Contribution values of influencing factors

下载: 全尺寸图片幻灯片

图 7 3种采集负样本方法构成随机森林易发图

a.耦合信息量法；b.TSES法；c.环境因子优化TSES法

Figure 7. Landslide susceptibility maps of random forest model by using three negative samples collecting methods

下载: 全尺寸图片幻灯片

图 8 3种采集负样本方法构成随机森林的ROC曲线

Figure 8. ROC curves of random forest model using three negative samples collecting methods

下载: 全尺寸图片幻灯片

表 1 影响因子数据来源

Table 1. Data sources of influencing factors

影响因子	数据名称	数据来源
高程、坡度、坡向、距水系距离、地形起伏度	12.5 m分辨率的ALOS数字高程模型(DEM)	http://wwwearthdate.org
坡位	地理空间数据云	https://www.gscloud.cn
距道路距离	全球地理信息资源目录服务系统	https://www.webmap.cn
距断层距离	中国活动构造图(1∶400万)
土地利用类型	鹏城实验室	https://data.ess.tsinghua.edu.cn
地层岩性	中国地质调查局公开的1∶50万中国地质图	http://www.ngac.org.cn

下载: 导出CSV

表 2 随机森林模型的混淆矩阵

Table 2. Confusion matrix of random forests model

模型种类	是否为滑坡(实际)	是否为滑坡(预测)		准确率ACC/%
模型种类	是否为滑坡(实际)	是	否	准确率ACC/%
耦合信息量法	是	340	72	88.1
随机森林模型	否	26	386	88.1
TSES法随机	是	365	47	79.4
森林模型	否	123	289	79.4
环境因子优化的	是	406	6	93.7
TSES法随机森林模型	否	46	366	93.7

下载: 导出CSV

参考文献(26)

[1]	许强, 汤明高, 徐开祥, 等. 滑坡时空演化规律及预警预报研究[J]. 岩石力学与工程学报, 2008, 27(6): 1104-1112. doi: 10.3321/j.issn:1000-6915.2008.06.003 XU Q, TANG M G, XU K X, et al. Research on space-time evolution laws and early warning-prediction of landslides[J]. Chinese Journal of Rock Mechanics and Engineering, 2008, 27(6): 1104-1112. (in Chinese with English abstract) doi: 10.3321/j.issn:1000-6915.2008.06.003
[2]	李文彦, 王喜乐. 频率比与信息量模型在黄土沟壑区滑坡易发性评价中的应用与比较[J]. 自然灾害学报, 2020, 29(4): 213-220. https://www.cnki.com.cn/Article/CJFDTOTAL-ZRZH202004022.htm LI W Y, WANG X L. Application and comparison of frequency ratio and information value model for evaluating landslide susceptibility of loess gully region[J]. Journal of Natural Disasters, 2020, 29(4): 213-220. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-ZRZH202004022.htm
[3]	许冲, 戴福初, 姚鑫, 等. 基于GIS的汶川地震滑坡灾害影响因子确定性系数分析[J]. 岩石力学与工程学报, 2010, 29(增刊1): 2972-2981. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX2010S1057.htm XU C, DAI F C, YAO X, et al. Analysis of deterministic coefficient of influencing factors of Wenchuan earthquake landslide disaster based on GIS[J]. Chinese Journal of Rock Mechanics and Engineering, 2010, 29(S1): 2972-2981. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX2010S1057.htm
[4]	杜国梁, 张永双, 高金川, 等. 基于GIS的白龙江流域甘肃段滑坡易发性评价[J]. 地质力学学报, 2016, 22(1): 1-11. doi: 10.3969/j.issn.1006-6616.2016.01.001 DU G L, ZHANG Y S, GAO J C, et al. Landslide susceptibility assessment based on GIS in Bailongjiang watershed, Gansu Province[J]. Journal of Geomechanics, 2016, 22(1): 1-11. (in Chinese with English abstract) doi: 10.3969/j.issn.1006-6616.2016.01.001
[5]	仉文岗, 何昱苇, 王鲁琦, 等. 基于水系分区的滑坡易发性机器学习分析方法: 以重庆市奉节县为例[J]. 地球科学, 2023, 48(5): 2024-2038. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202305028.htm ZHANG W G, HE Y W, WANG L Q, et al. Machine learning solution for landslide susceptibility based on hydrographic division: Case study of Fengjie County in Chongqing[J]. Earth Science, 2023, 48(5): 2024-2038. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202305028.htm
[6]	黄发明, 潘李含, 姚池, 等. 基于半监督机器学习的滑坡易发性预测建模[J]. 浙江大学学报(工学版), 2021, 55(9): 1705-1713. https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC202109012.htm HUANG F M, PAN L H, YAO C, et al. Landslide susceptibility prediction modelling based on semi-supervised machine learning[J]. Journal of Zhejiang University (Engineering Science), 2021, 55(9): 1705-1713. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC202109012.htm
[7]	黄发明, 陈彬, 毛达雄, 等. 基于自筛选深度学习的滑坡易发性预测建模及其可解释性[J]. 地球科学, 2023, 48(5): 1696-1710. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202305003.htm HUANG F M, CHEN B, MAO D X, et al. Landslide susceptibility prediction modeling and interpretability based on self-screening deep learning model[J]. Earth Science, 2023, 48(5): 1696-1710. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202305003.htm
[8]	刘艳辉, 方然可, 苏永超, 等. 基于机器学习的区域滑坡灾害预警模型研究[J]. 工程地质学报, 2021, 29(1): 116-124. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ202101013.htm LIU Y H, FANG R K, SU Y C, et al. Machine learning based model for warning of regional landslide disasters[J]. Journal of Engineering Geology, 2021, 29(1): 116-124. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ202101013.htm
[9]	CUI Y L, HU J H, ZHENG J, et al. Susceptibility assessment of landslides caused by snowmelt in a typical loess area in the Yining County, Xinjiang, China[J]. Quarterly Journal of Engineering Geology and Hydrogeology, 2022, 55(1): qjegh2021-024.
[10]	LUCCHESE L V, DE OLIVEIRA G G, PEDROLLO O C. Investigation of the influence of nonoccurrence sampling on landslide susceptibility assessment using Artificial Neural Networks[J]. CATENA, 2021, 198: 105067. doi: 10.1016/j.catena.2020.105067
[11]	刘纪平, 梁恩婕, 徐胜华, 等. 顾及样本优化选择的多核支持向量机滑坡灾害易发性分析评价[J]. 测绘学报, 2022, 51(10): 2034-2045. doi: 10.11947/j.AGCS.2022.20220326 LIU J P, LIANG E J, XU S H, et al. Multi-kernel support vector machine considering sample optimization selection for analysis and evaluation of landslide disaster susceptibility[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(10): 2034-2045. (in Chinese with English abstract) doi: 10.11947/j.AGCS.2022.20220326
[12]	周晓亭, 黄发明, 吴伟成, 等. 基于耦合信息量法选择负样本的区域滑坡易发性预测[J]. 工程科学与技术, 2022, 54(3): 25-35. https://www.cnki.com.cn/Article/CJFDTOTAL-SCLH202203003.htm ZHOU X T, HUANG F M, WU W C, et al. Regional landslide susceptibility prediction based on negative sample selected by coupling information value method[J]. Advanced Engineering Sciences, 2022, 54(3): 25-35. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-SCLH202203003.htm
[13]	LIU S L, WANG L Q, ZHANG W G, et al. A physics-informed data-driven model for landslide susceptibility assessment in the Three Gorges Reservoir Area[J]. Geoscience Frontiers, 2023, 14(5): 101621. doi: 10.1016/j.gsf.2023.101621
[14]	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(3): 425-439. doi: 10.1007/s10346-013-0391-7
[15]	缪亚敏, 朱阿兴, 杨琳, 等. 滑坡危险度制图中一种新型的负样本采样方法[J]. 地理与地理信息科学, 2016, 32(4): 61-67. doi: 10.3969/j.issn.1672-0504.2016.04.011 MIAO Y M, ZHU A X, YANG L, et al. A new method of pseudo absence data generation in landslide susceptibility mapping[J]. Geography and Geo-Information Science, 2016, 32(4): 61-67. (in Chinese with English abstract) doi: 10.3969/j.issn.1672-0504.2016.04.011
[16]	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
[17]	黄发明, 胡松雁, 闫学涯, 等. 基于机器学习的滑坡易发性预测建模及其主控因子识别[J]. 地质科技通报, 2022, 41(2): 79-90. doi: 10.19509/j.cnki.dzkq.2021.0087 HUANG F M, HU S Y, YAN X Y, et al. Landslide susceptibility prediction and identification of its main environmental factors based on machine learning models[J]. Bulletin of Geological Science and Technology, 2022, 41(2): 79-90. (in Chinese with English abstract) doi: 10.19509/j.cnki.dzkq.2021.0087
[18]	杨灿, 刘磊磊, 张遗立, 等. 基于贝叶斯优化机器学习超参数的滑坡易发性评价[J]. 地质科技通报, 2022, 41(2): 228-238. doi: 10.19509/j.cnki.dzkq.2022.0059 YANG C, LIU L L, ZHANG Y L, et al. Machine learning based on landslide susceptibility assessment with Bayesian optimized the hyperparameters[J]. Bulletin of Geological Science and Technology, 2022, 41(2): 228-238. (in Chinese with English abstract) doi: 10.19509/j.cnki.dzkq.2022.0059
[19]	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(5): 1711-1729. https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202305004.htm KONG J X, ZHUANG J Q, PENG J B, et al. Evaluation of landslide susceptibility in Chinese Loess Plateau based on IV-RF and IV-CNN coupling models[J]. Earth Science, 2023, 48(5): 1711-1729. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-DQKX202305004.htm
[20]	CAI H M, NG M. Feature weighting by RELIEF based on local hyperplane approximation[C]//Anon. Advances in Knowledge Discovery and Data Mining. Berlin, Heidelberg: Springer, 2012: 335-346.
[21]	KIRA K, RENDELL L A. The feature selection problem: Traditional methods and a new algorithm[C]//Anon. Proceedings of the Tenth National Conference on Artificial Intelligence. America, California: Aaai, 1992: 129-134.
[22]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45: 5-32. doi: 10.1023/A:1010933404324
[23]	杨硕, 李德营, 严亮轩, 等. 基于随机森林模型的乌江高陡岸坡滑坡地质灾害易发性评价[J]. 安全与环境工程, 2021, 28(4): 131-138. https://www.cnki.com.cn/Article/CJFDTOTAL-KTAQ202104019.htm YANG S, LI D Y, YAN L X, et al. Landslide susceptibility assessment in high and steep bank slopes along Wujiang River based on random forest model[J]. Safety and Environmental Engineering, 2021, 28(4): 131-138. (in Chinese with English abstract) https://www.cnki.com.cn/Article/CJFDTOTAL-KTAQ202104019.htm
[24]	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(6): 131-144. doi: 10.19509/j.cnki.dzkq.2020.0616 ZHENG Y K, CHEN J G, WANG C B, et al. Application of certainty factor and random forests model in landslide susceptibility evaluation in Mangshi City, Yunnan Province[J]. Bulletin of Geological Science and Technology, 2020, 39(6): 131-144. (in Chinese with English abstract) doi: 10.19509/j.cnki.dzkq.2020.0616
[25]	王珂, 郭长宝, 马施民, 等. 基于证据权模型的川西鲜水河断裂带滑坡易发性评价[J]. 现代地质, 2016, 30(3): 705-715. doi: 10.3969/j.issn.1000-8527.2016.03.022 WANG K, GUO C B, MA S M, et al. Landslide susceptibility evaluation based on weight-of-evidence modeling in the Xianshuihe fault zone, East Tibetan Plateau[J]. Geoscience, 2016, 30(3): 705-715. (in Chinese with English abstract) doi: 10.3969/j.issn.1000-8527.2016.03.022
[26]	DU G L, ZHANG Y S, YANG Z H, et al. Estimation of seismic landslide hazard in the eastern Himalayan syntaxis region of Tibetan Plateau[J]. Acta Geologica Sinica-English Edition, 2017, 91(2): 658-668. doi: 10.1111/1755-6724.13124