基于XGBoost和云模型的地质灾害易发性评价

张威; 胡舫瑞; 綦巍; 彭琳; 王咏林; 陈枫

doi:10.16031/j.cnki.issn.1003-8035.202210041

基于XGBoost和云模型的地质灾害易发性评价

doi: 10.16031/j.cnki.issn.1003-8035.202210041

辽宁省自然资源事务服务中心，辽宁沈阳　110044

详细信息

作者简介:
张威：张　威（1982-），男，辽宁丹东人，本科，高级工程师，主要从事自然灾害风险方面的研究。E-mail：5869365@qq.com

通讯作者:
胡舫瑞（1988-），男，辽宁营口人，硕士，工程师，主要从事地质灾害风险评价与管理方面的研究。E-mail：hufrcug@163.com

中图分类号: P642.22
计量
- 文章访问数: 730
- HTML全文浏览量: 164
- PDF下载量: 20
- 被引次数: 0
出版历程
- 收稿日期: 2022-09-25
- 录用日期: 2023-08-23
- 修回日期: 2023-07-17
- 网络出版日期: 2023-08-30

Susceptibility assessment of geological hazard based on XGBoost and cloud model

Liaoning Province Natural Resources Affairs Service Center, Shenyang, Liaoning　110044, China

摘要

摘要: 传统地质灾害易发性评价中，存在着易发性因子权重选取主观性强、因子分级具有随机性和模糊性的问题。采用单一评价模型只能对地质灾害的易发性进行定性评估，无法定量化评价。针对这一问题，文章基于改进集成算法（XGBoost）和云模型，在朝阳市189个灾害隐患点中选择坡度、气象条件、归一化植被指数、高程等12个易发性因子，通过XGBoost分类算法确定了易发性因子权重，拟合准确率为96.5%，达到了较高的精度。在此基础上利用云模型将因子分级的模糊性问题转化为定量问题，建立了朝阳市地质灾害易发性评价指标体系，进而评价地质灾害的易发性。以朝阳市大东山为评价单元对该评价体系进行验证。结果表明该评价单元的易发程度为高易发，与实际情况吻合。文章提出的方法可对地质灾害易发性评价提供参考。
- XGBoost /
- 易发性因子权重 /
- 云模型 /
- 易发性评价 /
- 地质灾害
Abstract: In the conventional process of geological hazard assessment, issues such as subjectivity in selecting susceptibility factor weights, randomness, and fuzziness in factor grading are prevalent. The application of a single assessment model can only provide qualitative evaluation of geological hazard susceptibility, lacking quantitative analysis. To overcome these challenges, this study employs an enhanced integrated algorithm (XGBoost) and cloud model. Among 189 disaster potential points in Chaoyang City, twelve susceptibility factors including slope, meteorological conditions, vegetation coverage and elevation were selected. The XGBoost classification algorithm was used to determine susceptibility factor weights. The results showed that the algorithm classification achieved high performance with fitting accuracy of 96.5%. On this basis, the cloud model was employed to transform the fuzzy factor grading into a quantitative problem, establishing a susceptibility evaluation index system for geological hazards in Chaoyang City, thereby assessing their susceptibility. To validate the evaluation index system, the Dadongshan landslide in Chaoyang City was selected as the assessment unit. Results indicate a high susceptibility level for this evaluation unit, consistent with actual conditions. The methodology proposed in this study is promising and can offers reference for evaluating geological hazard susceptibility.
- XGBoost /
- susceptibility factor weights /
- cloud model /
- susceptibility assessment /
- geological disaster

HTML全文

图 1 云模型示意图

Figure 1. Schematic diagram of cloud model

下载: 全尺寸图片幻灯片

图 2 朝阳市地质情况区位图

Figure 2. Location map of the study area

下载: 全尺寸图片幻灯片

图 3 地质灾害易发性因子与地质灾害点关系图

Figure 3. The relationship between geological hazard susceptibility factors and disaster points

下载: 全尺寸图片幻灯片

图 4 易发性因子相关性图

Figure 4. Correlation diagram of susceptibility factors

下载: 全尺寸图片幻灯片

图 5 易发性因子数据分布图

Figure 5. Data distribution of susceptibility factors

下载: 全尺寸图片幻灯片

图 6 样本与总体ROC曲线及P-R曲线

Figure 6. ROC curve and P-R curve for sample and overall population

下载: 全尺寸图片幻灯片

图 7 易发性因子权重分数图

Figure 7. Weighted scores of susceptibility factors

下载: 全尺寸图片幻灯片

图 8 评价指标云图

Figure 8. Cloud map of evaluation indicators

下载: 全尺寸图片幻灯片

图 9 大东山滑坡正射影像

Figure 9. Orthophoto image of Dadongshan landslide

下载: 全尺寸图片幻灯片

图 10 总体评估等级云相似度图

Figure 10. Cloud similarity graph of overall evaluation grades

下载: 全尺寸图片幻灯片

表 1 影响因子权重表

Table 1. Weight table of impact factors

序号	易发性因子	权重
1	坡度	0.169
2	气象条件	0.151
3	归一化植被指数	0.136
4	高程	0.133
5	人口密度	0.122
6	坡向	0.115
7	水文条件	0.053
8	公路距离	0.042
9	工程地质条件	0.029
10	断裂距离	0.028
11	水系距离	0.017
12	铁路距离	0.006

下载: 导出CSV

表 2 影响因子分级表

Table 2. Grading table of impact factors

序号	易发性因子	分级
1	坡度	{平台，缓坡，陡坡，悬崖}
2	气象条件	{好，较好，较差，差}
3	归一化植被指数	{好，中等，较差，差}
4	高程	{平原，低丘，高丘，低山}
5	人口密度	{好，较好，较差，差}
6	坡向/（°）	{45 ～ 135，315 ～ 45， 135 ～ 225，225 ～ 315}
7	水文条件	{富水性差，富水性较差，富水性较好，富水性好}
8	公路距离	{远，较远，较近，近}
9	工程地质条件	{碎屑岩类，花岗杂岩类、碳酸岩类，其它岩浆岩岩类，第四系松散土类、花岗岩类、片麻杂岩类}
10	断裂距离	{远，较远，较近，近}
11	水系距离	{远，较远，较近，近}
12	铁路距离	{远，较远，较近，近}

下载: 导出CSV

表 3 大东山滑坡影响因子云模型评价值

Table 3. Cloud model Evaluation values of impact factors for Dadongshan landslide

序号	易发性因子	影响因子云模型评价值
1	坡度	（6.91，1.270，0.1）
2	气象条件	（6.91，1.270，0.1）
3	归一化植被指数	（10.00，1.031，0.1）
4	高程	（10.00，1.031，0.1）
5	人口密度	（10.00，1.031，0.1）
6	坡向	（10.00，1.031，0.1）
7	水文条件	（10.00，1.031，0.1）
8	公路距离	（3.09，1.270，0.1）
9	工程地质条件	（10.00，1.031，0.1）
10	断裂距离	（10.00，1.031，0.1）
11	水系距离	（3.09，1.270，0.1）
12	铁路距离	（3.09，1.270，0.1）

下载: 导出CSV

表 4 总体评估等级云相似度表

Table 4. Cloud similarity table of overall evaluation grades

云相似度	高易发	中易发	低易发	不易发
大东山滑坡	0.9990	0.9970	0.9660	0.1319

下载: 导出CSV

参考文献(25)

[1]	牛瑞卿,彭令,叶润青,等. 基于粗糙集的支持向量机滑坡易发性评价[J]. 吉林大学学报(地球科学版),2012,42(2):430 − 439. [NIU Ruiqing,PENG Ling,YE Runqing,et al. Landslide susceptibility assessment based on rough sets and support vector machine[J]. Journal of Jilin University (Earth Science Edition),2012,42(2):430 − 439. (in Chinese with English abstract) NIU Ruiqing, PENG Ling, YE Runqing, et al. Landslide susceptibility assessment based on rough sets and support vector machine[J]. Journal of Jilin University （Earth Science Edition）, 2012, 42（2）: 430 − 439. （in Chinese with English abstract）
[2]	MOHAMMADY M,POURGHASEMI H R,PRADHAN B. Landslide susceptibility mapping at Golestan Province,Iran:A comparison between frequency ratio,dempster-shafer,and weights-of-evidence models[J]. Journal of Asian Earth Sciences,2012,61:221 − 236. doi: 10.1016/j.jseaes.2012.10.005
[3]	易靖松,王峰,程英建,等. 高山峡谷区地质灾害危险性评价——以四川省阿坝县为例[J]. 中国地质灾害与防治学报,2022,33(3):134 − 142. [YI Jingsong,WANG Feng,CHENG Yingjian,et al. Study on the risk assessment of geological disasters in alpine valley area:A case study in Aba County,Sichuan Province[J]. The Chinese Journal of Geological Hazard and Control,2022,33(3):134 − 142. (in Chinese with English abstract) YI Jingsong, WANG Feng, CHENG Yingjian, et al. Study on the risk assessment of geological disasters in alpine valley area: A case study in Aba County, Sichuan Province[J]. The Chinese Journal of Geological Hazard and Control, 2022, 33（3）: 134 − 142. （in Chinese with English abstract）
[4]	黄艳婷,郭永刚. 考虑降雨敏感度的泥石流危险性评价——以藏东南地区为例[J]. 中国地质灾害与防治学报,2023,34(1):129 − 138. [HUANG Yanting,GUO Yonggang. Debris flow risk assessment considering rainfall sensitivity:A case study of southeast Tibet[J]. The Chinese Journal of Geological Hazard and Control,2023,34(1):129 − 138. (in Chinese with English abstract) HUANG Yanting, GUO Yonggang. Debris flow risk assessment considering rainfall sensitivity: A case study of southeast Tibet[J]. The Chinese Journal of Geological Hazard and Control, 2023, 34（1）: 129 − 138. （in Chinese with English abstract）
[5]	许冲,戴福初,徐素宁,等. 基于逻辑回归模型的汶川地震滑坡危险性评价与检验[J]. 水文地质工程地质,2013,40(3):98 − 104. [XU Chong,DAI Fuchu,XU Suning,et al. Application of logistic regression model on the Wenchuan earthquake triggered landslide hazard mapping and its validation[J]. Hydrogeology & Engineering Geology,2013,40(3):98 − 104. (in Chinese with English abstract) XU Chong, DAI Fuchu, XU Suning, et al. Application of logistic regression model on the Wenchuan earthquake triggered landslide hazard mapping and its validation[J]. Hydrogeology & Engineering Geology, 2013, 40（3）: 98 − 104. （in Chinese with English abstract）
[6]	陈水满,赵辉龙,许震,等. 基于人工神经网络模型的福建南平市滑坡危险性评价[J]. 中国地质灾害与防治学报,2022,33(2):133 − 140. [CHEN Shuiman,ZHAO Huilong,XU Zhen,et al. Landslide risk assessment in Nanping City based on artificial neural networks model[J]. The Chinese Journal of Geological Hazard and Control,2022,33(2):133 − 140. (in Chinese with English abstract) CHEN Shuiman, ZHAO Huilong, XU Zhen, et al. Landslide risk assessment in Nanping City based on artificial neural networks model[J]. The Chinese Journal of Geological Hazard and Control, 2022, 33（2）: 133 − 140. （in Chinese with English abstract）
[7]	HONG Haoyuan,LIU Junzhi,BUI D T,et al. Landslide susceptibility mapping using J48 Decision Tree with AdaBoost,Bagging and Rotation Forest ensembles in the Guangchang area (China)[J]. CATENA,2018,163:399 − 413. doi: 10.1016/j.catena.2018.01.005
[8]	张福浩,朱月月,赵习枝,等. 地理因子支持下的滑坡隐患点空间分布特征及识别研究[J]. 武汉大学学报(信息科学版),2020,45(8):1233 − 1244. [ZHANG Fuhao,ZHU Yueyue,ZHAO Xizhi,et al. Spatial distribution and identification of hidden danger points of landslides based on geographical factors[J]. Geomatics and Information Science of Wuhan University,2020,45(8):1233 − 1244. (in Chinese with English abstract) ZHANG Fuhao, ZHU Yueyue, ZHAO Xizhi, et al. Spatial distribution and identification of hidden danger points of landslides based on geographical factors[J]. Geomatics and Information Science of Wuhan University, 2020, 45（8）: 1233 − 1244. （in Chinese with English abstract）
[9]	赵楠,卢毅敏. 基于XGBoost算法的近地面臭氧浓度遥感估算[J]. 环境科学学报,2022,42(5):95 − 108. [ZHAO Nan,LU Yimin. Remote-sensing estimation of near-surface ozone concentration based on XGBoost[J]. Acta Scientiae Circumstantiae,2022,42(5):95 − 108. (in Chinese with English abstract) ZHAO Nan, LU Yimin. Remote-sensing estimation of near-surface ozone concentration based on XGBoost[J]. Acta Scientiae Circumstantiae, 2022, 42（5）: 95 − 108. （in Chinese with English abstract）
[10]	孙德亮. 基于机器学习的滑坡易发性区划与降雨诱发滑坡预报预警研究[D]. 上海:华东师范大学,2019. [SUN Deliang. Study on landslide susceptibility zoning and rainfall-induced landslide prediction and early warning based on machine learning[D]. Shanghai:East China Normal University,2019. (in Chinese with English abstract) SUN Deliang. Study on landslide susceptibility zoning and rainfall-induced landslide prediction and early warning based on machine learning[D]. Shanghai: East China Normal University, 2019. （in Chinese with English abstract）
[11]	赵晓东,徐振涛,刘福,等. 基于极端梯度提升算法的滑坡易发性评价模型[J]. 科学技术与工程,2022,22(23):10347 − 10354. [ZHAO Xiaodong,XU Zhentao,LIU Fu,et al. Evaluation model of landslide susceptibility based on extreme gradient lifting algorithm[J]. Science Technology and Engineering,2022,22(23):10347 − 10354. (in Chinese with English abstract) ZHAO Xiaodong, XU Zhentao, LIU Fu, et al. Evaluation model of landslide susceptibility based on extreme gradient lifting algorithm[J]. Science Technology and Engineering, 2022, 22（23）: 10347 − 10354. （in Chinese with English abstract）
[12]	李丽秋,许成燕,王晓丽,等. 基于社区大数据的骨关节炎患病风险XGboost预测模型研究[J]. 中华全科医学,2022,20(12):2080 − 2083. [LI Liqiu,XU Chengyan,WANG Xiaoli,et al. Study on XGboost prediction model of osteoarthritis risk based on community big data[J]. Chinese Journal of General Practice,2022,20(12):2080 − 2083. (in Chinese) LI Liqiu, XU Chengyan, WANG Xiaoli, et al. Study on XGboost prediction model of osteoarthritis risk based on community big data[J]. Chinese Journal of General Practice, 2022, 20（12）: 2080 − 2083. （in Chinese）
[13]	钱宇,何益丰,谢斌鑫,等. 基于特征工程的XGboost风速短期预测[J]. 武汉大学学报(工学版),2022,55(10):1057 − 1064. [QIAN Yu,HE Yifeng,XIE Binxin,et al. Short-term forecast of XGboost wind speed based on feature engineering[J]. Engineering Journal of Wuhan University,2022,55(10):1057 − 1064. (in Chinese with English abstract) QIAN Yu, HE Yifeng, XIE Binxin, et al. Short-term forecast of XGboost wind speed based on feature engineering[J]. Engineering Journal of Wuhan University, 2022, 55（10）: 1057 − 1064. （in Chinese with English abstract）
[14]	李德毅,刘常昱. 论正态云模型的普适性[J]. 中国工程科学,2004,6(8):28 − 34. [LI Deyi,LIU Changyu. Study on the universality of the normal cloud model[J]. Engineering Science,2004,6(8):28 − 34. (in Chinese with English abstract) doi: 10.3969/j.issn.1009-1742.2004.08.006 LI Deyi, LIU Changyu. Study on the universality of the normal cloud model[J]. Engineering Science, 2004, 6（8）: 28 − 34. （in Chinese with English abstract） doi: 10.3969/j.issn.1009-1742.2004.08.006
[15]	朱文举,平建华,侯俊山,等. 安阳市地下水源热泵系统建设水资源管理区划研究[J]. 水文地质工程地质,2022,49(1):200 − 208. [ZHU Wenju,PING Jianhua,HOU Junshan,et al. A study of the water resources management and division of the groundwater heat pump system construction in Anyang[J]. Hydrogeology & Engineering Geology,2022,49(1):200 − 208. (in Chinese with English abstract) ZHU Wenju, PING Jianhua, HOU Junshan, et al. A study of the water resources management and division of the groundwater heat pump system construction in Anyang[J]. Hydrogeology & Engineering Geology, 2022, 49（1）: 200 − 208. （in Chinese with English abstract）
[16]	阮永芬,张虔,乔文件,等. 基于C-V-T模型的盾构穿越既有桥梁施工风险评估[J]. 岩土力学,2023,44(2):552 − 562. [RUAN Yongfen,ZHANG Qian,QIAO Wenjian,et al. Construction risk assessment of shield crossing existing bridge based on C-V-T model[J]. Rock and Soil Mechanics,2023,44(2):552 − 562. (in Chinese with English abstract) RUAN Yongfen, ZHANG Qian, QIAO Wenjian, et al. Construction risk assessment of shield crossing existing bridge based on C-V-T model[J]. Rock and Soil Mechanics, 2023, 44（2）: 552 − 562. （in Chinese with English abstract）
[17]	何乐平,罗舒月,胡启军,等. 基于理想点-可拓云模型的隧道围岩稳定性评价[J]. 中国地质灾害与防治学报,2021,32(2):126 − 134. [HE Leping,LUO Shuyue,HU Qijun,et al. Stability evaluation of tunnel surrounding rock based on ideal point-extension cloud model[J]. The Chinese Journal of Geological Hazard and Control,2021,32(2):126 − 134. (in Chinese with English abstract) HE Leping, LUO Shuyue, HU Qijun, et al. Stability evaluation of tunnel surrounding rock based on ideal point-extension cloud model[J]. The Chinese Journal of Geological Hazard and Control, 2021, 32（2）: 126 − 134. （in Chinese with English abstract）
[18]	陈忠源,戴自航. 基于指标变权重复合云模型的岩质边坡稳定性评价初探[J]. 中国地质灾害与防治学报,2021,32(6):9 − 17. [CHEN Zhongyuan,DAI Zihang. A preliminary study on evaluation of rock slope stability based on index variable weight compound cloud model[J]. The Chinese Journal of Geological Hazard and Control,2021,32(6):9 − 17. (in Chinese with English abstract) CHEN Zhongyuan, DAI Zihang. A preliminary study on evaluation of rock slope stability based on index variable weight compound cloud model[J]. The Chinese Journal of Geological Hazard and Control, 2021, 32（6）: 9 − 17. （in Chinese with English abstract）
[19]	CHEN Tianqi,GUESTRIN C. XGBoost:A scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. August 13 – 17,2016,San Francisco,California,USA. New York:ACM,2016:785 – 794.
[20]	刘桂花,宋承祥,刘弘. 云发生器的软件实现[J]. 计算机应用研究,2007,24(1):46 − 48. [LIU Guihua,SONG Chengxiang,LIU Hong. Software implementation of cloud generators[J]. Application Research of Computers,2007,24(1):46 − 48. (in Chinese with English abstract) LIU Guihua, SONG Chengxiang, LIU Hong. Software implementation of cloud generators[J]. Application Research of Computers, 2007, 24（1）: 46 − 48. （in Chinese with English abstract）
[21]	刘常昱,冯芒,戴晓军,等. 基于云X信息的逆向云新算法[J]. 系统仿真学报,2004,16(11):2417 − 2420. [LIU Changyu,FENG Mang,DAI Xiaojun,et al. A new algorithm of backward cloud[J]. Acta Simulata Systematica Sinica,2004,16(11):2417 − 2420. (in Chinese with English abstract) doi: 10.3969/j.issn.1004-731X.2004.11.013 LIU Changyu, FENG Mang, DAI Xiaojun, et al. A new algorithm of backward cloud[J]. Acta Simulata Systematica Sinica, 2004, 16（11）: 2417 − 2420. （in Chinese with English abstract） doi: 10.3969/j.issn.1004-731X.2004.11.013
[22]	BANDROWSKI J,HEHLMANN J,MERTA H,et al. Studies of sedimentation in settlers with packing[J]. Chemical Engineering and Processing:Process Intensification,1997,36(3):219 − 229. doi: 10.1016/S0255-2701(96)04190-6
[23]	黄琼桃,刘瑞敏. 云模型的相似性度量综述[J]. 数据通信,2019(6):43 − 49. [HUANG Qiongtao,LIU Ruimin. A survey of similarity measurement of cloud models[J]. Data Communications,2019(6):43 − 49. (in Chinese with English abstract) HUANG Qiongtao, LIU Ruimin. A survey of similarity measurement of cloud models[J]. Data Communications, 2019（6）: 43 − 49. （in Chinese with English abstract）
[24]	DAS I,STEIN A,KERLE N,et al. Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logistic regression models[J]. Geomorphology,2012,179:116 − 125. doi: 10.1016/j.geomorph.2012.08.004
[25]	李长春,朱亚强,吴京,等. 基于组合赋权法—云模型的甘肃省水安全时空变化分析[J]. 水电能源科学,2023,41(2):23 − 26. [LI Changchun,ZHU Yaqiang,WU Jing,et al. Spatial and temporal change analysis of water security in Gansu Province based on combined weighting method-cloud model[J]. Water Resources and Power,2023,41(2):23 − 26. (in Chinese with English abstract) LI Changchun, ZHU Yaqiang, WU Jing, et al. Spatial and temporal change analysis of water security in Gansu Province based on combined weighting method-cloud model[J]. Water Resources and Power, 2023, 41（2）: 23 − 26. （in Chinese with English abstract）