A review of the methods of regional landslide hazard assessment based on machine learning
-
摘要:
我国滑坡灾害分布范围广，危害严重。区域滑坡危险性评价一直都是滑坡灾害防灾减灾的重要内容之一。近年来，随着大数据和人工智能技术的飞速发展，机器学习技术逐渐在滑坡灾害危险性评价方面得到广泛应用，并取得了较好效果。在大量研读文献的基础上，系统阐述了基于机器学习技术的滑坡危险性评价方法研究现状。综述从评价因子选择与量化归一化、数据清洗与样本集构建、模型选取与训练评价等三个关键环节对现有研究成果进行分析评述，最后对机器学习滑坡危险性评价方法的发展趋势提出讨论意见。
Abstract:The landslide disaster in China is widespread and serious. Regional landslide risk assessment has always been one of the most important contents of landslide disaster prevention and mitigation. In recent years, with the rapid development of big data and artificial intelligence technology, machine learning technology has gradually been widely used in landslide hazard assessment andachieved good results. Based on a large number of literatures, this paper systematically expounds the research status of landslide risk assessment methods based on machine learning technology. This paper reviews and analyzes the existing research results from three key links: evaluation factor selection and quantization normalization, data cleaning and sample set construction, model selection and training evaluation, and finally puts forward some suggestions on the development trend of machine learning landslide risk evaluation methods.
-
Key words:
- landslide /
- risk assessment /
- machine learning /
- method survey /
- model research
-
-
表 1 滑坡危险性评价可选用的机器学习模型
Table 1. An optional machine learning model for landslide hazard assessment
类型 常用模型 优缺点 相关数学公式 分类
（判断类别已知的
离散型数据）KNN最近邻算法 适用多分类评价；准确度高，对异常点
不敏感。但计算量大，过于依赖均衡训
练数据。欧式距离： 
曼哈顿距离：
SVM支持向量机 核函数可映射至高维空间，解决非线性
分类评价。但对大规模和多分类训练样
本难以进行评价。高斯核函数： 
人工神经网络
（线性、BP、卷积）可高速寻找优化解。但需要大量参数，
学习时间过长，评价结果不确定。损失函数 
Logistic回归
（Sigmoid函数、梯度上升）评价效率高。但不能观察学习过程。 逻辑函数： 
决策树 适合评价离散小规模样本。但评价大量
连续变量和多类别样本效果欠佳。信息熵 
集成算法
（bagging、随机森林RF、
boosting、stacking）避免了强势样本对评价结果的影响。但
在某些噪音值较大的样本来进行危险性
评价时可能会发生过拟合现象。Bagging 
下载: 导出CSV
-
[1] VAN DIJKE J J, VAN WESTEN C J. Rockfall hazard: a geomorphologic application of neighbourhood analysis with ILWIS[J]. ITC Journal,1990:40 − 44.
[2] ALEOTTI P, CHOWDHURY R. Landslide hazard assessment: summary review and new perspectives[J]. Bulletin of Engineering Geology and the Environment,1999,58(1):21 − 44. doi: 10.1007/s100640050066
[3] 黄润秋, 李曰国. 三峡工程水库岸坡稳定性预测的逻辑信息模型[J]. 水文地质工程地质,1992,19(1):15 − 20. [HUANG Runqiu, LI Yueguo. LOGICAl message modei of stability predication ot bank slopes in Three Gorges[J]. Hydrogeology & Engineering Geology,1992,19(1):15 − 20. (in Chinese with English abstract)
[4] 刘传正, 刘艳辉, 温铭生. 长江三峡库区地质灾害成因与评价研究[M]. 北京: 地质出版社, 2007.
LIU Chuanzheng, LIU Yanhui, WEN Mingsheng. Research on the geo-hazards genesis and assessment in the Three Gorges reservoir of Changjiang River in China[M]. Beijing: Geological Publishing House, 2007. (in Chinese)
[5] 刘传正, 温铭生, 刘艳辉,等. 汶川地震区重大地质灾害成生规律研究[M], 北京: 地质出版社, 2017.
LIU Chuanzheng, LIU Yanhui, WEN Mingsheng, et al. Study on the law of formation of major geological disasters in Wenchuan Earthquake area[M].Beijing: Geological Publishing House, 2017. (in Chinese)
[6] 唐川, 朱静, 张翔瑞. GIS支持下的地震诱发滑坡危险区预测研究[J]. 地震研究,2001,24(1):73 − 81. [TANG Chuan, ZHU Jing, ZHANG Xiangrui. GIS based earthquake triggered landslide hazard prediction[J]. Journal of Seismological Research,2001,24(1):73 − 81. (in Chinese with English abstract) doi: 10.3969/j.issn.1000-0666.2001.01.012
[7] 张春山, 张业成, 马寅生. 黄河上游地区崩塌、滑坡、泥石流地质灾害区域危险性评价[J]. 地质力学学报,2003,9(2):143 − 153. [ZHANG Chunshan, ZHANG Yecheng, MA Yinsheng. Regional dangerous on the geological hazards of collapse, landslide and debris flows in the upper reaches of the Yellow River[J]. Journal of Geomechanics,2003,9(2):143 − 153. (in Chinese with English abstract) doi: 10.3969/j.issn.1006-6616.2003.02.007
[8] JIANG H, EASTMAN J R. Application of fuzzy measures in multi-criteria evaluation in GIS[J]. International Journal of Geographical Information Science,2000,14(2):173 − 184. doi: 10.1080/136588100240903
[9] 周超, 方秀琴, 吴小君, 等. 基于三种机器学习算法的山洪灾害风险评价[J]. 地球信息科学学报,2019,21(11):1679 − 1688. [ZHOU Chao, FANG Xiuqin, WU Xiaojun, et al. Risk assessment of mountain torrents based on three machine learning algorithms[J]. Journal of Geo-Information Science,2019,21(11):1679 − 1688. (in Chinese with English abstract) doi: 10.12082/dqxxkx.2019.190185
[10] TIEN BUI D, PRADHAN B, LOFMAN O, et al. Landslide susceptibility mapping at Hoa Binh Province (Vietnam) using an adaptive neuro-fuzzy inference system and GIS[J]. Computers & Geosciences,2012,45:199 − 211.
[11] CHEN W, POURGHASEMI H R, ZHAO Z. A GIS-based comparative study of Dempster-Shafer, logistic regression and artificial neural network models for landslide susceptibility mapping[J]. Geocarto International,2017,32(4):367 − 385. doi: 10.1080/10106049.2016.1140824
[12] TRIGILA A, IADANZA C, ESPOSITO C, et al. Comparison of Logistic Regression and Random Forests techniques for shallow landslide susceptibility assessment in Giampilieri (NE Sicily, Italy)[J]. Geomorphology,2015,249:119 − 136. doi: 10.1016/j.geomorph.2015.06.001
[13] HONG H Y, PRADHAN B, XU C, et al. Spatial prediction of landslide hazard at the Yihuang area (China) using two-class kernel logistic regression, alternating decision tree and support vector machines[J]. CATENA,2015,133:266 − 281. doi: 10.1016/j.catena.2015.05.019
[14] YOUSSEF A M, POURGHASEMI H R, POURTAGHI Z S, et al. Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia[J]. Landslides,2016,13(5):839 − 856. doi: 10.1007/s10346-015-0614-1
[15] CHEN W, POURGHASEMI H R, KORNEJADY A, et al. Landslide spatial modeling: Introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques[J]. Geoderma,2017,305:314 − 327. doi: 10.1016/j.geoderma.2017.06.020
[16] TSANGARATOS P, ILIA I. Comparison of a logistic regression and Naïve Bayes classifier in landslide susceptibility assessments: The influence of models complexity and training dataset size[J]. CATENA,2016,145:164 − 179. doi: 10.1016/j.catena.2016.06.004
[17] TIEN BUI D, TUAN T A, KLEMPE H, et al. Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree[J]. Landslides,2016,13(2):361 − 378. doi: 10.1007/s10346-015-0557-6
[18] 朱清华. 基于RF和SVM模型的灞桥区地质灾害易发性评价[D]. 西安: 西安科技大学, 2019.
ZHU Qinghua. Geological hazard susceptibility assessment in Baqiao district based on RF and SVM model[D]. Xi'an: Xi'an University of Science and Technology, 2019. (in Chinese with English abstract)
[19] 刘永垚, 第宝锋, 詹宇, 等. 基于随机森林模型的泥石流易发性评价: 以汶川地震重灾区为例[J]. 山地学报,2018,36(5):765 − 773. [LIU Yongyao, DI Baofeng, ZHAN Yu, et al. Debris flows susceptibility assessment in Wenchuan earthquake areas based on random forest algorithm model[J]. Mountain Research,2018,36(5):765 − 773. (in Chinese with English abstract)
[20] WESTEN C J V. Application of geographic information systems to landslide hazard zonation[EB]. 1993.
[21] CARRARA A, CARDINALI M, DETTI R, et al. GIS techniques and statistical models in evaluating landslide hazard[J]. Earth Surface Processes and Landforms,1991,16(5):427 − 445. doi: 10.1002/esp.3290160505
[22] MEIJERINK A M J. Data acquisition and data capture through terrain mapping units[EB]. 1988.
[23] ROSSI M, GUZZETTI F, REICHENBACH P, et al. Optimal landslide susceptibility zonation based on multiple forecasts[J]. Geomorphology,2010,114(3):129 − 142. doi: 10.1016/j.geomorph.2009.06.020
[24] 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: 以宁强县为例[D]. 西安: 西北大学, 2012.
QIU Haijun. Study on the regional landslide characteristic analysis and hazard assessment: A case study of Ningqiang County[D]. Xi'an: Northwest University, 2012. (in Chinese with English abstract)
[25] 刘林通. 基于TRIGRS模型的降雨型浅表层滑坡易发性评价: 以秦州区教场坝沟为例[D]. 兰州: 兰州大学, 2018.
LIU Lintong. Rainfall-induced shallow landslides susceptibility assesment based on TRIGRS model in jiaochangba valley[D]. Lanzhou: Lanzhou University, 2018. (in Chinese with English abstract)
[26] 张晓东. 基于遥感和GIS的宁夏盐池县地质灾害风险评价研究[D]. 北京: 中国地质大学(北京), 2018.
ZHANG Xiaodong. Research on risk assessment of geological disasters in Yanchi county, Ningxia[D]. Beijing:China university of geosciences (Beijing), 2018. (in Chinese with English abstract)
[27] 霍艾迪, 张骏, 卢玉东, 等. 地质灾害易发性评价单元划分方法: 以陕西省黄陵县为例[J]. 吉林大学学报(地球科学版),2011,41(2):523 − 528. [HUO Aidi, ZHANG Jun, LU Yudong, et al. Method of classification for susceptibility evaluation unit for geological hazards: a case study of Huangling County, Shaanxi, China[J]. Journal of Jilin University (Earth Science Edition),2011,41(2):523 − 528. (in Chinese with English abstract)
[28] 朱吉龙. 溪洛渡库区滑坡地质灾害风险评价研究[D]. 成都: 西南石油大学, 2019.
ZHU Jilong. Risk assessment of landslide geological hazard in Xiluodu Reservoir area[D]. Chengdu: Southwest Petroleum University, 2019. (in Chinese with English abstract)
[29] 于宪煜, 胡友健, 牛瑞卿. 基于RS-SVM模型的滑坡易发性评价因子选择方法研究[J]. 地理与地理信息科学,2016,32(3):23 − 28. [YU Xianyu, HU Youjian, NIU Ruiqing. Research on the method to select landslide susceptibility evaluation factors based on RS-SVM model[J]. Geography and Geo-Information Science,2016,32(3):23 − 28. (in Chinese with English abstract) doi: 10.3969/j.issn.1672-0504.2016.03.005
[30] 王念秦, 郭有金, 刘铁铭, 等. 基于支持向量机模型的滑坡危险性评价[J]. 科学技术与工程,2019,19(35):70 − 78. [WANG Nianqin, GUO Youjin, LIU Tieming, et al. Landslide susceptibility assessment based on support vector machine model[J]. Science Technology and Engineering,2019,19(35):70 − 78. (in Chinese with English abstract) doi: 10.3969/j.issn.1671-1815.2019.35.010
[31] 宋庆武. 葫芦岛市建昌县山区滑坡危险性评价[J]. 黑龙江水利科技,2019,47(7):217 − 221. [SONG Qingwu. Risk evaluation of landslide of mountainous area in Jiangchang County in Huludao City[J]. Heilongjiang Hydraulic Science and Technology,2019,47(7):217 − 221. (in Chinese with English abstract) doi: 10.3969/j.issn.1007-7596.2019.07.069
[32] 吴孝情, 赖成光, 陈晓宏, 等. 基于随机森林权重的滑坡危险性评价: 以东江流域为例[J]. 自然灾害学报,2017,26(5):119 − 129. [WU Xiaoqing, LAI Chengguang, CHEN Xiaohong, et al. A landslide hazard assessment based on random forest weight: A case study in the Dongjiang River Basin[J]. Journal of Natural Disasters,2017,26(5):119 − 129. (in Chinese with English abstract)
[33] 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)
[34] COSTANZO D, ROTIGLIANO E, IRIGARAY C, et al. Factors selection in landslide susceptibility modelling on large scale following the gis matrix method: application to the river Beiro basin (Spain)[J]. Natural Hazards and Earth System Sciences,2012,12(2):327 − 340. doi: 10.5194/nhess-12-327-2012
[35] CHEN W, PENG J B, HONG H Y, et al. Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China[J]. Science of the Total Environment,2018,626:1121 − 1135. doi: 10.1016/j.scitotenv.2018.01.124
[36] GHAILAN O, HODA M O, HEGAZY O. Improving credit scorecard modeling through applying text analysis[J]. International Journal of Advanced Computer Science and Applications,2016,7(4):512 − 517. doi: 10.14569/ijacsa.2016.070467
[37] 胡旭东. 基于集成学习的地质灾害易发性评价研究: 以云南省泸水县为例[D]. 武汉: 中国地质大学, 2019.
HU Xudong. Study on the geo-hazards susceptibility assessment based on A novel ensemble learning framework —application to the Lushui County, Yunnan Province[D]. Wuhan: China University of Geosciences(Wuhan), 2019. (in Chinese with English abstract)
[38] 梁万杰. 滑坡、泥石流地质灾害评价方法研究[D]. 南京: 南京农业大学, 2012.
LIANG Wanjie. Study on assessment methodology of landslide and debris flow geological hazards[D]. Nanjing: Nanjing Agricultural University, 2012. (in Chinese with English abstract)
[39] 戴福初, 李军. 地理信息系统在滑坡灾害研究中的应用[J]. 地质科技情报,2000,19(1):91 − 96. [DAI Fuchu, LI Jun. Applications of geographical information systems in landslide studies[J]. Geological Science and Technology Information,2000,19(1):91 − 96. (in Chinese with English abstract) doi: 10.3969/j.issn.1000-7849.2000.01.022
[40] YAO X, THAM L G, DAI F C. Landslide susceptibility mapping based on Support Vector Machine: a case study on natural slopes of Hong Kong, China[J]. Geomorphology,2008,101(4):572 − 582. doi: 10.1016/j.geomorph.2008.02.011
[41] KUMAR D, THAKUR M, DUBEY C S, et al. Landslide susceptibility mapping & prediction using Support Vector Machine for Mandakini River Basin, Garhwal Himalaya, India[J]. Geomorphology,2017,295:115 − 125. doi: 10.1016/j.geomorph.2017.06.013
[42] CHEN W T, LI X J, WANG Y X, et al. Forested landslide detection using LiDAR data and the random forest algorithm: a case study of the Three Gorges, China[J]. Remote Sensing of Environment,2014,152:291 − 301. doi: 10.1016/j.rse.2014.07.004
[43] 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. [LIU Jian, LI Shulin, CHEN Tao. 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)
[44] CHEN W, XIE X S, PENG J B, et al. GIS-based landslide susceptibility evaluation using a novel hybrid integration approach of bivariate statistical based random forest method[J]. CATENA,2018,164:135 − 149. doi: 10.1016/j.catena.2018.01.012
[45] 韩帅, 孙乐平, 杨艺云, 等. 基于改进K-Means聚类和误差反馈的数据清洗方法[J]. 电网与清洁能源,2020,36(7):9 − 15. [HAN Shuai, SUN Leping, YANG Yiyun, et al. A data cleaning method based on improved K-means clustering and error feedback[J]. Power System and Clean Energy,2020,36(7):9 − 15. (in Chinese with English abstract)
[46] 刘乾坤. 基于SPARK的四川省滑坡灾害成因分析与临界阈值研究[D]. 成都: 电子科技大学, 2020.
LIU Qiankun. Analysis of causes and critical threshold of landslide hazards in Sichuan Province based on SPARK[D]. Chengdu: University of Electronic Science and Technology of China, 2020. (in Chinese with English abstract)
[47] 朱力. 决策树算法在山区公路地质灾害风险评估系统中的应用[D]. 重庆: 重庆师范大学, 2019.
ZHU Li. Application of decision tree algorithm in risk assessment system of mountain highway geological disaster[D]. Chongqing: Chongqing Normal University, 2019. (in Chinese with English abstract)
[48] ALBERTO BOSCHETTI, LUCA MASSARON. Python data science essentials (Second Edition)[M]. 2016. Packet Publishing.
[49] 崔阳阳, 邓念东, 曹晓凡, 等. 基于集成学习的地质灾害危险性评价[J]. 水力发电,2020,46(10):36 − 41. [CUI Yangyang, DENG Niandong, CAO Xiaofan, et al. Geological disaster risk assessment based on ensemble learning algorithm[J]. Water Power,2020,46(10):36 − 41. (in Chinese with English abstract) doi: 10.3969/j.issn.0559-9342.2020.10.009
[50] 李娟. 汶川县威州镇高分影像滑坡信息提取及危险性评价研究[D]. 成都: 成都理工大学, 2019.
LI Juan. Landslide information extraction and risk assessment of high resolution imagery in Weizhou town, Wenchuan County[D]. Chengdu: Chengdu University of Technology, 2019. (in Chinese with English abstract)
[51] 李远远, 梅红波, 任晓杰, 等. 基于确定性系数和支持向量机的地质灾害易发性评价[J]. 地球信息科学学报,2018,20(12):1699 − 1709. [LI Yuanyuan, MEI Hongbo, REN Xiaojie, et al. Geological disaster susceptibility evaluation based on certainty factor and support vector machine[J]. Journal of Geo-Information Science,2018,20(12):1699 − 1709. (in Chinese with English abstract) doi: 10.12082/dqxxkx.2018.180349
[52] SNOEK J, LAROCHELLE H, ADAMS R P. Practical Bayesian optimization of machine learning algorithms[C]//NIPS'12: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 2.2012: 2951-2959.
[53] 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. Mapping landslide susceptibility based on machine learning and forecast warning of landslide induced by rainfall[D]. Shanghai: East China Normal University, 2019. (in Chinese with English abstract)
[54] 姚雄, 余坤勇, 刘健, 等. 基于随机森林模型的降水诱发山体滑坡空间预测技术[J]. 福建农林大学学报(自然科学版),2016,45(2):219 − 227. [YAO Xiong, YU Kunyong, LIU Jian, et al. Application of random forest model on the landslide spatial prediction caused by precipitation[J]. Journal of Fujian Agriculture and Forestry University (Natural Science Edition),2016,45(2):219 − 227. (in Chinese with English abstract)
[55] 邱维蓉, 吴帮玉, 潘学树, 等. 几种聚类优化的机器学习方法在灵台县滑坡易发性评价中的应用[J]. 西北地质,2020,53(1):222 − 233. [QIU Weirong, WU Bangyu, PAN Xueshu, et al. Application of several cluster-optimization-based machine learning methods in evaluation of landslide susceptibility in Lingtai County[J]. Northwestern Geology,2020,53(1):222 − 233. (in Chinese with English abstract)
[56] 管新邦. 云南省滑坡地质灾害危险性评价研究[D]. 北京: 中国矿业大学(北京), 2018.
GUAN Xinbang. Study on risk assessment of landslide in Yunnan Province[D]. Beijing: China University of Mining & Technology (Beijing), 2018. (in Chinese with English abstract)
[57] 郝国栋. 基于随机森林模型的商南县滑坡易发性评价[D]. 西安: 西安科技大学, 2019.
HAO Guodong. Landslide susceptibility assessment based on random forest model in Shangnan County[D]. Xi'an: Xi'an University of Science and Technology, 2019. (in Chinese with English abstract)
-