A early warning model of regional landslide in Qingchuan County, Sichuan Province based on logistic regression

FANG Ranke; LIU Yanhui; SU Yongchao; HUANG Zhiquan

doi:10.16030/j.cnki.issn.1000-3665.201911034

2021 Vol. 48, No. 1

Article Contents

Article navigation > Hydrogeology & Engineering Geology > 2021 > 48(1): 181-187

Next Article Previous Article

FANG Ranke, LIU Yanhui, SU Yongchao, HUANG Zhiquan. A early warning model of regional landslide in Qingchuan County, Sichuan Province based on logistic regression[J]. Hydrogeology & Engineering Geology, 2021, 48(1): 181-187. doi: 10.16030/j.cnki.issn.1000-3665.201911034

Citation:

FANG Ranke, LIU Yanhui, SU Yongchao, HUANG Zhiquan. A early warning model of regional landslide in Qingchuan County, Sichuan Province based on logistic regression[J]. Hydrogeology & Engineering Geology, 2021, 48(1): 181-187. doi: 10.16030/j.cnki.issn.1000-3665.201911034

A early warning model of regional landslide in Qingchuan County, Sichuan Province based on logistic regression

1.
North China University of Water Resources and Electric Power, Zhengzhou, Henan　450045, China
2.
China institute of geological environment monitoring (Technical Guidance Center for Geological Hazards, Ministry of Natural Resources), Beijing　100081, China
3.
Luoyang Institute of Science and Technology, Luoyang, Henan　471023, China

More Information

Corresponding author: LIU Yanhui, liuyh@cigem.cn

Received Date: 12 November 2019

Revised Date: 12 January 2020

Publish Date: 15 January 2021

Abstract

Abstract

In Qingchuan County of Sichuan Province, landslide disasters occur in a large number of places and cover a wide range of areas. Early warning of regional landslide disaster is an important means of effective disaster prevention and mitigation, and an early warning model is the core of successful early warning. The traditional regional geological disaster warning model is limited by the lack of big data and analysis methods of the complicated investigation and monitoring mechanism of the landslide in the study areas, and it has some problems, such as limited warning precision and insufficient refinement. In this paper, the training sample set of landslide disaster in Qingchuan County is constructed on the basis of the integrated collation and data cleaning of the results of geological disaster investigation and monitoring and precipitation monitoring. The sample set includes 27 input feature attributes such as geological environment rainfall and 1 output feature attribute, covering the total number of the samples in Qingchuan County in the past 9 years (2010—2018) up to 1826 (613 positive samples, 1213 negative samples). Based on the logistic regression algorithm, the study and training of the sample set is carried out with a 50%-fold cross validation. The Bayesian optimization algorithm is used for model optimization, and the accuracy and model generalization ability of the model are verified by such indicators as accuracy, ROC curve and AUC value. The ROC curve is also known as the “Receiver Operating Characteristic” curve. AUC value represents the area under the ROC curve. The verification results show that the training result model based on logistic regression algorithm is of good accuracy and generalization ability (accuracy 94.3% and AUC 0.980). Finally, it is proposed that in the actual warning of regional landslide, 27 characteristic attributes of each warning unit in the research area are input according to the format of characteristic attributes of training samples, and the pre-learned and trained model is called to output the probability of occurrence of landslide disaster, and the warning level of landslide disaster is segmented according to the output probability. A yellow alert is issued when the output probability P is greater than or equal to 40% and P is less than 60%. An orange alert is issued when the output probability P is greater than or equal to 60% and P is less than 80%. A red alert is issued when the output probability P is greater than or equal to 80%. In the next step, the accuracy of the model will be further verified in the landslide disaster early warning business in Qingchuan county.
- landslide hazard /
- Early warning model /
- logistic regression /
- model building /
- warning level

FullText(HTML)

References

[1]	刘传正, 温铭生, 唐灿. 中国地质灾害气象预警初步研究[J]. 地质通报,2004,23(4):303 − 309. [LIU Chuanzheng, WEN Mingsheng, TANG Can. Meteorological early warning of geo-hazards in China based on raining forecast[J]. Geological Bulletin of China,2004,23(4):303 − 309. (in Chinese with English abstract) doi: 10.3969/j.issn.1671-2552.2004.04.001 CrossRef Google Scholar
[2]	刘传正, 刘艳辉, 温铭生, 等. 中国地质灾害区域预警方法与应用[M]. 北京: 地质出版社, 2009. Google Scholar LIU Chuanzheng, LIU Yanhui, WEN Mingsheng, et al. Method and application of regional warning for geo-hazards in China [M]. Beijing: Geological Publishing. 2009. (in Chinese) Google Scholar
[3]	刘传正, 刘艳辉, 温铭生, 等. 中国地质灾害气象预警实践: 2003-2012[J]. 中国地质灾害与防治学报,2015,26(1):1 − 8. [LIU Chuanzheng, LIU Yanhui, WEN Mingsheng, et al. Early warning for regional geo-hazards during 2003-2012, China[J]. The Chinese Journal of Geological Hazard and Control,2015,26(1):1 − 8. (in Chinese with English abstract) Google Scholar
[4]	CANNON S H. Rainfall conditions for abundant debris avalanches, San Francisco Bay region, California[J]. California Geology,1985,38(12):267 − 272. Google Scholar
[5]	AU S W C. Rain-induced slop instability in Hong Kong[J]. Engineering Geology,1998,51(1):1 − 36. Google Scholar
[6]	ALEOTTI P. A warning system for rainfall-induced shallow failures[J]. Engineering geology,2004,73:247 − 265. Google Scholar
[7]	刘艳辉, 刘传正, 连建发, 等. 基于显式统计原理的地质灾害区域预警方法初步研究[J]. 中国地质,2008,35(2):344 − 350. [LIU Yanhui, LIU Chuanzheng, LIAN Jianfa, et al. Preliminary study of geo-hazards regional early warning based on explicit statistical theory[J]. Geology in China,2008,35(2):344 − 350. (in Chinese with English abstract) doi: 10.3969/j.issn.1000-3657.2008.02.020 CrossRef Google Scholar
[8]	刘艳辉, 刘传正, 温铭生, 等. 中国地质灾害气象预警模型研究[J]. 工程地质学报,2015,23(4):738 − 746. [LIU Yanhui, LIU Chuanzheng, WEN Mingsheng, et al. Study of early warning models for regional geo-hazards in China[J]. Journal of Engineering Geology,2015,23(4):738 − 746. (in Chinese with English abstract) Google Scholar
[9]	刘艳辉, 张振兴, 苏永超. 地质灾害承灾载体脆弱性评价方法研究[J]. 工程地质学报,2018,26(5):1121 − 1130. [LIU Yanhui, ZHANG Zhenxing, SU Yongchao. Case study of vulnerability evaluation for geo-hazards bearing capacity of a region[J]. Journal of Engineering Geology,2018,26(5):1121 − 1130. (in Chinese with English abstract) Google Scholar
[10]	刘艳辉, 苏永超. 四川青川县区域地质灾害气象风险预警模型研究[J]. 工程地质学报,2019,27(1):134 − 143. [LIU Yanhui, SU Yongchao. Early-warning model of regional geological disasters based on meteorological factor in Qingchuan County, Sichuan Province[J]. Journal of Engineering Geology,2019,27(1):134 − 143. (in Chinese with English abstract) Google Scholar
[11]	侯圣山, 李昂, 韩冰, 等. 四川雅安地质灾害预警预报及分析[J]. 中国地质灾害与防治学报,2014,25(4):134 − 138. [HOU Shengshan, LI Ang, HAN Bing, et al. An approach of geo-hazard warning system in Ya’an, Sichuan and its analysis[J]. The Chinese Journal of Geological Hazard and Control,2014,25(4):134 − 138. (in Chinese with English abstract) Google Scholar
[12]	李守定, 白亚恒, 姜越, 等. 基于内外动力耦合成因理论的新疆地质灾害气象预警显式统计模型[J]. 地球科学与环境学报,2017,39(2):287 − 300. [LI Shouding, BAI Yaheng, JIANG Yue, et al. An explicit statistical model for meteorological early warning of geological hazards in Xinjiang based on the coupling theory of internal and external dynamics[J]. Journal of Earth Sciences and Environment,2017,39(2):287 − 300. (in Chinese with English abstract) Google Scholar
[13]	魏平新, 李秀娟. 广东省突发性地质灾害气象预警实践[J]. 中国地质灾害与防治学报,2015,26(1):138 − 144. [WEI Pingxin, LI Xiujuan. The meteorologic early warning research of sudden geo-hazard in Guangdong province[J]. The Chinese Journal of Geological Hazard and Control,2015,26(1):138 − 144. (in Chinese with English abstract) Google Scholar
[14]	中国地质环境监测院. 城镇化过程中承灾载体脆弱性及脆弱性评价方法研究成果报告[R]. 北京: 中国地质环境监测院, 2018. Google Scholar China Institute of Geo-Environmental Monitoring. The research report of vulnerability vector and vulnerability assessment method during urbanization[R]. Beijing: China Institute of Geo-Environmental Monitoring, 2018. (in Chinese) Google Scholar
[15]	四川九零九建设工程有限公司. 四川省青川县地质灾害详细调查报告[R]. 成都: 四川九零九建设工程有限公司, 2015. Google Scholar Sichuan 909 Construction Engineering Co. LTD. A detailed survey report on geological hazards in Qingchuan County, Sichuan Province[R]. Chengdu: Sichuan 909 Construction Engineering Co. LTD, 2015. (in Chinese) Google Scholar
[16]	中国地质环境监测院. 四川青竹江流域地质灾害调查报告[R]. 北京: 中国地质环境监测院, 2016. Google Scholar China Institute of Geo-Environmental Monitoring. Geo-hazards investigation report of Qingzhujiang River region, Sichuan[R]. Beijing: China Institute of Geo-Environmental Monitoring, 2016. (in Chinese) Google Scholar
[17]	刘艳辉, 肖锐铧, 陈春利, 等. 区域滑坡预警中训练样本集的构建方法、系统及存储介质: 202010829816.0[P]. Google Scholar LIU Yanhui, XIAO Ruihua, CHEN Chunli, et al. Construction method system and storage medium of training sample set in regional landslide early warning: 202010829816.0[P].2020-08-18. (in Chinese with English abstract) Google Scholar
[18]	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. 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) Google Scholar
[19]	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. Google Scholar ZHU Li. Application of decision tree algorithm in the risk assessment system of mountain highway geological hazards[D]. Chongqing: Chongqing Normal University, 2019. (in Chinese with English abstract) Google Scholar
[20]	BOSCHETTI A, MASSARON L. Python data science essentials[M]. 2nd ed. Packt Publishing Ltd, 2015. Google Scholar
[21]	赵永红, 王航, 张琼, 等. 滑坡位移监测方法综述[J]. 地球物理学进展,2018,33(6):2606 − 2612. [ZHAO Yonghong, WANG Hang, ZHANG Qiong, et al. A review of monitoring methods for landslide displacement[J]. Progress in Geophysics,2018,33(6):2606 − 2612. (in Chinese with English abstract) doi: 10.6038/pg2018BB0464 CrossRef Google Scholar
[22]	张铎, 吴中海, 李家存, 等. 国内外地震滑坡研究综述[J]. 地质力学学报,2013,19(3):225 − 241. [ZHANG Duo, WU Zhonghai, LI Jiacun, et al. A review of seismic landslide studies at home and abroad[J]. Journal of geomechanics,2013,19(3):225 − 241. (in Chinese with English abstract) doi: 10.3969/j.issn.1006-6616.2013.03.001 CrossRef Google Scholar
[23]	LEE S, RYU J, MIN K, et al. Development and application of landslide susceptibility analysis techniques using geographic information system (GIS)[C]//IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No. 00CH37120). IEEE, 2000, 1: 319−321. Google Scholar
[24]	OHLMACHER G C, DAVIS J C. Using multiple logistic regression and GIS technology to predict landslide hazard in northeast Kansas, USA[J]. Engineering geology,2003,69:331 − 343. Google Scholar
[25]	李铁锋, 丛威青. 基于Logistic回归及前期有效雨量的降雨诱发型滑坡预测方法[J]. 中国地质灾害与防治学报,2006,17(1):33 − 35. [LI Tiefeng, CONG Weiqing. Rainfall-induced landslide prediction method based on Logistic regression and early effective rainfall[J]. Chinese Journal of Geological Hazards and Prevention,2006,17(1):33 − 35. (in Chinese with English abstract) doi: 10.3969/j.issn.1003-8035.2006.01.008 CrossRef Google Scholar
[26]	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. Google Scholar SUN Deliang. Study on landslide susceptibility regionalization and rainfall-Induced landslide prediction and Early Warning based on machine learning [D]. Shanghai: East China Normal University, 2019. (in Chinese with English abstract). Google Scholar
[27]	SNOEK J, LAROCHELLE H, ADAMS R P. Practical bayesian optimization of machine learning algorithms[J]. Advances in neural information processing systems,2012,25:2951 − 2959. Google Scholar
[28]	中国地质灾害防治工程行业协会. 地质灾害区域气象风险预警标准(试行): T/CAGHP 039-2018[S]. 武汉: 中国地质大学出版社, 2018. Google Scholar China Geological Disaster Prevention Engineering Association. Regional meteorological risk early warning standard for geological disaster (trial): T/CAGHP 039-2018[S]. Wuhan: China University of Geosciences Press, 2018. ](in Chinese) Google Scholar