摘要
四川省青川县滑坡灾害群发,点多面广,区域滑坡灾害预警是有效防灾减灾的重要手段,预警模型是成功预警的核心。由于研究区滑坡诱发机理复杂、调查监测大数据及分析方法不足等原因,传统区域地质灾害预警模型存在预警精度有限、精细化不足等问题。文章在青川县地质灾害调查监测和降水监测成果集成整理与数据清洗基础上,构建了青川县区域滑坡灾害训练样本集,样本集包括地质环境、降雨等27个输入特征属性和1个输出特征属性,涵盖了青川县近9年(2010—2018年)全部样本,数量达1826个(其中,正样本613个,负样本1213个)。基于逻辑回归算法,对样本集进行5折交叉验证学习训练,采用贝叶斯优化算法进行模型优化,采用精确度、ROC曲线和AUC值等指标校验模型准确度和模型泛化能力。其中,ROC曲线也称为“受试者工作特征”曲线;AUC值表示ROC曲线下的面积。校验结果显示,基于逻辑回归算法的模型训练结果准确率和泛化能力均较好(准确率94.3%,AUC为0.980)。开展区域滑坡实际预警时,按训练样本特征属性格式,输入研究区各预警单元27个特征属性,调用预先学习训练好的模型,输出滑坡灾害发生概率,根据输出概率分段确定滑坡灾害预警等级。当输出概率P≥40%且P<60%时,发布黄色预警;当输出概率P≥60%且P<80%时,发布橙色预警;当输出概率P≥80%时,发布红色预警。
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 setincludes 27 input feature attributes such as geological environment rainfall and 1 output feature attribute, coveringthe total number of the samples in Qingchuan County in the past 9 years (2010—2018) up to 1 826 (613 positivesamples, 1 213 negative samples). Based on the logistic regression algorithm, the study and training of the sampleset is carried out with a 50%-fold cross validation. The Bayesian optimization algorithm is used for modeloptimization, and the accuracy and model generalization ability of the model are verified by such indicators asaccuracy, 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 resultmodel based on logistic regression algorithm is of good accuracy and generalization ability (accuracy 94.3% andAUC 0.980). Finally, it is proposed that in the actual warning of regional landslide, 27 characteristic attributes ofeach warning unit in the research area are input according to the format of characteristic attributes of trainingsamples, and the pre-learned and trained model is called to output the probability of occurrence of landslidedisaster, and the warning level of landslide disaster is segmented according to the output probability. A yellowalert is issued when the output probability P is greater than or equal to 40% and P is less than 60%. An orange alertis issued when the output probability P is greater than or equal to 60% and P is less than 80%. A red alert is issuedwhen the output probability P is greater than or equal to 80%. In the next step, the accuracy of the model will befurther verified in the landslide disaster early warning business in Qingchuan county.
作者
方然可
刘艳辉
苏永超
黄志全
FANG Ranke;LIU Yanhui;SU Yongchao;HUANG Zhiquan(North China University of Water Resources and Electric Power,Zhengzhou,Henan 450045,China;China institute of geological environment monitoring(Technical Guidance Center for Geological Hazards,Ministry of Natural Resources),Beijing 100081,China;Luoyang Institute of Science and Technology,Luoyang,Henan 471023,China)
出处
《水文地质工程地质》
CAS
CSCD
北大核心
2021年第1期181-187,共7页
Hydrogeology & Engineering Geology
基金
国家重点研发计划(2018YFC1505503)
国家自然科学基金项目(42077440,41202217)
国家科技支撑计划子课题(2015BAK10B021)。
关键词
滑坡灾害
预警模型
逻辑回归
模型构建
预警等级
landslide hazard
Early warning model
logistic regression
model building
warning level
