基于预警隶属度函数多模型融合的滑坡预警方法
|
摘要
不同的滑坡预报模型存在预报同一滑坡可能提前也有可能延迟、预报精度差异较大的问题,而且,融合多模型预警方法未能充分体现个体模型预报特征,其融合预警精度不高。在分析模型可靠性的基础上,区分预报提前和延迟2种情况,设计不同的发生滑坡隶属度函数,以最低风险原则确定滑坡预警隶属度函数,利用模糊积分实现多模型融合滑坡预警。利用16个已知滑坡对预报模型进行可靠性评价,另选4个已知滑坡分别进行滑坡发生3d前和1d前多模型融合预警验证实验,结果表明,多模型融合预警虚警率比多个单一模型平均虚警率分别降低16.6%和25.0%。实验表明利用预警隶属函数进行多模型滑坡预警能提高预警精度20.0%左右。
Different landslide prediction models have the problem of predicting the same landslide in advance or delay,and the prediction accuracy is quite different.At present,the fusion multi-model early-warning method fails to fully reflect the characteristics of individual model prediction,and the fusion early-warning accuracy is not high.On the basis of analyzing the reliability of these models,twolandslide occurrence membership functions of delay and advance were designed respectively.According to the principle of minimum risk,the membership function of landslide warning was determined,and multi-model fusion of landslide early warning was realized by fuzzy integral.Sixteen known landslides were used to evaluate the reliability of the prediction models,and the other four known landslides were used to carry out the fusion early warning experiment of the landslide three days before and one day before the landslide occurrence,and the false alarm rate of multi-model fusion early warning was reduced by 16.6%and 25%respectively,compared with the average false alarm rate of multiple single models.The experiment shows that using early warning membership function for multi-model landslide early warning can improve the early warning accuracy for about 20%.
Different landslide prediction models have the problem of predicting the same landslide in advance or delay,and the prediction accuracy is quite different.At present,the fusion multi-model early-warning method fails to fully reflect the characteristics of individual model prediction,and the fusion early-warning accuracy is not high.On the basis of analyzing the reliability of these models,twolandslide occurrence membership functions of delay and advance were designed respectively.According to the principle of minimum risk,the membership function of landslide warning was determined,and multi-model fusion of landslide early warning was realized by fuzzy integral.Sixteen known landslides were used to evaluate the reliability of the prediction models,and the other four known landslides were used to carry out the fusion early warning experiment of the landslide three days before and one day before the landslide occurrence,and the false alarm rate of multi-model fusion early warning was reduced by 16.6%and 25%respectively,compared with the average false alarm rate of multiple single models.The experiment shows that using early warning membership function for multi-model landslide early warning can improve the early warning accuracy for about 20%.
引文
[1] Ma G,Kirby J T,Hsu T J,et al.A Two-Layer Granular Landslide Model for Tsunami Wave Generation:Theory and Computation[J].Ocean Modelling,2015,93:40-55.
[2] 杜光波,倪万魁.降雨诱发型残坡积土滑坡形成机理分析[J].防灾减灾工程学报,2016,36(4):565-571.Du Guangbo,Ni Wankui.Analysis of the Formation Mechanism of Rainfall-Induced Residual Soil Landslide[J].Journal of Disaster Prevention and Mitigation Engineering,2016,36(4):565-571.
[3] 黄海峰,易武,易庆林,等.滑坡位移分解预测中的平滑先验分析方法[J].水文地质工程地质,2014,41(5):95-100.Huang Haifeng,Yi Wu,Yi Qinglin,et al.Smoothness Priors Approach in Displacement Decomposition and Prediction of Landslides[J].Hydrogeology &Engineering Geology,2014,41(5):95-100.
[4] 唐鹏,陈国庆,黄润秋,等.基于物理模拟试验的岩质滑坡地表位移分析[J].水文地质工程地质,2017,44(4):105-110.Tang Peng,Chen Guoqing,Huang Runqiu,et al.Surface Displacement Analysis of Rock Slope Based on Physical Simulation Tests[J].Hydrogeology &Engineering Geology,2017,44(4):105-110.
[5] 张俊,殷坤龙,王佳佳,等.基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J].岩石力学与工程学报,2015,34(2):382-391.Zhang Jun, Yin Kunlong, Wang Jiajia,et al.Displacement Prediction of Baishuihe Landslide Based on Time Series and PSO-SVR Model[J].Chinese Journal of Rock Mechanics and Engineering,2015,34(2):382-391.
[6] 龙万学,林剑,许湘华,等.Verhulst反函数模型滑坡起始预测时刻的选择[J].岩石力学与工程学报,2008,27(增刊1):3298-3304.Long Wanxue,Lin Jian,Xu Xianghua,et al.Selection of Initial Prediction Time for Landslide with Verhulst Inverse Function Model[J].Chinese Journal of Rock Mechanics and Engineering,2008,27(Sup.1):3298-3304.
[7] Lian C,Zeng Z G,Yao W,et al.Displacement Prediction Model of Landslide Based on a Modified Ensemble Empirical Mode Decomposition and Extreme Learning Machine[J].Natural Hazards,2013,66(2):759-771.
[8] Lian C,Zeng Z G,Yao W,et al.Ensemble of Extreme Learning Machine for Landslide Displacement Prediction Based on Time Series Analysis[J].Neural Computing &Applications,2014,24(1):99-107.
[9] 王萌,姜元俊,黄栋,等.基于小流域的地震扰动区降型滑坡泥石流危险性评价方法[J].吉林大学学报(地球科学版),2015,45(6):1781-1788.Wang Meng,Jiang Yuanjun,Huang Dong,et al.Hazard Assessment on Rainfall-Triggered Landslide and Debris Flow in the Seismic Disturbance Area at Watershed Level[J].Journal of Jinlin University(Earth Science Edition),2015,45(6):1781-1788.
[10] Zhai J H,Wang J G,Hu W X.Combination of OSELM Classifiers with Fuzzy Integral for Large Scale Classification[J].Journal of Intelligent &Fuzzy Systems,2015,28(5):2257-2268.
[11] 徐则民,梅雪峰,王礼荣,等.滑坡预警中的降水时空变异性:以云南头寨沟为例[J].吉林大学学报(地球科学版),2017,47(1):154-162.Xu Zemin,Mei Xuefeng,Wang Lirong,et al.Precipitation Temporal and Variability of Landslide Earthy Warning Research:A Case Study on Touzhai Gully in Yunnan Province[J].Journal of Jinlin University(Earth Science Edition),2017,47(1):154-162.
[12] 沈玲玲,刘连友,许冲,等.基于多模型的滑坡易发性评价:以甘肃岷县地震滑坡为例[J].工程地质学报,2016,24(1):19-28.Sheng Lingling,Liu Lianyou,Xu Chong,et al.Multi-Models Based Landslides Susceptibility EvaluationIllustrated with Landslides Ttriggered by Minxian Earthquake[J].Journal of Engineering Geology,2016,24(1):19-28.
[13] 李艳华,林剑,龙万学,等.基于位移的滑坡临滑时刻多模型综合预测模糊积分方法[J].自然灾害学报,2013,22(4):209-212.Li Yanhua,Lin Jian,Long Wangxue,et al.Displacement Based Fuzzy Integral Method for Multi-Model Comprehensive Forecast of Landslide-Approaching Time[J].Journal of Natural Disasters,2013,22(4):209-212.
[14] Yin X X,Lin Y G,Li W,et al.A Novel Fuzzy Integral Sliding Mode Current Control Strategy for Maximizing Wind Power Extraction and Eliminating Voltage Harmonics[J].Energy,2015,85:677-686.
[15] Yoo B S,Kim J H.Fuzzy Integral-Based Gaze Control of a Robotic Head for Human Robot Interaction[J].IEEE Transactions on Cybernetics,2015,45(9):1769-1783.
[2] 杜光波,倪万魁.降雨诱发型残坡积土滑坡形成机理分析[J].防灾减灾工程学报,2016,36(4):565-571.Du Guangbo,Ni Wankui.Analysis of the Formation Mechanism of Rainfall-Induced Residual Soil Landslide[J].Journal of Disaster Prevention and Mitigation Engineering,2016,36(4):565-571.
[3] 黄海峰,易武,易庆林,等.滑坡位移分解预测中的平滑先验分析方法[J].水文地质工程地质,2014,41(5):95-100.Huang Haifeng,Yi Wu,Yi Qinglin,et al.Smoothness Priors Approach in Displacement Decomposition and Prediction of Landslides[J].Hydrogeology &Engineering Geology,2014,41(5):95-100.
[4] 唐鹏,陈国庆,黄润秋,等.基于物理模拟试验的岩质滑坡地表位移分析[J].水文地质工程地质,2017,44(4):105-110.Tang Peng,Chen Guoqing,Huang Runqiu,et al.Surface Displacement Analysis of Rock Slope Based on Physical Simulation Tests[J].Hydrogeology &Engineering Geology,2017,44(4):105-110.
[5] 张俊,殷坤龙,王佳佳,等.基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J].岩石力学与工程学报,2015,34(2):382-391.Zhang Jun, Yin Kunlong, Wang Jiajia,et al.Displacement Prediction of Baishuihe Landslide Based on Time Series and PSO-SVR Model[J].Chinese Journal of Rock Mechanics and Engineering,2015,34(2):382-391.
[6] 龙万学,林剑,许湘华,等.Verhulst反函数模型滑坡起始预测时刻的选择[J].岩石力学与工程学报,2008,27(增刊1):3298-3304.Long Wanxue,Lin Jian,Xu Xianghua,et al.Selection of Initial Prediction Time for Landslide with Verhulst Inverse Function Model[J].Chinese Journal of Rock Mechanics and Engineering,2008,27(Sup.1):3298-3304.
[7] Lian C,Zeng Z G,Yao W,et al.Displacement Prediction Model of Landslide Based on a Modified Ensemble Empirical Mode Decomposition and Extreme Learning Machine[J].Natural Hazards,2013,66(2):759-771.
[8] Lian C,Zeng Z G,Yao W,et al.Ensemble of Extreme Learning Machine for Landslide Displacement Prediction Based on Time Series Analysis[J].Neural Computing &Applications,2014,24(1):99-107.
[9] 王萌,姜元俊,黄栋,等.基于小流域的地震扰动区降型滑坡泥石流危险性评价方法[J].吉林大学学报(地球科学版),2015,45(6):1781-1788.Wang Meng,Jiang Yuanjun,Huang Dong,et al.Hazard Assessment on Rainfall-Triggered Landslide and Debris Flow in the Seismic Disturbance Area at Watershed Level[J].Journal of Jinlin University(Earth Science Edition),2015,45(6):1781-1788.
[10] Zhai J H,Wang J G,Hu W X.Combination of OSELM Classifiers with Fuzzy Integral for Large Scale Classification[J].Journal of Intelligent &Fuzzy Systems,2015,28(5):2257-2268.
[11] 徐则民,梅雪峰,王礼荣,等.滑坡预警中的降水时空变异性:以云南头寨沟为例[J].吉林大学学报(地球科学版),2017,47(1):154-162.Xu Zemin,Mei Xuefeng,Wang Lirong,et al.Precipitation Temporal and Variability of Landslide Earthy Warning Research:A Case Study on Touzhai Gully in Yunnan Province[J].Journal of Jinlin University(Earth Science Edition),2017,47(1):154-162.
[12] 沈玲玲,刘连友,许冲,等.基于多模型的滑坡易发性评价:以甘肃岷县地震滑坡为例[J].工程地质学报,2016,24(1):19-28.Sheng Lingling,Liu Lianyou,Xu Chong,et al.Multi-Models Based Landslides Susceptibility EvaluationIllustrated with Landslides Ttriggered by Minxian Earthquake[J].Journal of Engineering Geology,2016,24(1):19-28.
[13] 李艳华,林剑,龙万学,等.基于位移的滑坡临滑时刻多模型综合预测模糊积分方法[J].自然灾害学报,2013,22(4):209-212.Li Yanhua,Lin Jian,Long Wangxue,et al.Displacement Based Fuzzy Integral Method for Multi-Model Comprehensive Forecast of Landslide-Approaching Time[J].Journal of Natural Disasters,2013,22(4):209-212.
[14] Yin X X,Lin Y G,Li W,et al.A Novel Fuzzy Integral Sliding Mode Current Control Strategy for Maximizing Wind Power Extraction and Eliminating Voltage Harmonics[J].Energy,2015,85:677-686.
[15] Yoo B S,Kim J H.Fuzzy Integral-Based Gaze Control of a Robotic Head for Human Robot Interaction[J].IEEE Transactions on Cybernetics,2015,45(9):1769-1783.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |