钟山县山洪地质灾害风险评估与预警
|
摘要
为研究山洪地质灾害的智能评估与预警,以亚热带典型地区中国广西壮族自治区钟山县为研究对象,以遥感影像和实地调查为数据源,在ENVI和ArcGIS平台上处理遥感影像、光谱数据和DEM数据,全方位获取研究区的地形坡度、植被覆盖指数、土壤松散系数、山谷山脊类别、降雨量等数据。量化数据作为输入因子,以山洪灾害风险等级为输出因子,建立钟山县山洪地质灾害风险等级评价的广义回归神经网络模型。模型经过历史数据训练后,具有较强的自学习功能,通过实例验算,模型计算出的风险等级与实际风险等级吻合较好,所建模型适用于钟山县全境的山洪地质灾害风险等级评价。通过无线传输技术输入GPS定位的经纬度到模型中,自动匹配该点的神经网络输入数据,再经模型运算输出灾害风险等级,在用户终端上输出警示信息,从而实现对山洪地质灾害的实时智能预警,在钟山县具有较好的应用效果。
To study the intelligent assessment and early warning of mountain flood geological disaster,Zhongshan County of Guangxi Zhuang Autonomous Region was taken as the research sample.Remote sensing images and actual surveys were used as data sources.Remote sensing images,spectral data and DEM data were processed on ENVI and ArcGIS platforms.The data of the study area were obtained,such as slope,NDVI,soil looseness coefficient,valley and ridge classification and rainfall.These data were taken as the input factors,the risk degree of the mountain flood geological disaster was taken as the output factor.A generalized regression neural network model for risk assessment of mountain flood geological disaster in Zhongshan County was established.After the training of historical data,the model has a strong self-learning function.By case checking,the risk degree calculated by the model is in good agreement with the actual risk degree.The model can be applied to the assessment of the risk degree of the mountain flood geological disaster in Zhongshan County.Through the wireless transmission technology to enter GPS positioning latitude and longitude to the model,the model platform can receive and automatically match the neural network input data,and output the disaster risk degree by the model operation,and output the warning on the user′s terminal,so as to realize the real-time intelligent early warning of the mountain flood geological disaster,which has a good application effect in Zhongshan County.
To study the intelligent assessment and early warning of mountain flood geological disaster,Zhongshan County of Guangxi Zhuang Autonomous Region was taken as the research sample.Remote sensing images and actual surveys were used as data sources.Remote sensing images,spectral data and DEM data were processed on ENVI and ArcGIS platforms.The data of the study area were obtained,such as slope,NDVI,soil looseness coefficient,valley and ridge classification and rainfall.These data were taken as the input factors,the risk degree of the mountain flood geological disaster was taken as the output factor.A generalized regression neural network model for risk assessment of mountain flood geological disaster in Zhongshan County was established.After the training of historical data,the model has a strong self-learning function.By case checking,the risk degree calculated by the model is in good agreement with the actual risk degree.The model can be applied to the assessment of the risk degree of the mountain flood geological disaster in Zhongshan County.Through the wireless transmission technology to enter GPS positioning latitude and longitude to the model,the model platform can receive and automatically match the neural network input data,and output the disaster risk degree by the model operation,and output the warning on the user′s terminal,so as to realize the real-time intelligent early warning of the mountain flood geological disaster,which has a good application effect in Zhongshan County.
引文
[1]张凯,韦凤年,尚全民,等.提高山洪灾害防御能力撑起人民群众“生命的保护伞”[J].中国水利,2012(3):46-48.
[2]邱瑞田.山洪灾害防治县级非工程措施项目建设进展及成效[J].中国水利,2012(23):7-9.
[3]Wu M C,Lin G F.An Hourly Streamflow Forecasting Model Coupled with an Enforced Learning Strategy[J].Water,2015,7(11):5876-5895.
[4]Yang T H,Chen Y C,Chang Y C,et al.Comparison of different grid cell ordering approaches in a simplified inundation model[J].Water,2015,7(2):438-454.
[5]Thierion V,Ayral P A,Jacob G,et al.Grid technology reliability for flash flood forecasting:end-user assessment[J].Journal of Grid Computing,2011,9(3):405-422.
[6]Hapuarachchi H A P,Wang Q J,Pagano T C.A review of advances in flash flood forecasting[J].Hydrological Processes,2011,25(18):2771-2784.
[7]刘国忠,黄嘉宏,曾小团,等.引发广西两次严重山洪地质灾害的暴雨过程分析[J].气象,2013,39(11):1402-1412.
[8]胡娟,闵颖,李华宏,等.云南省山洪地质灾害气象预报预警方法研究[J].灾害学,2014,29(1):62-66.
[9]陈殿强,王来贵,郝哲.辽宁省山洪地质灾害特点及其分布规律研究[J].渤海大学学报:自然科学版,2008,29(2):105-112.
[10]吴兴国.广西前汛期暴雨天气过程的特征分析[J].广西气象,2000,21(2):7-8.
[11]陈明.MATLAB神经网络原理与实例精解[M].北京:清华大学出版社,2013.
[12]朱凯,王正林.精通MATLAB神经网络[M].北京:电子工业出版社,2010.
[13]Cigizoglu H K.Generalized regression neural network in monthly flow forecasting[J].Civil Engineering and Environmental Systems,2005,22(2):71-81.
[14]Cigizoglu H K,Alp M.Generalized regression neural network in modelling river sediment yield[J].Advances in Engineering Software,2006,37(2):63-68.
[15]KisO.A combined generalized regression neural network wavelet model for monthly streamflow prediction[J].KSCE Journal of Civil Engineering,2011,15(8):1469-1479.
[16]Panda B N,Bahubalendruni M V A R,Biswal B B.A general regression neural network approach for the evaluation of compressive strength of FDM prototypes[J].Neural Computing and Applications,2015,26(5):1129-1136.
[17]丛沛桐,祖元刚,于景华,等.根据植物茎叶图像模拟根系图像的人工神经网络算法[J].生态学报,2002,22(2):163-168.
[18]聂江力,丛沛桐,祖元刚,等.用人工智能计算技术估测东北地区北五味子果实资源量[J].植物研究,2003,23(2):245-251.
[2]邱瑞田.山洪灾害防治县级非工程措施项目建设进展及成效[J].中国水利,2012(23):7-9.
[3]Wu M C,Lin G F.An Hourly Streamflow Forecasting Model Coupled with an Enforced Learning Strategy[J].Water,2015,7(11):5876-5895.
[4]Yang T H,Chen Y C,Chang Y C,et al.Comparison of different grid cell ordering approaches in a simplified inundation model[J].Water,2015,7(2):438-454.
[5]Thierion V,Ayral P A,Jacob G,et al.Grid technology reliability for flash flood forecasting:end-user assessment[J].Journal of Grid Computing,2011,9(3):405-422.
[6]Hapuarachchi H A P,Wang Q J,Pagano T C.A review of advances in flash flood forecasting[J].Hydrological Processes,2011,25(18):2771-2784.
[7]刘国忠,黄嘉宏,曾小团,等.引发广西两次严重山洪地质灾害的暴雨过程分析[J].气象,2013,39(11):1402-1412.
[8]胡娟,闵颖,李华宏,等.云南省山洪地质灾害气象预报预警方法研究[J].灾害学,2014,29(1):62-66.
[9]陈殿强,王来贵,郝哲.辽宁省山洪地质灾害特点及其分布规律研究[J].渤海大学学报:自然科学版,2008,29(2):105-112.
[10]吴兴国.广西前汛期暴雨天气过程的特征分析[J].广西气象,2000,21(2):7-8.
[11]陈明.MATLAB神经网络原理与实例精解[M].北京:清华大学出版社,2013.
[12]朱凯,王正林.精通MATLAB神经网络[M].北京:电子工业出版社,2010.
[13]Cigizoglu H K.Generalized regression neural network in monthly flow forecasting[J].Civil Engineering and Environmental Systems,2005,22(2):71-81.
[14]Cigizoglu H K,Alp M.Generalized regression neural network in modelling river sediment yield[J].Advances in Engineering Software,2006,37(2):63-68.
[15]KisO.A combined generalized regression neural network wavelet model for monthly streamflow prediction[J].KSCE Journal of Civil Engineering,2011,15(8):1469-1479.
[16]Panda B N,Bahubalendruni M V A R,Biswal B B.A general regression neural network approach for the evaluation of compressive strength of FDM prototypes[J].Neural Computing and Applications,2015,26(5):1129-1136.
[17]丛沛桐,祖元刚,于景华,等.根据植物茎叶图像模拟根系图像的人工神经网络算法[J].生态学报,2002,22(2):163-168.
[18]聂江力,丛沛桐,祖元刚,等.用人工智能计算技术估测东北地区北五味子果实资源量[J].植物研究,2003,23(2):245-251.