结合GA-BP神经网络的GPS-IR雪深反演
|
摘要
针对传统雪深反演中出现的系统偏差和跳变问题,该文提出一种结合遗传算法-反向传播(GA-BP)神经网络的雪深反演方法。首先通过二次项拟合有效分离出信噪比残差,进而对变换单位后的信噪比残差进行频谱分析,计算得到初步雪深值。最后,建立基于初步雪深值的GA-BP神经网络优化模型。以美国板块边界观测计划(PBO)提供的监测数据为例,并与传统方法对比分析,结果表明:采用GA-BP神经网络不仅能够削弱初步反演结果中出现的系统偏差,还能有效消除反演过程出现的跳变现象。采用PRN09和PRN24卫星反演,RMSE和MAE均分别小于0.083m和0.065m,R~2有了明显提高,优于未处理初始雪深的情况。
Aiming at the problem of system deviation and cycle slips in traditional snow depth retrieval,a method of snow depth retrieval combining genetic algorithms-back propagation(GA-BP)neural network was proposed in this paper.Firstly,the residual of signal to noise ratio(SNR)was separated effectively by quadratic item fitting method from original sequence,and then the spectrum analysis for the SNR residual which had been transformed unit was carried out,and the initial snow depth was calculated,and finally,a GA-BP neural network optimization model based on the initial snow depth value was established.Taking the monitoring data provided by plate boundary observatory(PBO)as an example,and compared it with traditional methods.The results showed that using GA-BP neural network could not only weaken the systematic bias in the preliminary inversion results,but also effectively eliminate the cycle slips phenomenon in the inversion process.Using the PRN09 and PRN24 satellites for inversion,the root mean square error(RMSE)and mean absolute error(MAE)were less than 0.083 mand 0.065 mrespectively,and R~2 was significantly improved,which was superior to the untreated case.
Aiming at the problem of system deviation and cycle slips in traditional snow depth retrieval,a method of snow depth retrieval combining genetic algorithms-back propagation(GA-BP)neural network was proposed in this paper.Firstly,the residual of signal to noise ratio(SNR)was separated effectively by quadratic item fitting method from original sequence,and then the spectrum analysis for the SNR residual which had been transformed unit was carried out,and the initial snow depth was calculated,and finally,a GA-BP neural network optimization model based on the initial snow depth value was established.Taking the monitoring data provided by plate boundary observatory(PBO)as an example,and compared it with traditional methods.The results showed that using GA-BP neural network could not only weaken the systematic bias in the preliminary inversion results,but also effectively eliminate the cycle slips phenomenon in the inversion process.Using the PRN09 and PRN24 satellites for inversion,the root mean square error(RMSE)and mean absolute error(MAE)were less than 0.083 mand 0.065 mrespectively,and R~2 was significantly improved,which was superior to the untreated case.
引文
[1] SHI J C,DOZIER J.Estimation of snow water equivalence using SIR-C/X-SAR,Part I:inferring snow density and subsurface properties[J].IEEE Transactions on Geoscience and Remote Sensing,2000,38(6):2465-2474.
[2] ESTILOW T W,YOUNG A H,ROBINSON D A.A long-term northern hemisphere snow cover extent data record for climate studies and monitoring[J].Earth System Science Data,2015,7(1):137-142.
[3] GUTMANN E,LARSON K M,WILLIAMS M W,et al.Snow measurement by GPS interferometric reflectometry:an evaluation at Niwot Ridge,Colorado[J].Hydrological Processes,2012,26(19):2951-2961.
[4] BONIFACE K,BRAUN J J,MCCREIGHT J L,et al.Comparison of snow data assimilation system with GPS reflectometry snow depth in the western United States[J].Hydrological Processes,2015,29(10):2425-2437.
[5] LARSON K M,NIEVINSKI F G.GPS snow sensing:results from the EarthScope Plate Boundary Observatory[J].GPS Solutions,2013,17(1):41-52.
[6]戴凯阳,张双成,李振宇,等.利用GPS的SNR观测值进行雪深监测研究[J].大地测量与地球动力学,2016,36(6):525-528.(DAI Kaiyang,ZHANG Shuangcheng,LI Zhenyu,et al.Snow depth detection with GPS SNR observations[J].Journal of Geodesy and Geodynamics,2016,36(6):525-528.)
[7]税广通,郑南山,周方平,等.一种GPS多路径反射信号的雪深反演[J].测绘科学,2017,42(10):55-59,72.(SHUI Guangtong,ZHENG Nanshan,ZHOU Fangping,et al.Inversion of snow depth based on GPS multipath signals[J].Science of Surveying and Mapping,2017,42(10):55-59,72.)
[8]王敏,柴洪洲,刘鸣,等.一种顾及GEO卫星多路径效应影响的BDS长距离相对定位方法[J].测绘科学技术学报,2016,33(2):121-126.(WANG Min,CHAI Hongzhou,LIU Ming,et al.A method of BDS relative positioning over long baseline considering the influence of multipath effect from GEO satellite[J].Journal of Geomatics Science and Technology,2016,33(2):121-126.)
[9]吉绪发,卢辰龙.GPS多路径误差滤波方法比较研究[J].测绘通报,2015(4):10-13.(JI Xufa,LU Chenlong.Comparing different filtering methods for mitigation of GPS multipath error[J].Bulletin of Surveying and Mapping,2015(4):10-13.)
[10]肖胜昌,王冲,丁学智,等.GPS一机多天线实时监测系统在小湾水电站中的应用[J].水力发电,2006,32(11):22-23.(XIAO Shengchang,WANG Chong,DING Xuezhi,et al.Application of real time monitoring system with multi-antenna GPS in the Xiaowan hydroelectric project[J].Water Power,2006,32(11):22-23.)
[11]吴雨航,陈秀万,吴才聪.利用信噪比削弱多路径误差的方法研究[J].武汉大学学报(信息科学版),2008,33(8):842-845.(WU Yuhang,CHEN Xiuwan,WU Caicong.Mitigation of multi-path effect using SNR values[J].Geomatics and Information Science of Wuhan University,2008,33(8):842-845.)
[12]尹为松,陶庭叶,邓清军,等.遗传算法优化的GPS对流层延迟内插算法[J].测绘科学,2016,41(1):180-184.(YIN Weisong,TAO Tingye,DENG Qingjun,et al.Interpolation algorithm of GPS tropospheric delay based on GA-BP[J].Science of Surveying and Mapping,2016,41(1):180-184.)
[13]周志宇.基于EMD与GA-BP神经网络的短期负荷预测[J].电测与仪表,2013,50(4):17-21.(ZHOU Zhiyu.Short-term load forecasting based on the EMD and GABP neural network[J].Electrical Measurement&Instrumentation,2013,50(4):17-21.)
[14]王雪红,刘晓青,陶海龙,等.优化BP神经网络的位移预测模型[J].水利水运工程学报,2014(2):38-42.(WANG Xuehong,LIU Xiaoqing,TAO Hailong,et al.A displacement prediction model based on improved particle swarm-BP neural network algorithm[J].Hydro-Science and Engineering,2014(2):38-42.)
[15]梁月吉,任超,刘立龙,等.基于EMD和GA-BP神经网络的大坝变形预测[J].桂林理工大学学报,2015,35(1):111-116.(LIANG Yueji,REN Chao,LIU Lilong,et al.Dam deformation prediction based on EMD and GA-BP neural network[J].Journal of Guilin University of Technology,2015,35(1):111-116.)
[2] ESTILOW T W,YOUNG A H,ROBINSON D A.A long-term northern hemisphere snow cover extent data record for climate studies and monitoring[J].Earth System Science Data,2015,7(1):137-142.
[3] GUTMANN E,LARSON K M,WILLIAMS M W,et al.Snow measurement by GPS interferometric reflectometry:an evaluation at Niwot Ridge,Colorado[J].Hydrological Processes,2012,26(19):2951-2961.
[4] BONIFACE K,BRAUN J J,MCCREIGHT J L,et al.Comparison of snow data assimilation system with GPS reflectometry snow depth in the western United States[J].Hydrological Processes,2015,29(10):2425-2437.
[5] LARSON K M,NIEVINSKI F G.GPS snow sensing:results from the EarthScope Plate Boundary Observatory[J].GPS Solutions,2013,17(1):41-52.
[6]戴凯阳,张双成,李振宇,等.利用GPS的SNR观测值进行雪深监测研究[J].大地测量与地球动力学,2016,36(6):525-528.(DAI Kaiyang,ZHANG Shuangcheng,LI Zhenyu,et al.Snow depth detection with GPS SNR observations[J].Journal of Geodesy and Geodynamics,2016,36(6):525-528.)
[7]税广通,郑南山,周方平,等.一种GPS多路径反射信号的雪深反演[J].测绘科学,2017,42(10):55-59,72.(SHUI Guangtong,ZHENG Nanshan,ZHOU Fangping,et al.Inversion of snow depth based on GPS multipath signals[J].Science of Surveying and Mapping,2017,42(10):55-59,72.)
[8]王敏,柴洪洲,刘鸣,等.一种顾及GEO卫星多路径效应影响的BDS长距离相对定位方法[J].测绘科学技术学报,2016,33(2):121-126.(WANG Min,CHAI Hongzhou,LIU Ming,et al.A method of BDS relative positioning over long baseline considering the influence of multipath effect from GEO satellite[J].Journal of Geomatics Science and Technology,2016,33(2):121-126.)
[9]吉绪发,卢辰龙.GPS多路径误差滤波方法比较研究[J].测绘通报,2015(4):10-13.(JI Xufa,LU Chenlong.Comparing different filtering methods for mitigation of GPS multipath error[J].Bulletin of Surveying and Mapping,2015(4):10-13.)
[10]肖胜昌,王冲,丁学智,等.GPS一机多天线实时监测系统在小湾水电站中的应用[J].水力发电,2006,32(11):22-23.(XIAO Shengchang,WANG Chong,DING Xuezhi,et al.Application of real time monitoring system with multi-antenna GPS in the Xiaowan hydroelectric project[J].Water Power,2006,32(11):22-23.)
[11]吴雨航,陈秀万,吴才聪.利用信噪比削弱多路径误差的方法研究[J].武汉大学学报(信息科学版),2008,33(8):842-845.(WU Yuhang,CHEN Xiuwan,WU Caicong.Mitigation of multi-path effect using SNR values[J].Geomatics and Information Science of Wuhan University,2008,33(8):842-845.)
[12]尹为松,陶庭叶,邓清军,等.遗传算法优化的GPS对流层延迟内插算法[J].测绘科学,2016,41(1):180-184.(YIN Weisong,TAO Tingye,DENG Qingjun,et al.Interpolation algorithm of GPS tropospheric delay based on GA-BP[J].Science of Surveying and Mapping,2016,41(1):180-184.)
[13]周志宇.基于EMD与GA-BP神经网络的短期负荷预测[J].电测与仪表,2013,50(4):17-21.(ZHOU Zhiyu.Short-term load forecasting based on the EMD and GABP neural network[J].Electrical Measurement&Instrumentation,2013,50(4):17-21.)
[14]王雪红,刘晓青,陶海龙,等.优化BP神经网络的位移预测模型[J].水利水运工程学报,2014(2):38-42.(WANG Xuehong,LIU Xiaoqing,TAO Hailong,et al.A displacement prediction model based on improved particle swarm-BP neural network algorithm[J].Hydro-Science and Engineering,2014(2):38-42.)
[15]梁月吉,任超,刘立龙,等.基于EMD和GA-BP神经网络的大坝变形预测[J].桂林理工大学学报,2015,35(1):111-116.(LIANG Yueji,REN Chao,LIU Lilong,et al.Dam deformation prediction based on EMD and GA-BP neural network[J].Journal of Guilin University of Technology,2015,35(1):111-116.)
© 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 |