声速剖面反演预测方法
|
摘要
利用2006—2017年我国南海部分区域(112°～114°E,10°～12°N)的Argo观测数据,对该海区声速剖面进行了仿真分析和研究。在此基础上,利用遗传算法(GA)优化的径向基函数(RBF)神经网络建立反演预测模型(GA-RBF),结合海区表面实测温度和历史数据,研究了该区域2016—2017年的声速剖面实时预测情况,并获得该海区6月和12月的声速剖面平均均方根误差值为0.845 m/s和0.815 m/s;而采用平均声速剖面方法获得该海区6月和12月的声速均方根误差分别是2.393 m/s和2.176 m/s。仿真结果表明:基于GA-RBF网络模型并利用海区表面实测温度的反演预测结果更趋近实测声速剖面,该模型可用于海区垂直声速剖面的实时预测。
Based on Argo data in a region(112°～114°E, 10°～12°N) of the South China Sea from 2006 to 2017, the ocean SSP is analyzed to obtain Empirical Orthogonal Function(EOF). The inversion prediction model for ocean SSP is developed with Radial Basis Function(RBF) neural network optimized by Genetic Algorithm(GA)(GA-RBF). This model is used to inverted SSP in 2016—2017 with Sea Surface Temperature(SST). The averaged Root-Mean-Square Errors(RMSE) of inverted SSP in June and December are 0.845 m/s and 0.815 m/s with GA-RBF, and those are 2.393 m/s and 2.176 m/s with AGV. The GA-RBF model is better and it can be used to real-time forecast the SSP.
Based on Argo data in a region(112°～114°E, 10°～12°N) of the South China Sea from 2006 to 2017, the ocean SSP is analyzed to obtain Empirical Orthogonal Function(EOF). The inversion prediction model for ocean SSP is developed with Radial Basis Function(RBF) neural network optimized by Genetic Algorithm(GA)(GA-RBF). This model is used to inverted SSP in 2016—2017 with Sea Surface Temperature(SST). The averaged Root-Mean-Square Errors(RMSE) of inverted SSP in June and December are 0.845 m/s and 0.815 m/s with GA-RBF, and those are 2.393 m/s and 2.176 m/s with AGV. The GA-RBF model is better and it can be used to real-time forecast the SSP.
引文
[1] CARUTHERS J W.Fundamentals of marine acoustics[M].Amsterdam-Oxford-New York:Elsevier Scientific Publishing Company,1977:1-12.
[2] LI Y Y,DA L L,HAN M,et al.Underwater acoustic environment rapid assessment modeling and simulation[J].Journal of System Simulation,2012,24(6):1156-1160.
[3] LI Y Y,DA L L,SONG J.Research on underwater acoustic environment simulation and visualization[J].Journal of Geomatics Science & Technology,2009,26(1):8-11.
[4] GROSSO V A D.New equations for the speed of sound in natural waters (with comparisons to other equations)[J].Journal of the Acoustical Society of America,1974,56(4):1084-1091.
[5] DENISOV D A,ABRAMOV A V,ABRAMOVA E P.A method for calculating the speed of sound in seawater[J].Acoustical Physics,2003,49(4):413-419.
[6] CARNES M R,MITCHELL J L.Synthetic temperature profiles derived from geosat altimetry:comparison with air-dropped expendable bathythermograph profiles[J].Journal of Geophysical Research Oceans,1990,95(c10):17979-17992.
[7] ZHOU H.Inversion of sound speed profile in dynamic ocean environment[D].Hangzhou:Zhejiang University,2013.周辉.动态海洋环境下声速剖面的反演方法研究[D].杭州:浙江大学,2013.
[8] MUNK W,WORCESTER P,WUNSCH C.Ocean acoustic tomography[M].UK:Cambridge University Press,1995:6-58.
[9] LEBLANC L R,MIDDLETON F H.An underwater acoustic sound velocity data model[J].The Journal of the Acoustical Society of America.1980,67(6):2055-2062.
[10] WANG Y Y.The sound speed profile reconstruction and it’s software realization based on decomposition of empirical orthogonal function[D].Harbin:Harbin Engineering University,2011.王延意.基于经验正交函数分解的声速剖面重构及软件实现[D].哈尔滨:哈尔滨工程大学,2011.
[11] ZHANG X,ZHANG Y G,ZHANG S J,et al.A comparison between the EOF and GDEM methods for reconstruction of sound speed profile[J].Applied Acoustics,2010,29(2):115-121.张旭,张永刚,张胜军,等.经验正交函数与广义数值环境模式重构声速剖面的比较[J].应用声学,2010,29(2):115-121.
[12] DAVIS R E.Predictability of sea surface temperature and sea level pressure anomalies over the North Pacific Ocean[J].Journal of Physical Oceanography,1976,6(3):249-266.
[13] PARK J C,KENNEDY R M.Remote sensing of ocean sound speed profiles by a perceptron neural network[J].IEEE Journal of Oceanic Engineering,1996,21(2):216-224.
[14] ZHOU S H,ZHANG M Y,ZHOU Y P,et al.Study on orthogonal functions expression and prediction of the sound speed field[J].Marine Science Bulletin,1999,18(5):27-34.周士弘,张茂有,周曰鹏,等.海洋声速场的经验正交函数描述及声速剖面预报[J].海洋通报,1999,18(5):27-34.
[15] HE L,LI Z L,PENG C H,et al.Inversion for sound speed profiles in the northern of South China Sea[J].Scientia Sinica:Physical,Mechanics,Astronomy,2011,41(1):49-57.何利,李整林,彭朝晖,等.南海北部海水声速剖面声学反演[J].中国科学:物理学力学天文学,2011,41(1):49-57.
[16] HUANG Q W.The genetic algorithm’s application in the sea water acoustic impedance inversion[D].Qingdao:Ocean University of China,2014.黄庆文.遗传算法在海洋水体波阻抗反演中的应用[D].青岛:中国海洋大学,2014.
[17] TANG J F.Research on inversion of sound speed profile in the ocean[D].Harbin:Harbin Engineering University,2006.唐俊峰.海水中的声速剖面反演研究[D].哈尔滨:哈尔滨工程大学,2006.
[18] AI R F,CHENG J,QUYANG J,et al.On-line retrieval methodology for sound speed profile of sea area[J].Journal of Computer Applications,2015,35(Suppl.1):327-330,338.艾锐峰.程杰,欧阳军,等.海区声速剖面的现场反演方法[J].计算机应用,2015,35(增1):327-330,338.
[19] NAJAH A,El-SHAFIE A,KARIM O A,et al.Application of artificial neural networks for water quality prediction[J].Neural Computing & Applications,2013,22(1):187-201.
[20] GAO Y H.The RBF neural network optimization and application based on hybrid hierarchy genetic algorithm[D].Chengdu:Sichuan University,2004.高彦荷.基于混合递阶遗传算法的RBF神经网络优化及应用[D].成都:四川大学,2004.
[21] HAN H G,CHEN Q L,QIAO J F.An efficient self-organizing RBF neural network for water quality prediction[J].Neural Networks,2011,24(7):717.
[22] COELHO L D S,SANTOS A A P.A RBF neural network model with GARCH errors:application to electricity price forecasting[J].Electric Power Systems Research,2011,81(1):74-83.
[23] LIU J K.Intelligent control[M].Beijing:Publishing House of Electronics Industry,2014:236-240.刘金琨.智能控制[M].北京:电子工业出版社,2014:236-240.
[24] DHOMPS A L,GUINEHUT S,TRAON P Y L,et al.A global comparison of Argo and satellite altimetry observations[J].Ocean Science,2011,7(2):175-183.
[25] China Argo Real-time Data Center.ARGO newsletter:No.47[EB/OL].[2017-09-28].http://www.argo.org.cn.中国Argo实时资料中心.ARGO简讯:第47期[EB/OL].[2017-09-28].http://www.argo.org.cn.
[26] POWELL M J D.Radial basis functions for multivariable interpolation:a review[M]//MASON J,COX M.Algorithms for approximation.Oxford:Clarendon Press,1987:143-167.
[27] BROOMHEAD D S,LOWE D.Radial basis functions,multi-variable functional interpolation and adaptive networks[J].Advances in Neural Information Processing Systems,1988,rsre-memo-4148:728-734.
[28] QIAO J F,HAN H G.Optimal structure design for RBFNN structure[J].Acta Automatica Sinica,2010(6):865-872.乔俊飞,韩红桂.RBF神经网络的结构动态优化设计[J].自动化学报,2010(6):865-872.
[29] LIU J K.Intelligent control[M].Beijing:Publishing House of Electronics Industry,2014:132-142.刘金琨.智能控制[M].北京:电子工业出版社,2014:132-142.
[30] WEN X,LI X,ZHANG X W,et al.The application of MATLAB neural network[M].Beijing:National Defense Industry Press,2015:205-212.闻新,李新,张兴旺,等.应用MATLAB实现神经网络[M].北京:国防工业出版社,2015:205-212.
[31] HOLLAND J H.Outline for a logical theory of adaptive systems[J].Journal of the America,1962,9(3):297-314.
[32] GUO P F.Research on the optimized prediction model of water quality based on RBF neural network[D].Nanchang:East China Jiaotong University,2013.郭鹏飞.基于改进RBF神经网络算法的水质预测模型研究[D].南昌:华东交通大学,2013.
[33] SHETA A F,DE JONG K.Time-series forecasting using GA-tuned radial basis functions[J].Information Sciences,2001,133(3/4):221-228.
[2] LI Y Y,DA L L,HAN M,et al.Underwater acoustic environment rapid assessment modeling and simulation[J].Journal of System Simulation,2012,24(6):1156-1160.
[3] LI Y Y,DA L L,SONG J.Research on underwater acoustic environment simulation and visualization[J].Journal of Geomatics Science & Technology,2009,26(1):8-11.
[4] GROSSO V A D.New equations for the speed of sound in natural waters (with comparisons to other equations)[J].Journal of the Acoustical Society of America,1974,56(4):1084-1091.
[5] DENISOV D A,ABRAMOV A V,ABRAMOVA E P.A method for calculating the speed of sound in seawater[J].Acoustical Physics,2003,49(4):413-419.
[6] CARNES M R,MITCHELL J L.Synthetic temperature profiles derived from geosat altimetry:comparison with air-dropped expendable bathythermograph profiles[J].Journal of Geophysical Research Oceans,1990,95(c10):17979-17992.
[7] ZHOU H.Inversion of sound speed profile in dynamic ocean environment[D].Hangzhou:Zhejiang University,2013.周辉.动态海洋环境下声速剖面的反演方法研究[D].杭州:浙江大学,2013.
[8] MUNK W,WORCESTER P,WUNSCH C.Ocean acoustic tomography[M].UK:Cambridge University Press,1995:6-58.
[9] LEBLANC L R,MIDDLETON F H.An underwater acoustic sound velocity data model[J].The Journal of the Acoustical Society of America.1980,67(6):2055-2062.
[10] WANG Y Y.The sound speed profile reconstruction and it’s software realization based on decomposition of empirical orthogonal function[D].Harbin:Harbin Engineering University,2011.王延意.基于经验正交函数分解的声速剖面重构及软件实现[D].哈尔滨:哈尔滨工程大学,2011.
[11] ZHANG X,ZHANG Y G,ZHANG S J,et al.A comparison between the EOF and GDEM methods for reconstruction of sound speed profile[J].Applied Acoustics,2010,29(2):115-121.张旭,张永刚,张胜军,等.经验正交函数与广义数值环境模式重构声速剖面的比较[J].应用声学,2010,29(2):115-121.
[12] DAVIS R E.Predictability of sea surface temperature and sea level pressure anomalies over the North Pacific Ocean[J].Journal of Physical Oceanography,1976,6(3):249-266.
[13] PARK J C,KENNEDY R M.Remote sensing of ocean sound speed profiles by a perceptron neural network[J].IEEE Journal of Oceanic Engineering,1996,21(2):216-224.
[14] ZHOU S H,ZHANG M Y,ZHOU Y P,et al.Study on orthogonal functions expression and prediction of the sound speed field[J].Marine Science Bulletin,1999,18(5):27-34.周士弘,张茂有,周曰鹏,等.海洋声速场的经验正交函数描述及声速剖面预报[J].海洋通报,1999,18(5):27-34.
[15] HE L,LI Z L,PENG C H,et al.Inversion for sound speed profiles in the northern of South China Sea[J].Scientia Sinica:Physical,Mechanics,Astronomy,2011,41(1):49-57.何利,李整林,彭朝晖,等.南海北部海水声速剖面声学反演[J].中国科学:物理学力学天文学,2011,41(1):49-57.
[16] HUANG Q W.The genetic algorithm’s application in the sea water acoustic impedance inversion[D].Qingdao:Ocean University of China,2014.黄庆文.遗传算法在海洋水体波阻抗反演中的应用[D].青岛:中国海洋大学,2014.
[17] TANG J F.Research on inversion of sound speed profile in the ocean[D].Harbin:Harbin Engineering University,2006.唐俊峰.海水中的声速剖面反演研究[D].哈尔滨:哈尔滨工程大学,2006.
[18] AI R F,CHENG J,QUYANG J,et al.On-line retrieval methodology for sound speed profile of sea area[J].Journal of Computer Applications,2015,35(Suppl.1):327-330,338.艾锐峰.程杰,欧阳军,等.海区声速剖面的现场反演方法[J].计算机应用,2015,35(增1):327-330,338.
[19] NAJAH A,El-SHAFIE A,KARIM O A,et al.Application of artificial neural networks for water quality prediction[J].Neural Computing & Applications,2013,22(1):187-201.
[20] GAO Y H.The RBF neural network optimization and application based on hybrid hierarchy genetic algorithm[D].Chengdu:Sichuan University,2004.高彦荷.基于混合递阶遗传算法的RBF神经网络优化及应用[D].成都:四川大学,2004.
[21] HAN H G,CHEN Q L,QIAO J F.An efficient self-organizing RBF neural network for water quality prediction[J].Neural Networks,2011,24(7):717.
[22] COELHO L D S,SANTOS A A P.A RBF neural network model with GARCH errors:application to electricity price forecasting[J].Electric Power Systems Research,2011,81(1):74-83.
[23] LIU J K.Intelligent control[M].Beijing:Publishing House of Electronics Industry,2014:236-240.刘金琨.智能控制[M].北京:电子工业出版社,2014:236-240.
[24] DHOMPS A L,GUINEHUT S,TRAON P Y L,et al.A global comparison of Argo and satellite altimetry observations[J].Ocean Science,2011,7(2):175-183.
[25] China Argo Real-time Data Center.ARGO newsletter:No.47[EB/OL].[2017-09-28].http://www.argo.org.cn.中国Argo实时资料中心.ARGO简讯:第47期[EB/OL].[2017-09-28].http://www.argo.org.cn.
[26] POWELL M J D.Radial basis functions for multivariable interpolation:a review[M]//MASON J,COX M.Algorithms for approximation.Oxford:Clarendon Press,1987:143-167.
[27] BROOMHEAD D S,LOWE D.Radial basis functions,multi-variable functional interpolation and adaptive networks[J].Advances in Neural Information Processing Systems,1988,rsre-memo-4148:728-734.
[28] QIAO J F,HAN H G.Optimal structure design for RBFNN structure[J].Acta Automatica Sinica,2010(6):865-872.乔俊飞,韩红桂.RBF神经网络的结构动态优化设计[J].自动化学报,2010(6):865-872.
[29] LIU J K.Intelligent control[M].Beijing:Publishing House of Electronics Industry,2014:132-142.刘金琨.智能控制[M].北京:电子工业出版社,2014:132-142.
[30] WEN X,LI X,ZHANG X W,et al.The application of MATLAB neural network[M].Beijing:National Defense Industry Press,2015:205-212.闻新,李新,张兴旺,等.应用MATLAB实现神经网络[M].北京:国防工业出版社,2015:205-212.
[31] HOLLAND J H.Outline for a logical theory of adaptive systems[J].Journal of the America,1962,9(3):297-314.
[32] GUO P F.Research on the optimized prediction model of water quality based on RBF neural network[D].Nanchang:East China Jiaotong University,2013.郭鹏飞.基于改进RBF神经网络算法的水质预测模型研究[D].南昌:华东交通大学,2013.
[33] SHETA A F,DE JONG K.Time-series forecasting using GA-tuned radial basis functions[J].Information Sciences,2001,133(3/4):221-228.