基于支持向量机和小波包的金属矿床地震数据去噪
|
摘要
针对深部找矿地震资料信噪比很低的问题,结合小波包和支持向量机的理论,提出了一种新的去噪算法.该算法首先从地震资料中找出噪声干扰极小的和噪声很强的数据,利用支持向量机进行训练学习,提取噪声和有效信号的样本特征.然后将地震资料实施小波包变换得到更加精细和不同频带的信号,利用支持向量机训练出的样本特征对小波包变换后的数据进行分类提取出有效的信号.最后将有效信号重构还原为地震信号.文章最后通过对实际的金属矿床地震资料进行了去噪,并与其他去噪算法进行比较.结果表明,该算法在理论上是正确的,实际应用效果也是成功的.
A new de-noising algorithm,which is based on the combination of the theories of wavelet package and support vector machine,is raised to solve the problem of low signal-to-noise in seismic data of the metallic ore deposit.In this algorithm,firstly,data with minimal noisy hindrance and data with loud noise would be found out from seismic data,and by using support vector machine training,sample characters about noise and effective signals would be extracted.Then,through implementing the wavelet package transform on the seismic data and making use of the sample characters trained by support vector machine to classify the data after wavelet packet transform effective signals would be extracted.Lastly,these effective signals would be reconstituted to restore the seismic signals.At last,through de-noising practical metallic ore deposit seismic data and comparing with other de-noising algorithm.Finally through a real case analyzed,the result shows that the method is theoretically correct and application effect is successful.
A new de-noising algorithm,which is based on the combination of the theories of wavelet package and support vector machine,is raised to solve the problem of low signal-to-noise in seismic data of the metallic ore deposit.In this algorithm,firstly,data with minimal noisy hindrance and data with loud noise would be found out from seismic data,and by using support vector machine training,sample characters about noise and effective signals would be extracted.Then,through implementing the wavelet package transform on the seismic data and making use of the sample characters trained by support vector machine to classify the data after wavelet packet transform effective signals would be extracted.Lastly,these effective signals would be reconstituted to restore the seismic signals.At last,through de-noising practical metallic ore deposit seismic data and comparing with other de-noising algorithm.Finally through a real case analyzed,the result shows that the method is theoretically correct and application effect is successful.
引文
[1]周平,施俊法.金属矿地震勘查方法评述[J].地球科学进展, 2008,23(2):120-128. Zhou P,Shi J F,Review on seismic methods for mineral exploration [J].Advances in Earth Science,2008,23(2):120-128.
[2]孙燕,刘建明,曾庆栋,等.综合地球物理方法在某金多金属矿区找矿中的应用.地球物理学进展,2010,25(6):2096-2101. Sun Y,Liu J M,Zeng Q D,et al.Application of comprehensive geophysical methods in ore prospecting in one Au polymetallic mineralizing area.Progress in Geophysics,(in Chinese),2010, 25(6):2096-2101.
[3]严加永,滕吉文,吕庆田.深部金属矿产资源地球物理勘查与应用[J].地球物理学进展,2008,23(3):871-891. Yan J J,Teng J W,Lu Q T.Geophysical exploration and application of deep metallic ore resources[J].Progress in Geophysics(in Chinese),2008,23(3):871-891.
[4]张华军,吕宁,田连玉,等.地震资料去噪方法、技术综合评述[J].地球物理学进展,2005,20(4):1083-1091. Zhang J H,Lv N,Tian L Y,et al.An overview of the methods and techniques for seismic data noise attenuation[J].Progress in Geophysics(in Chinese),2005,20(4):1083-1091.
[5]刘建红,孟小红,李合群.西部山地复杂地震资料处理技术研究[J].地球物理学进展,2008,23(3):859-863. Liu J H,Meng X H,Li H Q.Seismic data processing in the complex mountains of western China[J].Progress in Geophysics(in Chinese),2008,23(3):859-863.
[6]Yu S,Cai X,Su Y.Seismic signal enhancement by polynomial fitting[J].Applied Geophysics,1989,1:57-65.
[7]Ghghg C L.Random noise reduction,the 54th Annual Meeting of SEG.1984.
[8]Jones I F,Levy S.Signal-to-noise ratio enhancement in multichannel seismic data via the Karhunen-Loeve transform.Geophysical Prospecting,1987,35(2):12-32.
[9]Alan R Michell,Panos G Kelamis.Efficient tau-p hyperbolic velocity filtering.Geophysics,1990,55(5):619-625.
[10]Cai T T,Low M G.Nonparametric estimation over shrinking neighborhoods:superefficiency and adaptation,The Annals of Statistics.2005,33(1):184-213.
[11]吴招才,刘天佑.地震数据去噪中的小波方法[J].地球物理学进展,2008,23(2):493-499. Wu Z C,Liu T Y.Wavelet transform methods in seismic data noise attenuation[J].Progress in Geophysics(in Chinese), 2008,23(2):493-499.
[12]马继涛,Mrinal K.Sen,陈小宏.平面波域反数据处理压制多次波方法研究.地球物理学报,2009,52(3):808-816. Ma J T,Mrinal K.Sen,Chen X H.Multiple attenuation using inverse data processing in the plane-wave domain.Chinese J. Geophys.(in Chinese),2009,52(3):808-816.
[13]Alam,A Austin J.Suppression of multiples using slant stacks. Ann.Soc.Explor.Geophys.Mtg.,1981.
[14]Zhang Rongfeng,Ulrych T J.Physical wavelet frame denoising. Geophysics,2002,68(1):225-231.
[15]陈文超,高静怀,包乾宗.基于连续小波变换的自适应面波压制方法.地球物理学报,2009,52(11):2854-2861. Chen W C,Gao J H,Bao Q Z.Adaptive attenuation of ground roll via continuous wavelet transform.Chinese J.Geophys.(in Chinese),2009,52(11):2854-2861.
[16]胡天跃,王润秋,B E White.地震资料处理中的聚束滤波方法[J].地球物理学报,2000,43(1):105-115. Hu T Y,Wang R Q,B.E.WHITE.Beamforming in seismic data processing.Chinese J.Geophys.(in Chinese),2000,43 (1):105-115.
[17]Cox H,Zeskind R M,Owen M K.Robust adaptive beamforming [J].IEEE Trans.Acoust.Speech Signal Process ing, 1987,ASSP- 35(10):1365-1376.
[18]徐晨,赵瑞珍,甘小冰.小波分析应用算法[M].北京:科学出版社,200 4. Xu C,Zhao R Z,Gan X B.Applied Algorithm of Wavelet Analysis[M].Beijing:Science Press,2004.
[19]崔锦泰.小波分析导论[M].程正兴,译.西安:西安交通大学出版社,1995. Chui J T.An introduction to wavelets[M].Cheng Zheng xing translates.Xi an:Xi an Jiaotong UniversityPress,1995.
[20]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].科学出版社,2004. Deng L Y,Tian Y J.Data Mining of new method -Support Vector Machine[M].Bei Jing:Science Press,2004.
[21]吴琼,杨长春,张文忠,肖高杰.过渡带拼接地震资料处理方法研究[J].地球物理学进展,2008,23(3):760-767. Wu Q,Yang C C,Zhang W Z,Xiao G J.Research on processing technology for matching seismic data acquired in seashore and marine prospect[J].Progress in Geophysics(in Chinese),2008,23(3):761-767.
[22]刘建红,孟小红,李合群.西部山地复杂地震资料处理技术研究[J].地球物理学进展,2008,23(3):859-863. Liu J H,Meng X H,Li H Q.Seismic data processing in the complex mountains of western China[J].Progress in Geophysics(in Chinese),2008,23(3):859-863.
[23]马义忠,于更新,符力耘.复杂地表低信噪比地震数据处理研究[J].地球物理学进展,2008,23(6):1849-1858. Ma Y Z,Yu G X,Fu L Y.Seismic processing of low-S/N ratio data from complex near surface areas in huola mountain[J]. Progress in Geophysics(in Chinese),2008,23(6):1849 - 1858.
[24]姜静清.最小二乘支持向量机算法及应用研究[D].吉林:吉林大学博士论文,2007. Jiang Jingqing.Study on Least Squares Support vector Machine and its application[D].Doctoral essay in Ji Lin University,2007
[25]张孝珍,董汉强,等.地震勘探中的去噪技术新发展[J].勘探地球物理学进展,2009,32(3):172-178. Zhang X Z,Dong H Q,et al.Advances in denoising technology in seismic exploration[J].Progress in Exploration Geophysics,2009,32(3):172-178.
[26]Nuristan Acer.A support vector machine classifier algorithm based on a perturbation method and its application to EGG beat recognition systems[J].Expert Systems with Applications 31(2006),150-158.
[27]Engin Avci.Derya Avci.A novel approach for digital radio signal classication:Wavelet packet energy-multiclass support vector machine(WPE-MSVM)[J].Expert Systems with Applications 34(2008),2140-2147.
[28]Samjin Choi.Detection of volvuli heart disorders using wavelet packet decomposition and support vector machine[J].Expert Systems with Applications 35(2008),1679-1687.
[29]勾丽敏,刘学伟,等.金属矿地震勘探技术方法研究综述～金属矿地震勘探技术及其现状[J].勘探地球物理进展,2007,30(1):16-24. Gou L M,Liu X W,et al.Review of seismic survey in mining exploration:Part Theory and reflection seismic methods[J]. Progress in Exploration Geophysics,2007,30(1):16-24.
[30]刘洋,Fomel Sergey,刘财,等.高阶seislet变换及其在随机噪声消除中的应用.地球物理学报,2009,52(8):2142-2151. Liu Y,Fomel Sergey,Liu C,et at.High-order seislet transform and its application of random noise attenuation. Chinese J.Geophys.(in Chinese),2009,52(8):2142 - 2151.
[2]孙燕,刘建明,曾庆栋,等.综合地球物理方法在某金多金属矿区找矿中的应用.地球物理学进展,2010,25(6):2096-2101. Sun Y,Liu J M,Zeng Q D,et al.Application of comprehensive geophysical methods in ore prospecting in one Au polymetallic mineralizing area.Progress in Geophysics,(in Chinese),2010, 25(6):2096-2101.
[3]严加永,滕吉文,吕庆田.深部金属矿产资源地球物理勘查与应用[J].地球物理学进展,2008,23(3):871-891. Yan J J,Teng J W,Lu Q T.Geophysical exploration and application of deep metallic ore resources[J].Progress in Geophysics(in Chinese),2008,23(3):871-891.
[4]张华军,吕宁,田连玉,等.地震资料去噪方法、技术综合评述[J].地球物理学进展,2005,20(4):1083-1091. Zhang J H,Lv N,Tian L Y,et al.An overview of the methods and techniques for seismic data noise attenuation[J].Progress in Geophysics(in Chinese),2005,20(4):1083-1091.
[5]刘建红,孟小红,李合群.西部山地复杂地震资料处理技术研究[J].地球物理学进展,2008,23(3):859-863. Liu J H,Meng X H,Li H Q.Seismic data processing in the complex mountains of western China[J].Progress in Geophysics(in Chinese),2008,23(3):859-863.
[6]Yu S,Cai X,Su Y.Seismic signal enhancement by polynomial fitting[J].Applied Geophysics,1989,1:57-65.
[7]Ghghg C L.Random noise reduction,the 54th Annual Meeting of SEG.1984.
[8]Jones I F,Levy S.Signal-to-noise ratio enhancement in multichannel seismic data via the Karhunen-Loeve transform.Geophysical Prospecting,1987,35(2):12-32.
[9]Alan R Michell,Panos G Kelamis.Efficient tau-p hyperbolic velocity filtering.Geophysics,1990,55(5):619-625.
[10]Cai T T,Low M G.Nonparametric estimation over shrinking neighborhoods:superefficiency and adaptation,The Annals of Statistics.2005,33(1):184-213.
[11]吴招才,刘天佑.地震数据去噪中的小波方法[J].地球物理学进展,2008,23(2):493-499. Wu Z C,Liu T Y.Wavelet transform methods in seismic data noise attenuation[J].Progress in Geophysics(in Chinese), 2008,23(2):493-499.
[12]马继涛,Mrinal K.Sen,陈小宏.平面波域反数据处理压制多次波方法研究.地球物理学报,2009,52(3):808-816. Ma J T,Mrinal K.Sen,Chen X H.Multiple attenuation using inverse data processing in the plane-wave domain.Chinese J. Geophys.(in Chinese),2009,52(3):808-816.
[13]Alam,A Austin J.Suppression of multiples using slant stacks. Ann.Soc.Explor.Geophys.Mtg.,1981.
[14]Zhang Rongfeng,Ulrych T J.Physical wavelet frame denoising. Geophysics,2002,68(1):225-231.
[15]陈文超,高静怀,包乾宗.基于连续小波变换的自适应面波压制方法.地球物理学报,2009,52(11):2854-2861. Chen W C,Gao J H,Bao Q Z.Adaptive attenuation of ground roll via continuous wavelet transform.Chinese J.Geophys.(in Chinese),2009,52(11):2854-2861.
[16]胡天跃,王润秋,B E White.地震资料处理中的聚束滤波方法[J].地球物理学报,2000,43(1):105-115. Hu T Y,Wang R Q,B.E.WHITE.Beamforming in seismic data processing.Chinese J.Geophys.(in Chinese),2000,43 (1):105-115.
[17]Cox H,Zeskind R M,Owen M K.Robust adaptive beamforming [J].IEEE Trans.Acoust.Speech Signal Process ing, 1987,ASSP- 35(10):1365-1376.
[18]徐晨,赵瑞珍,甘小冰.小波分析应用算法[M].北京:科学出版社,200 4. Xu C,Zhao R Z,Gan X B.Applied Algorithm of Wavelet Analysis[M].Beijing:Science Press,2004.
[19]崔锦泰.小波分析导论[M].程正兴,译.西安:西安交通大学出版社,1995. Chui J T.An introduction to wavelets[M].Cheng Zheng xing translates.Xi an:Xi an Jiaotong UniversityPress,1995.
[20]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].科学出版社,2004. Deng L Y,Tian Y J.Data Mining of new method -Support Vector Machine[M].Bei Jing:Science Press,2004.
[21]吴琼,杨长春,张文忠,肖高杰.过渡带拼接地震资料处理方法研究[J].地球物理学进展,2008,23(3):760-767. Wu Q,Yang C C,Zhang W Z,Xiao G J.Research on processing technology for matching seismic data acquired in seashore and marine prospect[J].Progress in Geophysics(in Chinese),2008,23(3):761-767.
[22]刘建红,孟小红,李合群.西部山地复杂地震资料处理技术研究[J].地球物理学进展,2008,23(3):859-863. Liu J H,Meng X H,Li H Q.Seismic data processing in the complex mountains of western China[J].Progress in Geophysics(in Chinese),2008,23(3):859-863.
[23]马义忠,于更新,符力耘.复杂地表低信噪比地震数据处理研究[J].地球物理学进展,2008,23(6):1849-1858. Ma Y Z,Yu G X,Fu L Y.Seismic processing of low-S/N ratio data from complex near surface areas in huola mountain[J]. Progress in Geophysics(in Chinese),2008,23(6):1849 - 1858.
[24]姜静清.最小二乘支持向量机算法及应用研究[D].吉林:吉林大学博士论文,2007. Jiang Jingqing.Study on Least Squares Support vector Machine and its application[D].Doctoral essay in Ji Lin University,2007
[25]张孝珍,董汉强,等.地震勘探中的去噪技术新发展[J].勘探地球物理学进展,2009,32(3):172-178. Zhang X Z,Dong H Q,et al.Advances in denoising technology in seismic exploration[J].Progress in Exploration Geophysics,2009,32(3):172-178.
[26]Nuristan Acer.A support vector machine classifier algorithm based on a perturbation method and its application to EGG beat recognition systems[J].Expert Systems with Applications 31(2006),150-158.
[27]Engin Avci.Derya Avci.A novel approach for digital radio signal classication:Wavelet packet energy-multiclass support vector machine(WPE-MSVM)[J].Expert Systems with Applications 34(2008),2140-2147.
[28]Samjin Choi.Detection of volvuli heart disorders using wavelet packet decomposition and support vector machine[J].Expert Systems with Applications 35(2008),1679-1687.
[29]勾丽敏,刘学伟,等.金属矿地震勘探技术方法研究综述～金属矿地震勘探技术及其现状[J].勘探地球物理进展,2007,30(1):16-24. Gou L M,Liu X W,et al.Review of seismic survey in mining exploration:Part Theory and reflection seismic methods[J]. Progress in Exploration Geophysics,2007,30(1):16-24.
[30]刘洋,Fomel Sergey,刘财,等.高阶seislet变换及其在随机噪声消除中的应用.地球物理学报,2009,52(8):2142-2151. Liu Y,Fomel Sergey,Liu C,et at.High-order seislet transform and its application of random noise attenuation. Chinese J.Geophys.(in Chinese),2009,52(8):2142 - 2151.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心