氡浓度和环境参数的分层神经网络研究
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
采用分层神经网络(LNN)分析地下水的氡浓度,试图给出氡浓度和环境参数之间的函数关系。由于环境(例如:降雨量)对水氡浓度的影响可能是非线性的,与目前时间脉冲响应线性计算方法相比,该方法能够较准确的估计环境参数造成的氡浓度变化。
LNN had been used to analyze the current radon concentration in groundwater,attempting to find the function relationship between the radon concentration and environmental parameters. The influence of environment(for example:rainfall) on the radon concentration in groundwater may be nonlinear.The LNN can estimate more accurately the radon concentration by environmental parameters change,comparing with the linear computational technique (CLT).The analysis results of Radon observation data from the wells in Xiamen Dongfu show that LNN can accurately find out the change of radon concentration caused by the earthquake from environmental factors(for example:rainfall).In addition,LNN can tell the change of radon concentration by the environmental factors from other factors.
引文
高文学,蒋凤亮,高庆华,等.地球化学异常——地震预测整体观的探索[M].北京:地震出版社,2000.
    蒋宗礼.人工神经网络导论[M].北京:高等教育出版社,2001.
    邹昌明,王雪芳,王增春,等.非地震因素引起水氡异常一例[J].地震地磁观测与研究,1995,16(4):68-74.
    Fleischer R L.Dislocation model for radon response to distant earthquakes[J].Geophysics Research Letter,1981,8: 477-480.
    Igarashi G,Wakita S.Groundwater radon anomalies associated with earthquakes[J].Tectonophysics,1990,180:237-254.
    Levin E,Tisby N,Solla S A.A statistical approach to learning and generalization in layered neural networks[J].Proceeding of IEEE,1990,78:1 568-1 573.
    Lippmann R P.An introduction to computing with neural nets[J].IEEE ASSP Magazine,1987,4:4-22.
    Swingler K.Applying neural networks[M].London:Academic Press,1996.
    Wattananikorn K,Kanaree M,Wiboolsake S.Soil gas radon as an earthquake precursor:some consideration on data improvement [J].Radiation Measurement,1998,29:593-598.

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