文章基本信息

标题：Inversion of Magnetic Anomalies Due to 2-D Cylindrical Structures – By an Artificial Neural Network
本地全文：下载
作者：Bhagwan Das Mamidala ; Sundararajan Narasimman
期刊名称：International Journal on Soft Computing
电子版ISSN：2229-7103
出版年度：2019
卷号：10
期号：1
页码：1-18
DOI：10.5121/ijsc.2019.10101
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Application of Artificial Neural Network Committee Machine (ANNCM) for the inversion of magneticanomalies caused by a long-2D horizontal circular cylinder is presented. Although, the subsurface targetsare of arbitrary shape, they are assumed to be regular geometrical shape for convenience of mathematicalanalysis. ANNCM inversion extract the parameters of the causative subsurface targets include depth to thecentre of the cylinder (Z), the inclination of magnetic vector(Ɵ)and the constant term (A)comprising theradius(R)and the intensity of the magnetic field(I). The method of inversion is demonstrated over atheoretical model with and without random noise in order to study the effect of noise on the technique andthen extended to real field data. It is noted that the method under discussion ensures fairly accurate resultseven in the presence of noise. ANNCM analysis of vertical magnetic anomaly near Karimnagar, Telangana,India, has shown satisfactory results in comparison with other inversion techniques that are in vogue.Thestatistics of the predicted parameters relative to the measured data, show lower sum error (<9.58%) andhigher correlation coefficient (R>91%) indicating that good matching and correlation is achieved betweenthe measured and predicted parameters.
关键词：Magnetic anomaly; Artificial Neural Network; Committee machine; Levenberg ; Marquardt algorithm;Hilbert transform; modified Hilbert transform; trial and error method.