PC-based artificial neural network inversion for airborne time-domain electromagnetic data

PC-based artificial neural network inversion for airborne time-domain electromagnetic data
复制标题

基于PC的机载时域电磁数据人工神经网络反演

DOI:
10.1007/s11770-012-0307-7
复制
发表时间:
2012-04
期刊:
影响因子:
0.7
通讯作者:
Lin Jun
Lin Jun
中科院分区:
地球科学4区
文献类型:
--
作者:
Zhu Kai-Guang;Ma Ming-Yao;Che Hong-Wei;Yang Er-Wei;Ji Yan-Ju;Yu Sheng-Bao;Lin Jun

文献摘要

参考文献

被引文献

相似文献

传统上,航空时间域电磁(ATEM)数据反演地球模型是通过迭代。然而,数据往往是高度相关的通道之间,从而导致不适定和超定的问题,在反演。这种相关性使ATEM数据与大地参数之间的映射关系变得复杂,从而增加了反演的复杂性。为了克服这一问题,我们采用主成分分析将ATEM数据转换为正交主成分(PC),以减少相关性和数据的维数,同时抑制无关的噪声。本文利用人工神经网络逼近地球模型参数与PC的映射关系,避免了雅可比导数的计算。基于PC的人工神经网络算法适用于合成数据的分层模型相比,基于数据的人工神经网络航空时域电磁反演。结果表明,与基于数据的神经网络相比,基于PC的神经网络具有网络结构更简单、训练步骤更少、反演结果更好的优点,尤其是对于受污染的数据。此外,基于PC的人工神经网络算法的有效性进行了检查的伪二维模型的反演和比较基于数据的人工神经网络和Zhody的方法。结果表明,基于PC的人工神经网络反演可以达到更好的协议与真实的模型,也证明了基于PC的人工神经网络是可行的反演大ATEM数据集。
Traditionally, airborne time-domain electromagnetic (ATEM) data are inverted to derive the earth model by iteration. However, the data are often highly correlated among channels and consequently cause ill-posed and over-determined problems in the inversion. The correlation complicates the mapping relation between the ATEM data and the earth parameters and thus increases the inversion complexity. To obviate this, we adopt principal component analysis to transform ATEM data into orthogonal principal components (PCs) to reduce the correlations and the data dimensionality and simultaneously suppress the unrelated noise. In this paper, we use an artificial neural network (ANN) to approach the PCs mapping relation with the earth model parameters, avoiding the calculation of Jacobian derivatives. The PC-based ANN algorithm is applied to synthetic data for layered models compared with data-based ANN for airborne time-domain electromagnetic inversion. The results demonstrate the PC-based ANN advantages of simpler network structure, less training steps, and better inversion results over data-based ANN, especially for contaminated data. Furthermore, the PC-based ANN algorithm effectiveness is examined by the inversion of the pseudo 2D model and comparison with data-based ANN and Zhody’s methods. The results indicate that PC-based ANN inversion can achieve a better agreement with the true model and also proved that PC-based ANN is feasible to invert large ATEM datasets.
DOI: 10.1071/aseg2009ab102
发表时间: 2009-09
期刊: ASEG Extended Abstracts
影响因子: --
作者:
M. Asten
通讯作者: M. Asten
DOI: --
发表时间: 2001
期刊: Coal Geology & Exploration
影响因子: --
作者:
Li Shi
通讯作者: Li Shi
DOI: 10.4133/1.3614179
发表时间: 2011
期刊: --
影响因子: --
作者:
Jeannie Norton;J. Sheehan;L. Beard
通讯作者: Jeannie Norton;J. Sheehan;L. Beard
DOI: 10.1071/eg998077
发表时间: 1998-06
影响因子: 0.9
作者:
A. Green
通讯作者: A. Green
DOI: 10.1071/aseg2001ab044
发表时间: 2001-12
期刊: ASEG Extended Abstracts
影响因子: --
作者:
P. Fullagar;J. Reid
通讯作者: P. Fullagar;J. Reid