Zhu Kai-Guang, Ma Ming-Yao, Che Hong-Wei，Yang Er-Wei, Ji Yan-Ju, Yu Sheng-Bao, and Lin Jun
Key Laboratory of Geo-exploration Instrumentation, College of Instrumentation and Electrical Engineering Changchun,Jilin University, Changchun, Jilin, 130026, China
Abstract 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 netw ork 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.
This work is supported by the National Natural Science Foundation of China (Grant No. 40974039) and High-Tech Research and Development Program of China (Grant No.2006AA06205), Leading Strategic Project of Science and Technology, Chinese Academy of Sciences (XDA08020500).
Corresponding Authors: Lin Jun Email: lin_jun@jlu.edu.cn.
Ardjmandpour, N., Pain, C., Singer, J., Saunders, J., Aristodemou, E., and Carter, J., 2011, Artificial neural
[2]
network forward modelling and inversion of electrokinetic logging data: Geophysical Prospecting, 59, 721 - 748.
[3]
Asten, M., 2009, Use of principal component images for classification of the EM response of unexploded
[4]
ordnance: 20th International Geophysical Conference and Exhibition, ASEG Extended Abstracts, 1 - 6, Australian
[5]
Society of Exploration Geophysicists.
[6]
Boadu, F., 2011, Artificial neural networks models for determining the basic geotechnical properties of soils from
[7]
electrical measurements: Symposium on the Application of Geophysics to Engineering and Environmental Problems,
[8]
, 79 - 79.
[9]
Brodie, R., and Sambridge, M., 2009, An example of holistic inversion of time domain AEM data: 20th
[10]
International Geophysical Conference and Exhibition, ASEG Extended Abstracts, 1 - 9.
[11]
Brodie, R. C., 2010, Holistic inversion of airborne electromagnetic data: PhD Thesis, Australian National University.
[12]
Brodie, R. C., 2011, One-step calibration, processing, and quantitative interpretation of airborne electromagnetic
[13]
data via holistic inversion: International Workshop on Gravity, Electrical, and Magnetic Methods and Their
[14]
Applications, Beijing, China.
[15]
Chen, J., and Raiche, A., 1998, Inverting AEM data using a damped eigenparameter method: Exploration
[16]
Geophysics, 29, 128 - 132.
[17]
Christensen, N. B., Reid, J. E., and Halkjær, M., 2009, Fast laterally smooth inversion of airborne time-domain
[18]
electromagnetic data: Near Surface Geophysics, 7(5), 599 - 612.
[19]
Cox, L. H., Wilson, G. A., and Zhdanov, M. S., 2010, 3D inversion of airborne electromagnetic data using a moving
[20]
footprint: Exploration Geophysics, 41, 250 - 259.
[21]
Fullagar, P. K., and Reid, J. E., 2001, Emax conductivity-depth transformation of airborne TEM data: 15th Conference and Exhibition, ASEG Extended Abstracts, 1 - 1.
[22]
Green, A., 1998, The use of multivariate statistical techniques for the analysis and display of AEM data:
[23]
Exploration Geophysics, 29, 77 - 82.
[24]
Haykin, S., 2004, Neural networks: A comprehensive foundation, 2nd edition: China Machine Press, Beijing.
[25]
Huang, H. P., and Rudd, J., 2008, Conductivity-depth imaging of helicopter-borne TEM data based on a
2012, Vol. 9 
|
