论文信息 - Neural Network Algorithm for Solving 3d Inverse Problem of Geoelectrics

Neural Network Algorithm for Solving 3d Inverse Problem of Geoelectrics

The approximating neural network algorithm for solving the inverse problems of geoelectrics in the class of grid (block) models of the medium is presented. The algorithm is based on constructing an approximate inverse operator using neural networks and makes it possible to formally obtain the solutions of the geoelectrics inverse problem with a total number of the sought parameters of the medium \( \sim n\, \times \, 10^{ 3} \). The questions concerning the correctness of the problem of constructing the inverse neural network operators are considered. The a posteriori estimates of the degree of ambiguity in the inverse problem solutions are calculated. The work of the algorithm is illustrated by the examples of 2D and 3D inversions of the synthesized data and the real magnetotelluric sounding data.

Sergey Dolenko | E. A. Obornev | I. E. Obornev | M. I. Shimelevich | E. A. Rodionov

[1] Simon Haykin,et al. Neural Networks: A Comprehensive Foundation , 1998 .

[2] P. Werbos,et al. Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[3] Carsten Peterson,et al. Pattern recognition in high energy physics with artificial neural networks - JETNET 2.0 , 1992 .

[4] E. A. Obornev,et al. The neural network approximation method for solving multidimensional nonlinear inverse problems of geophysics , 2017, Izvestiya, Physics of the Solid Earth.

[5] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[6] An approximation method for solving the inverse MTS problem with the use of neural networks , 2009 .

[7] Mary M. Poulton,et al. Neural network pattern recognition of subsurface EM images , 1992 .

[8] A. Raiche. A pattern recognition approach to geophysical inversion using neural nets , 1991 .

[9] J. T. Smith,et al. Three-dimensional electromagnetic modeling using finite difference equations: The magnetotelluric example , 1994 .

[10] R. Swiniarski,et al. Neural network approximation of an inverse functional , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[11] I. G. Persiantsev,et al. Comparison of Adaptive Algorithms for Significant Feature Selection in Neural Network Based Solution of the Inverse Problem of Electrical Prospecting , 2009, ICANN.