Geodesic
An algorithm for solving an inverse geoelectrics problem based on the neural network approximation
Sibirskij žurnal vyčislitelʹnoj matematiki, Tome 21 (2018) no. 4, pp. 451-468.

Voir la notice de l'article provenant de la source Math-Net.Ru

The approximation neural network algorithm for solving the inverse geoelectrics problems in the class of grid (block) media models is presented. The algorithm is based on constructing an approximate inverse operator using neural networks and makes it possible to formally obtain solutions of the inverse geoelectrics problem with the total number of desired parameters of the medium $\sim n\cdot103$. The correctness of the problem of constructing the neural network inverse operators is considered. A posteriori estimates of the degree of ambiguity of the inverse problem solutions are calculated. The operation of the algorithm is illustrated by examples of the 2D, the 3D inversions of synthesized and field geoelectric data, obtained by the MTS method. 
@article{SJVM_2018_21_4_a7,
     author = {M. I. Shimelevich and E. A. Obornev and I. E. Obornev and E. A. Rodionov},
     title = {An algorithm for solving an inverse geoelectrics problem based on the neural network approximation},
     journal = {Sibirskij \v{z}urnal vy\v{c}islitelʹnoj matematiki},
     pages = {451--468},
     publisher = {mathdoc},
     volume = {21},
     number = {4},
     year = {2018},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/SJVM_2018_21_4_a7/}
}
TY  - JOUR
AU  - M. I. Shimelevich
AU  - E. A. Obornev
AU  - I. E. Obornev
AU  - E. A. Rodionov
TI  - An algorithm for solving an inverse geoelectrics problem based on the neural network approximation
JO  - Sibirskij žurnal vyčislitelʹnoj matematiki
PY  - 2018
SP  - 451
EP  - 468
VL  - 21
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/SJVM_2018_21_4_a7/
LA  - ru
ID  - SJVM_2018_21_4_a7
ER  - 
%0 Journal Article
%A M. I. Shimelevich
%A E. A. Obornev
%A I. E. Obornev
%A E. A. Rodionov
%T An algorithm for solving an inverse geoelectrics problem based on the neural network approximation
%J Sibirskij žurnal vyčislitelʹnoj matematiki
%D 2018
%P 451-468
%V 21
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/SJVM_2018_21_4_a7/
%G ru
%F SJVM_2018_21_4_a7
M. I. Shimelevich; E. A. Obornev; I. E. Obornev; E. A. Rodionov. An algorithm for solving an inverse geoelectrics problem based on the neural network approximation. Sibirskij žurnal vyčislitelʹnoj matematiki, Tome 21 (2018) no. 4, pp. 451-468. http://geodesic.mathdoc.fr/item/SJVM_2018_21_4_a7/

[1] Berdichevsky M. N., Dmitriev V. I., “Inverse problems of magnetotellurics: A modern formulation”, Izvestiya. Physics of the Solid Earth, 40:4 (2004), 276–292 | MR

[2] Vanyan L. L., Butkovskaya A. I., Magnitotelluricheskoe zondirovanie sloistykh sred, Nedra, M., 1980

[3] Vorontsov K. V., Lektsii po iskusstvennym neironnym setyam, , 2009 http://www.machinelearning.ru/wiki/images/c/cc/Voron-ML-NeuralNets.pdf

[4] Galushkin A. I., Sintez mnogosloinykh sistem raspoznavaniya obrazov, Energiya, M., 1974

[5] Glasko V. B., Guschin G. V., Starostenko V. I., “O primenenii metoda regulyarizatsii A. N. Tikhonova k resheniyu nelineinykh sistem uravnenii”, Zhurn. vychisl. matem. i mat. fiziki, 16:2 (1976), 283–292 | MR | Zbl

[6] Dmitriev V. I., Obratnye zadachi geofiziki, MAKS Press, M., 2012

[7] Dmitriev V. I., Kokotushkin G. A., Albom paletok dlya magnitotelluricheskogo zondirovaniya v neodnorodnykh sredakh, Izd-vo MGU, M., 1971

[8] Dmitrieva M. V., Chislennoe modelirovanie fizicheskikh protsessov v plazme ustanovok tokamak pri vozdeistvii elektromagnitnykh voln alfvenovskogo diapazona chastot, Avtoreferat dis. $\dots$ kand. fiz.-mat. nauk: 01.01.07, IPM AN SSSR, M., 1985

[9] Ivanov V. K., “O nekorrektno postavlennykh zadachakh”, Matematicheskii sbornik, 61(103):2 (1963), 211–223 | MR | Zbl

[10] Kabanikhin S. I., Shishlenin M. A., Novikov N. S., “Algoritmy opredeleniya uprugikh parametrov po ploschadnym sistemam nablyudenii (pryamaya lineinaya obrabotka dannykh seismicheskikh nablyudenii”, Vestnik kibernetiki, 2016, no. 2, 83–91

[11] Romanov V. G., Kabanikhin S. I., Obratnye zadachi geoelektriki, Nauka, M., 1991 | MR

[12] Strakhov V. N., Lapina M. I., “Montazhnyi metod resheniya obratnoi zadachi gravimetrii”, Dokl. AN SSSR, 227:2 (1976), 344–347 | MR

[13] Spichak V. V., Popova I. V., “Application of the neural network approach to the reconstruction of a three-dimensional geoelectric structure”, Izvestiya. Physics of the Solid Earth, 34:1 (1998), 33–39

[14] Khaikin S., Neironnye seti, Polnyi kurs, 2-e izd., Izd. dom “Vilyams”, M., 2006

[15] Feldman I. S., Okulesskii B. A., Suleimanov A. K., Nikolaeva V. I., Kuncherov V. A., Chamo S. S., “Elektrorazvedka metodom MTZ v komplekse regionalnykh neftegazopoiskovykh rabot v evropeiskoi chasti Rossii”, Zapiski Gornogo instituta, 176, SPb., 2008, 125–131

[16] Shimelevich M. I., Obornev E. A., “An approximation method for solving the inverse mts problem with the use of neural networks”, Izvestiya. Physics of the Solid Earth, 45:12 (2009), 1055–1071 | DOI

[17] Shimelevich M. I., Obornev E. A., Obornev I. E., Rodionov E. A., “Numerical methods for estimating the degree of practical stability of inverse problems in geoelectrics”, Izvestiya. Physics of the Solid Earth, 49:3 (2013), 356–362 | DOI | DOI

[18] Shimelevich M. I., Obornev E. A., Obornev I. E., Rodionov E. A., “The neural network approximation method for solving multidimensional nonlinear inverse problems of geophysics”, Izvestiya. Physics of the Solid Earth, 53:4 (2017), 588–597 | DOI | DOI

[19] Cybenko G., “Approximation by superpositions of a Sigmoidal Function”, Mathematics of Control, Signals, and Systems, 2 (1989), 303–314 | DOI | MR | Zbl

[20] Dolenko S., Guzhva A., Obornev E., Persiantsev I., Shimelevich M., “Comparison of adaptive algorithms for significant feature selection in neural network based solution of the inverse problem of electrical prospecting”, Proc. ICANN 2009, Part II, Lect. Notes in Computer Science, 5769, Springer-Verlag, Berlin–Heidelberg, 2009, 397–405 | DOI

[21] Eisenstat S., Schultz M., Sherman A., “Algorithms and data structures for sparse symmetric gaussian elimination”, SIAM J. Sci. and Stat. Comput., 2:2 (1981), 225–237 | DOI | MR | Zbl

[22] Hidalgo H., Gymez-Trevico E., Swiniarski R., “Neural network approximation of a inverse functional”, Proc. IEEE International Conference on Neural Networks, 5 (1994), 3387–3392

[23] Kabanikhin S. I., “Definitions and examples of inverse and ill-posed problems”, J. Inv. Ill-Posed Problems, 16 (2008), 317–357 | MR | Zbl

[24] Lönnblad L., Peterson C., Rognvalsson T., “Pattern recognition in high energy physics with artificial neural networks – JETNET 2.0”, Computer Physics Communications, 70:1 (1992), 167–182 | DOI

[25] Mackie R. L., Smith J. T., Madden T. R., “Three-dimensional electromagnetic modeling using finite difference equations: the magnetotelluric example”, Radio Science, 29 (1994), 923–935 | DOI

[26] Poulton M., Sternberg B., Glass C., “Neural network pattern recognition of subsurface EM images”, J. of Applied Geophysics, 29:1 (1992), 21–36 | DOI

[27] Raiche A., “A pattern recognition approach to geophysical inversion using neural nets”, Geophysics J. Int., 105 (1991), 629–648 | DOI

[28] Shimelevitch M., Obornev E., “The method of neuron network in inverse problems MTZ”, Abstracts of the 14-th workshop on Electromagnetic Induction in the Earth, Sinaia, Romania, 1998

[29] Werbos P. J., Beyond regression: new tools for prediction and analysis in the behavioral sciences, PhD thesis, Harvard University, Cambridge, MA, 1974 | MR

[30] Yagola A., “Error estimation for ill-posed problems with priori information”, Global J. on Technology Optimization, 1 (2010), 88–92