Increase of the Resistance to Noise in Data for Neural Network Solution of the Inverse Problem of Magnetotellurics with Group Determination of Parameters

Isaev, Igor; Obornev, Eugeny; Obornev, Ivan; Shimelevich, M. I.; Доленко, С. А.

doi:10.1007/978-3-319-44778-0_59

Cited by 7 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce the output dimension of the problem, autonomous determination [13,14] of parameters was used, which consists in individual determination of each parameter by training a separate NN. When using the regression approach, each such NN has a single output.…”

Section: Reducing the Output Dimensionmentioning

confidence: 99%

“…At the same time, when solving the RG problem, the ML methods can be used at various stages of its solution: in data preprocessing, e.g., for noise removal [7,8]; as an independent optimization method [2,3,9] or as a component of optimization methods used to solve the EG problem [10]; as an independent inversion method [1,[11][12][13][14][15][16][17][18][19]; in solving the classification problem to select a class of geological media [20]. In this study, we considered neural networks as an independent inversion method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Network Solution of Inverse Problems of Geological Prospecting with Discrete Output

Isaev¹,

Obornev²,

Obornev³

et al. 2021

Proceedings of the 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)

Self Cite

View full text Add to dashboard Cite

The inverse problems of exploration geophysics are to reconstruct the spatial distribution of the properties of the medium in the Earth's thickness from the geophysical fields measured on its surface. In particular, this paper deals with the problems of gravimetry, magnetometry, and magnetotelluric sounding, as well as their integration, i.e., the simultaneous use of several geophysical fields to restore the desired distribution. To implement the integration, a 4-layer 2D model was used, where the inverse problem was to determine the lower boundary of the layers, and each layer was characterized by variable values of the depth of the lower boundary along the section and fixed values of density, magnetization, and resistivity, both for the layer and for the entire data set. To implement the neural network solution of the inverse problem, a data set was generated by solving the direct problem, where for each pattern, the distribution of layer depth values was set randomly in a given range and with a given step, i.e. it took discrete values from a certain set. In this paper, we consider an approach involving the use of neural networks to solve the problem of multiclass classification, where class labels correspond to discrete values of the determined layer depths. The results of the solution are compared with the results of the solution of the same inverse problem in the formulation of the regression problem, in terms of the error in determining the depth of the layers.

show abstract

Section: Reducing the Output Dimensionmentioning

confidence: 99%