Automatic Geoelectric Boundaries Detection on the Resistivity Images Based on 3D Numerical Simulation and Convolutional Neural Network

Danilovskiy, K. N.; Loginov, G.; Nechaev, O. V.

doi:10.3997/2214-4609.202053015

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Одним из наиболее важных факторов, которые в недавнем времени сделали возможным широкое применение глубоких ИНС для решения различных научно-технических задач, является увеличение объемов данных, доступных для их обучения [Goodfellow et al, 2017] Аугментация увеличивает как объем, так и разнообразие данных, что является эффективной стратегией борьбы с переобучением ИНС [Krizhevsky et al, 2012] Для расширения обучающей выборки к полученным в результате трехмерного численного моделирования имиджам УЭС применяется процедура аугментации [Danilovskiy et al, 2020]. В задачах, связанных с компьютерным зрением, аугментацию данных зачастую проводят при помощи простых преобразований исходных изображений: сдвигов, поворотов, масштабирования.…”

Section: создание набора данных для обучения инсunclassified

Lateral scanning logging while drilling data processing using convolutional neural networks

Danilovskii

Loginov

2022

Russian Journal of geophysical technologies

View full text Add to dashboard Cite

This article discusses a new approach to processing lateral scanning logging while drilling data based on a combination of three-dimensional numerical modeling and convolutional neural networks. We prepared dataset for training neural networks. Dataset contains realistic synthetic resistivity images and geoelectric layer boundary layouts, obtained based on true values of their spatial orientation parameters. Using convolutional neural networks two algorithms have been developed and programmatically implemented: suppression of random noise and detection of layer boundaries on the resistivity images. The developed algorithms allow fast and accurate processing of large amounts of data, while, due to the absence of full-connection layers in the neural networks’ architectures, it is possible to process resistivity images of arbitrary length.

show abstract

Section: создание набора данных для обучения инсunclassified

Lateral scanning logging while drilling data processing using convolutional neural networks

Danilovskii

Loginov

2022

Russian Journal of geophysical technologies

View full text Add to dashboard Cite

show abstract

Application of Convolutional Neural Networks for Resistivity Logs Processing and Non-Iterative Express-Inversion in Complex Reservoir Environments

Leonenko

Danilovskiy

Петров

2021

Interexpo GEO-Siberia

View full text Add to dashboard Cite

The work is devoted to the development of techniques and software for the quantitative interpretation of resistivity oil well logs. The article considers the results of applying the neural network approach to the processing of resistivity logging data measured at intervals composed of thin layers with contrasting electrical properties. The proposed algorithms combine the advantages of data interpretation based on a two-dimensional axisymmetric medium model and high performance, which allows them to be used at the primary processing stage, increasing the reliability of express interpretation.

show abstract

Fast Resistivity Logs Simulation in Two-Dimensional Anisotropic Near-Wellbore Space Models Based on Numerical Simulation and Machine Learning

Петров

Danilovskiy

Eremenko

2021

Interexpo GEO-Siberia

View full text Add to dashboard Cite

The article presents the results of a new approach application for oil well galvanic and induction resistivity logs simulation to enhance the efficiency of geological environment parameters evaluation and to speed up the interpretation. The use of modern machine learning technologies allows us to create algorithms for resistivity logs simulation in high-detailed two-dimensional anisotropic geoelectric models. The developed algorithms are characterized by a qualitatively new level of performance compared to the approaches used today.

show abstract

Automatic Geoelectric Boundaries Detection on the Resistivity Images Based on 3D Numerical Simulation and Convolutional Neural Network

Cited by 4 publications

References 0 publications

Lateral scanning logging while drilling data processing using convolutional neural networks

Lateral scanning logging while drilling data processing using convolutional neural networks

Application of Convolutional Neural Networks for Resistivity Logs Processing and Non-Iterative Express-Inversion in Complex Reservoir Environments

Fast Resistivity Logs Simulation in Two-Dimensional Anisotropic Near-Wellbore Space Models Based on Numerical Simulation and Machine Learning

Contact Info

Product

Resources

About