Modeling extra-deep electromagnetic logs using a deep neural network
Authors:
- Sergey AlyaevSASergey Alyaev
- Mostafa ShahriariMSMostafa Shahriari
- David PardoDPDavid Pardo
- Angel Javier OmellaAOAngel Javier Omella
- David LarsenDLDavid Larsen
- Nazanin JahaniNJNazanin Jahani
- Erich SuterESErich Suter
Preprint
Abstract
Modern geosteering is heavily dependent on real-time interpretation of deep electromagnetic (EM) measurements. We present a methodology to construct a deep neural network (DNN) model trained to reproduce a full set of extra-deep EM logs consisting of 22 measurements per logging position. The model is trained in a 1D layered environment consisting of up to seven layers with different resistivity values. A commercial simulator provided by a tool vendor is used to generate a training dataset. The dataset size is limited because the simulator provided by the vendor is optimized for sequential execution. Therefore, we design a training dataset that embraces the geological rules and geosteering specifics supported by the forward model. We use this dataset to produce an EM simulator based on a DNN without access to the proprietary information about the EM tool configuration or the original simulator source code. Despite employing a relatively small training set size, the resulting DNN forward model is quite accurate for the considered examples: a multi-layer synthetic case and a section of a published historical operation from the Goliat Field. The observed average evaluation time of 0.15 ms per logging position makes it also suitable for future use as part of evaluation-hungry statistical and/or Monte-Carlo inversion algorithms within geosteering workflows.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Error control and loss functions for the deep learning inversion of borehole resistivity measurementsInternational Journal for Numerical Methods in Engineering, 2020
- A deep learning approach to the inversion of borehole resistivity measurementsComputational Geosciences, 2020
- One-dimensional deep learning inversion of electromagnetic induction data using convolutional neural networkGeophysical Journal International, 2020
- Physics-Constrained Deep Learning of Geomechanical LogsIEEE Transactions on Geoscience and Remote Sensing, 2020
- A Fast Inversion of Induction Logging Data in Anisotropic Formation Based on Deep LearningIEEE Geoscience and Remote Sensing Letters, 2020
- A Deep Neural Network as Surrogate Model for Forward Simulation of Borehole Resistivity MeasurementsProcedia Manufacturing, 2020
- A decision support system for multi-target geosteeringJournal of Petroleum Science and Engineering, 2019
- Deep learning electromagnetic inversion with convolutional neural networksGeophysical Journal International, 2019
- Generation of synthetic dielectric dispersion logs in organic-rich shale formations using neural-network modelsGeophysics, 2019
- Machine learning in geosciences and remote sensingGeoscience Frontiers, 2016