Modeling extra-deep EM logs using a deep neural network

What is it about?

we design a training dataset that embraces the geological rules and geosteering specics 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.

Featured Image

Why is it important?

The observed average evaluation time of 0.15 ms per logging position makes it suitable to be used as part of evaluation-hungry statistical and/or Monte-Carlo inversion algorithms within geosteering workflows.