Direct multi-modal inversion of geophysical logs using deep learning

TL;DR

This paper introduces a deep learning method for rapid, multi-modal inversion of geophysical logs, improving real-time stratigraphic interpretation by providing multiple probable solutions with associated probabilities.

Contribution

It presents a novel mixture density neural network with a unique loss function that avoids mode collapse, enabling multi-modal predictions for geophysical log inversion.

Findings

The approach produces multiple plausible stratigraphic solutions in milliseconds.

It outperforms deterministic models by capturing geological uncertainties.

Probabilistic outputs improve decision-making in geosteering.

Abstract

Geosteering of wells requires fast interpretation of geophysical logs, which is a non-unique inverse problem. Current work presents a proof-of-concept approach to multi-modal probabilistic inversion of logs using a single evaluation of an artificial deep neural network (DNN). A mixture density DNN (MDN) is trained using the "multiple-trajectory-prediction" (MTP) loss functions, which avoids mode collapse typical for traditional MDNs, and allows multi-modal prediction ahead of data. The proposed approach is verified on the real-time stratigraphic inversion of gamma-ray logs. The multi-modal predictor outputs several likely inverse solutions/predictions, providing more accurate and realistic solutions than a deterministic regression using a DNN. For these likely stratigraphic curves, the model simultaneously predicts their probabilities, which are implicitly learned from the training geological data. The stratigraphy predictions and their probabilities obtained in milliseconds from the MDN can enable better real-time decisions under geological uncertainties.