Deep learning for prediction of complex geology ahead of drilling

TL;DR

This paper introduces machine learning techniques, specifically GANs and FDNNs, into geosteering decision support to improve real-time geological uncertainty estimation during drilling in complex environments.

Contribution

It presents a novel integration of GANs and FDNNs into geosteering decision frameworks, enabling real-time uncertainty reduction.

Findings

GAN-generated earth models improve geological representation.

FDNN accelerates electromagnetic simulation for real-time use.

Combined ML methods reduce geological uncertainty ahead of the drill-bit.

Abstract

During a geosteering operation the well path is intentionally adjusted in response to the new data acquired while drilling. To achieve consistent high-quality decisions, especially when drilling in complex environments, decision support systems can help cope with high volumes of data and interpretation complexities. They can assimilate the real-time measurements into a probabilistic earth model and use the updated model for decision recommendations. Recently, machine learning (ML) techniques have enabled a wide range of methods that redistribute computational cost from on-line to off-line calculations. In this paper, we introduce two ML techniques into the geosteering decision support framework. Firstly, a complex earth model representation is generated using a Generative Adversarial Network (GAN). Secondly, a commercial extra-deep electromagnetic simulator is represented using a Forward Deep Neural Network (FDNN). The numerical experiments demonstrate that the combination of the GAN and the FDNN in an ensemble randomized maximum likelihood data assimilation scheme provides real-time estimates of complex geological uncertainty. This yields reduction of geological uncertainty ahead of the drill-bit from the measurements gathered behind and around the well bore.