A decision support system for multi-target geosteering

Abstract

Geosteering is a sequential decision process under uncertainty. The goal of geosteering is to maximize the expected value of the well, which should be defined by an objective value-function for each operation.In this paper we present a real-time decision support system (DSS) for geosteering that aims to approximate the uncertainty in the geological interpretation with an ensemble of geomodel realizations. As the drilling operation progresses, the ensemble Kalman filter is used to sequentially update the realizations using the measurements from real-time logging while drilling. At every decision point a discrete dynamic programming algorithm computes all potential well trajectories for the entire drilling operation and the corresponding value of the well for each realization. Then, the DSS considers all immediate alternatives (continue/steer/stop) and chooses the one that gives the best predicted value across the realizations. This approach works for a variety of objectives and constraints and suggests reproducible decisions under uncertainty. Moreover, it has real-time performance.The system is tested on synthetic cases in a layer-cake geological environment where the target layer should be selected dynamically based on the prior (predrill) model and the electromagnetic observations received while drilling. The numerical closed-loop simulation experiments demonstrate the ability of the DSS to perform successful geosteering and landing of a well for different geological configurations of drilling targets. Furthermore, the DSS allows to adjust and reweight the objectives, making the DSS useful before fully-automated geosteering becomes reality.

Deep learning for prediction of complex geology ahead of drilling

“…In the DSS for geosteering [3], one uses data assimilation to condition the earth model to measurements made while drilling. The fundamental idea is that if a poorly known earth model can be made consistent with measurements it will provide more accurate forecasts, and, hence, provide a better basis for decisions.…”

“…In the EnKF the uncertainty is represented by an ensemble of equiprobable realizations. This workflow has then been combined with a global optimization method and applied as a Decision Support System (DSS) [3].…”

“…The DSS framework provides high quality decisions on synthetic cases, but practical challenges should be addressed for it to be applicable to real operations [3]. Firstly, to our knowledge, there is no studies which combine the ensemble update with a commercial tool for simulation of measurements.…”

Direct multi-modal inversion of geophysical logs using deep learning

“…Fast probabilistic inversion of geophysical data is specifically important for processing measurements during drilling, since it opens the possibilities to use probabilistic decision algorithms Chen et al (2015); Kullawan et al (2018); Alyaev et al (2019) to adjust the trajectory during operation resulting in better well placement. The intentional adjustment of the drilling trajectory, termed geosteering, is essential for hydrocarbon wells Bristow et al (2000), but is gradually introduced in other types of drilling, e.g., geothermal Ungemach et al (2021) and civil wells and tunnels Johnson et al (2021).…”

Modeling extra-deep electromagnetic logs using a deep neural network

“…To reach high-quality geosteering decisions, it is convenient to use statistical (Bayesian) interpretation, which provides uncertainties (Kullawan et al, 2014). Bayesian workflows for updating geomodels while drilling provide promising results in synthetic testing (Chen et al, 2015;Luo et al, 2015;Alyaev et al, 2019). At the same time, adequate uncertainty representation may require up to 100,000 forward simulations per logging position (Dupuis and Manuscript received by the Editor 5 June 2020; revised manuscript received 19 January 2021; published ahead of production 10 March 2021; published online 13 May 2021.…”