An Automatic Well Planner for Efficient Well Placement Optimization Under Geological Uncertainty

Kristoffersen, Brage S.; Silva, T.; Bellout, Mathias C.; Berg, Carl Fredrik

doi:10.3997/2214-4609.202035211

Cited by 4 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AWP is also well suited for optimization under uncertainty when the uncertainty is represented by an ensemble of models. In this setting, the low-order parameterization of the AWP allows for customized well paths for each member in the ensemble, thereby obtaining a well placement which is optimized with respect to adaptive well paths (Kristoffersen et al 2020).…”

Section: Discussionmentioning

confidence: 99%

“…This capability simplifies and can help decrease the computational load required by field development operations, e.g., well completion design and well placement, especially if these operations involve iterative procedures and extensive reservoir simulation. A particular application is towards the heavy computational cost associated with using derivative-free algorithms, e.g., for well placement search (Bellout et al 2012;Kristoffersen et al 2020), since sampling requirements for these type of algorithms, and therefore overall performance, are typically proportional to the number of variables.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Automatic Well Planner for Complex Well Trajectories

et al. 2021

View full text Add to dashboard Cite

A data-driven automatic well planner procedure is implemented to develop complex well trajectories by efficiently adapting to near-well reservoir properties and geometry. The procedure draws inspiration from geosteering drilling operations, where modern logging-while-drilling tools enable the adjustment of well trajectories during drilling. Analogously, the proposed procedure develops well trajectories based on a selected geology-based fitness measure using an artificial neural network as the decision maker in a virtual sequential drilling process within a reservoir model. While neural networks have seen extensive use in other areas of reservoir management, to the best of our knowledge, this work is the first to apply neural networks on well trajectory design within reservoir models. Importantly, both the input data generation used to train the network and the actual trajectory design operations conducted by the trained network are efficient calculations, since these rely solely on geometric and initial properties of the reservoir, and thus do not require additional simulations. Therefore, the main advantage over traditional methods is the highly articulated well trajectories adapted to reservoir properties using a low-order well representation. Well trajectories generated in a realistic reservoir by the automatic well planner are qualitatively and quantitatively compared to trajectories generated by a differential evolution algorithm. Results show that the resulting trajectories improve productivity compared to straight line well trajectories, both for channelized and geometrically complex reservoirs. Moreover, the overall productivity with the resulting trajectories is comparable to well solutions obtained using differential evolution, but at a much lower computational cost.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Automatic Well Planner for Complex Well Trajectories

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[6] demonstrated application of dynamic programming for finding optimal long-term decision strategies for a certain set of geosteering problems. [7] proposed an AI based approach to steering based on the initial field planning. In [8], a simplified dynamic programming algorithm was used in a context of a more general geosteering problem with several targets.…”

Section: Introductionmentioning

confidence: 99%

Man vs machine: an experimental study of geosteering decision skills

Alyaev,

Bratvold,

Ivanova

et al. 2020

Preprint

View full text Add to dashboard Cite

With the steady growth of the amount of real-time data while drilling, operational decision-making is becoming both better informed and more complex.Therefore, as no human brain has the capacity to interpret and integrate all decision-relevant information from the data, the adoption of advanced algorithms is required not only for data interpretation but also for decision optimization itself. However, the advantages of the automatic decision-making are hard to quantify.The main contribution of this paper is an experiment in which we compare the decision skills of geosteering experts with those of an automatic decision support system in a fully controlled synthetic environment. The implementation of the system, hereafter called DSS-1, is presented in our earlier work [Alyaev et al. "A decision support system for multi-target geosteering." Journal of Petroleum Science and Engineering 183 (2019)]. For the current study we have developed an easy-to-use web-based platform which can visualize and update uncertainties in a 2D geological model. The platform has both user and application interfaces (GUI and API) allowing us to put human participants and DSS-1 into a similar environment and conditions.

show abstract

Effect of CO2 tax on energy use in oil production: waterflooding optimization under different emission costs

et al. 2022

View full text Add to dashboard Cite

Tackling emissions from hydrocarbon production is a necessity because hydrocarbon production will last for a prolonged time. As a popular hydrocarbon production method, waterflooding operation is energy-intensive and accounts for significant CO2 emissions. This article investigates the effect of CO2 tax level on recovery process of already producing fields with waterflooding. Our methodology is waterflooding optimization in reservoir simulation models, specifically optimizing well-controls. Unlike traditional studies, our optimization objective comprises two components: the profitability of hydrocarbon production and an additional tax proportional to CO2 emissions. The associated CO2 emissions is estimated using a scheme developed upon an integrated model of reservoir, surface network, and topside facility. We examine our methodology on two cases with heterogeneous reservoir models. In each case, we optimize multi-scenarios enforcing different CO2 tax rates. The solutions indicate that imposing a higher CO2 tax rate reduces both emissions and hydrocarbon production. The fractional reduction of oil produced is however smaller than the emission reduction. While an increased tax rate drives the topside equipment to operate at higher efficiencies, the main effects of a higher tax rate are reduced water injection and more efficient subsurface drainage. There is a non-linear relationship between the reduced production and emissions. For increasing tax levels there are diminishing returns on lower emissions, reflecting reduced opportunities for emission reduction by changes in the drainage strategy. Some increments on the tax rate will therefore have negligible impacts on the optimal drainage strategy, and hence an adverse effect on the profitability with negligible emission reduction.

show abstract

An Automatic Well Planner for Efficient Well Placement Optimization Under Geological Uncertainty

Cited by 4 publications

References 17 publications

An Automatic Well Planner for Complex Well Trajectories

An Automatic Well Planner for Complex Well Trajectories

Man vs machine: an experimental study of geosteering decision skills

Effect of CO2 tax on energy use in oil production: waterflooding optimization under different emission costs

Contact Info

Product

Resources

About