A Flow Feature Clustering-Assisted Uncertainty Analysis Workflow for Optimal Well Rates in Waterflood Projects

Abstract

Summary The optimal schedule based on single geologic model may not necessarily result in favorable outcomes on the real field due to geologic uncertainty. This paper proposes an efficient workflow to evaluate the uncertainty of optimal well rates in waterflood problems. Specifically, a flow feature clustering method is derived using streamline and unsupervised machine-learning techniques to minimize the number of geologic realizations needed for geologic uncertainty representation, thus significantly accelerating the workflow. Given a set of historical production and injection data, first, an ensemble of Nreal history-matched geologic realizations is generated using ensemble-smoother with multiple data assimilation (ESMDA). Subsequently, the streamline time of flight (TOF) and principal component analysis (PCA) are used to extract the flow feature of all realizations, based on which k-means clustering algorithm generates a subset of Nclust realizations representing the whole ensemble. The rate optimization is performed on each of the representative realizations using a streamline-based rate optimization algorithm that seeks to maximize the oil production during the optimization period. The distribution of optimal schedules obtained by optimizing the representative realizations is shown to be in high correspondence with that obtained by optimizing the full ensemble. Using the optimal schedule distribution, the key wells are identified, for which rate change is advised with high certainty. The workflow is tested on a synthetic 2D reservoir model as well as a 3D field-scale benchmark reservoir model [sensitivity analysis of the impact of geological uncertainties on production (SAIGUP) model]. The novelty of this work is the combination of the streamline-extracted flow features and unsupervised machine-learning methods to formulate an efficient workflow for uncertainty analysis of optimal well schedules. The proposed approach ensures quality and rigor of uncertainty analysis with a significantly reduced number of geologic realizations and thus makes the approach well-suited for large-scale field applications.

Constraint optimization of an integrated production model utilizing history matching and production forecast uncertainty through the ensemble Kalman filter

“…Chen et al 12 proposed an efficient workflow for evaluating the uncertainty of optimal well rates in waterflood problems. Their research is highly commendable and presents several innovative contributions.…”

“…In their study, Chen et al 12 employed a set of historical production and injection data. Initially, they generated an ensemble of history-matched geologic realizations using the ensemble smoother with multiple data assimilation (ESMDA) technique.…”

“…Based on these features, they employed the k-means clustering algorithm to derive a subset of realizations that represent the entire ensemble. Given the exceptional nature and comprehensiveness of Chen et al’s 12 work, this article aims to follow their methodology. Moreover, this research endeavors to incorporate the separator controller in the constraint optimization process to prevent the occurrence of slug flow regimes before the separator.…”