A Cognitive Data-Driven Single-Well Modeling Workflow for Reservoir Deliverability Predictions – Expanding the Wireline Formation Tester Application Envelope

Abstract

In today's dynamically challenging E&P industry, exploration activities demand for out-of-the-box measures to make the most out of the data available at hand. Instead of relying on time consuming and cost-intensive deliverability testing, there is a strong push to extract maximum possible information from time- and cost-efficient wireline formation testers in combination with other openhole logs to get critical reservoir insight. Consequently, driving efficiency in the appraisal process by reducing redundant expenditures linked with reservoir evaluation. Employing a data-driven approach, this paper addresses the need to build single-well analytical models that combines knowledge of core data, petrophysical evaluation and reservoir fluid properties. Resultantly, predictive analysis using cognitive processes to determine multilayer productivity for an exploratory well is achieved. Single Well Predictive Modeling (SWPM) workflow is developed for this case which utilizes plethora of formation evaluation information which traditionally resides across siloed disciplines. A tailor-made workflow has been implemented which goes beyond the conventional formation tester deliverables while incorporating PVT and numerical simulation methodologies. Stage one involved reservoir characterization utilizing Interval Pressure Transient Testing (IPTT) done through the mini-DST operation on wireline formation tester. Stage two concerns the use of analytical modeling to yield exact solution to an approximate problem whose end-product is an estimate of the Absolute Open Flow Potential (AOFP). Stage three involves utilizing fluid properties from downhole fluid samples and integrating with core, OH logs, and IPTT answer products to yield a calibrated SWPM model, which includes development of a 1D petrophysical model. Additionally, this stage produces a 3D simulation model to yield a reservoir production performance deliverable which considers variable rock typing through neural network analysis. Ultimately, stage four combines the preceding analysis to develop a wellbore production model which aids in optimizing completion strategies. The application of this data-driven and cognitive technique has helped the operator in evaluating the potential of the reservoir early-on to aid in the decision-making process for further investments. An exhaustive workflow is in place that can be adopted for informed reservoir deliverability modeling in case of early well-life evaluations.