Data-Driven Methodologies for Enhancing Efficiency and Accuracy in Wireline Formation Testing

Wireline Formation Testing (WFT) is essential for eval- uating petroleum reservoirs, providing critical data such as pressure and permeability to guide reservoir manage- ment and operational strategies. However, challenges remain in conducting these tests efficiently, particularly in determining pressure stabilization, which is often as- sessed subjectively and inconsistently. This paper intro- duces a novel methodology that combines mathemati- cal modeling, optimization, and data science to address these challenges, reducing operational time and enhanc- ing data reliability. Two models are developed: a simple analytical model and a more complex approach that ac- counts for pressure transients in greater detail, both op- timized using nonlinear regression. Quality factors (qf), derived from pressure buildup curves, are introduced to categorize tests and predict stabilization times. Addi- tionally, the methodology incorporates a survival analy- sis framework to dynamically estimate stabilization win- dows. The results highlight substantial operational ef- ficiency gains, achieving an average 75% reduction in overall buildup time. The predictive models achieved high accuracy, with R2 values exceeding 0.97 and mean pressure differences below 1 psi across most categories of pre-tests. This structured data-driven approach pro- vides robust support for real-time decision-making, en- hancing the efficiency and sustainability of WFT opera- tions.