Abstract
The definition of the locations of new wells in mature fields is a challenging problem especially in contexts of high geological complexity and low data reliability, when running fluid-flow simulations can be extremely difficult. For this reason, we develop an innovative Surrogate Reservoir Model, based on a data-driven process, which combines Machine Learning algorithms with spatial interpolation techniques. We call our approach WIZARD (acronym for: Well Infilling optimiZAtion through Regression and Data analytics).
WIZARD is a collection of different data-driven methods for the sake of definition of new infilling well locations on the basis of the expected cumulative oil productions (after a fixed target period) of unexploited areas of the reservoir. The first method, named COSMIC, is used to find a correlation between petrophysical well properties and well productivity through a regression algorithm.
The second method, that we call WIZARDMAP, uses spatial interpolation methodologies like K-Nearest Neighbours to estimate input petrophysical well data far away the existing wells and the trained COSMIC model applied to these interpolated data to predict the expected cumulative oil productions in unexploited areas of the reservoir. Finally, predictions of WIZARMAP model are compared with the ones given by another method that we call WIZARDROC, that is a predictive model trained by using only the cumulative oil productions of the existing wells and their locations.
WIZARD workflow is applied to a highly faulted and layered reservoir with around 460 wells and 40 years production history, for which petrophysical and production data are available. Validation tests have been performed to evaluate WIZARD accuracy to forecast expected cumulative oil productions for new wells. WIZARD geological and physical soundness have been confirmed by experienced reservoir geologists and engineers, clearly showing that the methodology is reliable and therefore can be used for t least qualitative location screening of new infilling wells. This is furtherly confirmed by the satisfying match between the oil cumulative predictions of WIZARDROC and WIZARDMAP that has been obtained, indicating that the model can be reasonably used for predictive purposes.
WIZARD is an innovative Reservoir Surrogate Model that, combining Machine Learning techniques with spatial interpolation methodologies, is able to provide key insights for reservoir management and development plan, by suggesting the most promising locations for the new infilling wells.
