Predictive Models for Oil in Place for Oil Rim Reservoirs in the Niger Delta Using Machine Learning Approach

One of the key factors that analysts consider when calculating the economics of oil field development is the amount of oil in place (OIP). Conventional methods used for its estimation have some features affecting their predictive capabilities and applications. In addition, Oil bidders have limited time to evaluate and rank reservoirs from complex and large reservoir data packages - which sometimes fees are paid for their access. In this study, data-driven machine learning models - artificial neural network (ANN), support vector regression (SVR) and multiple linear regression (MLR) were developed for quick estimation of OIP for oil rim reservoirs in the Niger Delta. The models were evaluated using statistical error tools, and the results showed reasonable predictions. The sensitivity analysis performed on the selected input parameters showed that areal extent has the greatest impact on the estimation of the OIP with 29.94 %, oil formation volume factor has 22.74 % impact, oil column thickness was 16.61 %, m-factor has 13.29 %, water saturation was 9.01 %, and lastly porosity has 8.38 %. Comparison with recovery factor surrogate models existing in open literature were also carried out. The newly developed models can be helpful for oil bidders in ranking and evaluation of oil rim reservoirs in the Niger Delta.