Abstract
One important property of oil and gas reservoirs is permeability, which has proven to be difficult to predict. Empirical and regression models are the current industrial practice for predicting permeability due to high cost and time consumption associated with laboratory measurement. In recent times, machine learning algorithms have been employed for the prediction of permeability due to their better predictive capability. In this study, a novel competitive ensemble machine learning model is introduced for predicting permeability in heterogeneous oil and gas reservoirs. In this approach, the well log data were partitioned into a number of regions using a clustering algorithm and each region was modeled by a machine learning algorithm. Contrary to previous studies that combine the outputs of the models from each region, we propose two selection mechanisms: nearest cluster center and K-nearest neighbor, which select the best representative ensemble member for a data point to be predicted. The novelties of the proposed ensemble are the simplicity of the selection mechanism employed as well as the elimination of functions and/or training that are normally required in finding the weight of models forming the ensemble. Several homogeneous and heterogeneous combinations of ensemble members were developed and investigated to compare their performances. The results showed that the competitive ensemble models improve the prediction accuracy of the permeability when compared to the single models. Competitive heterogeneous ensembles show better performance when compared with their homogeneous counterparts. In addition, the proposed competitive ensemble outperform three other existing ensemble approaches. These experimental results showed the potentials of the developed competitive ensemble for better prediction of permeability in heterogeneous reservoirs.