Classification of Reservoir Recovery Factor for Oil and Gas Reservoirs: A Multi-Objective Feature Selection Approach

The accurate classification of reservoir recovery factor is dampened by irregularities such as noisy and high-dimensional features associated with the measurements or characterization. These irregularities, especially a larger number features, make it difficult to perform factor, generated are usually heterogeneous. Consequently, imperative select relevant while preserving amplifying accuracy. This phenomenon can be treated multi-objective optimization problem, since there two conflicting objectives: minimizing high In this study, wrapper-based feature selection approaches proposed estimate set Pareto optimal solutions that represents optimum trade-off between these objectives. Specifically, three algorithms—Non-dominated Sorting Genetic Algorithm II (NSGA-II), Multi-Objective Grey Wolf Optimizer (MOGWO) Particle Swarm Optimization (MOPSO)—are investigated in selecting from dataset. To best our knowledge, first time has been used for classification. Artificial Neural Network (ANN) algorithm evaluate selected features. Findings experimental results show MOGWO-ANN outperforms other (MOPSO NSGA-II) terms producing non-dominated small subset reduced error rate.