Modified aquila optimizer for forecasting oil production

Oil production estimation plays a critical role in economic plans for local governments and organizations. Therefore, many studies applied different Artificial Intelligence (AI) based methods to estimate oil countries. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is well-known model that has been successfully employed various applications, including time-series forecasting. However, the ANFIS faces shortcomings its parameters during configuration process. From this point, paper works solve drawbacks of by optimizing using modified Aquila Optimizer (AO) with Opposition-Based Learning (OBL) technique. main idea developed model, AOOBL-ANFIS, enhance search process AO use AOOBL boost performance ANFIS. proposed evaluated real-world datasets collected from oilfields several metrics, Root Mean Square Error (RMSE), Absolute (MAE), coefficient determination (R2), Standard Deviation (Std), computational time. Moreover, AOOBL-ANFIS compared models include Particle Swarm Optimization (PSO)-ANFIS, Grey Wolf (GWO)-ANFIS, Sine Cosine Algorithm (SCA)-ANFIS, Slime Mold (SMA)-ANFIS, Genetic (GA)-ANFIS, respectively. Additionally, it time series forecasting methods, namely, Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Seasonal (SARIMA), Neural Network (NN). outcomes verified high which outperformed classic models.