Forecasting crude oil production using quadratic regression and layer recurrent neural network models

• Main Authors: Pwasong, Augustine, Sathasivam, Saratha
• Format: Conference Proceeding
• Language: English
• Subjects: Computer simulation; Crude oil; Economic forecasting; Error detection; Forecasting techniques; Neural networks; Petroleum production; Recurrent neural networks; Regression analysis; Regression models; Root-mean-square errors
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/1.4954514

In this study, a quadratic regression model and a two layered layer recurrent neural network (TLLRNN) method were used to model forecasting performance of the daily crude oil production data of the Nigerian National Petroleum Corporation (NNPC). The two methods were applied on the log difference series of the NNPC series. The results indicates that the two layered layer recurrent neural network model have better forecasting performance greater than the quadratic regression method based on the mean square error sense. The root mean square error (RMSE) and the mean absolute error (MAE) were applied to ascertain the assertion that the two layered layer recurrent neural network method have better forecasting performance greater than the quadratic regression method. These results were achieved from 1 day ahead predictions, 3 days ahead predictions and 5 days ahead predictions for 50 days sample length, 100 days sample length, 200 days sample length, 400 days sample length and 800 days sample length. The data used in this study is a time series data obtained from the daily crude oil production of the Nigerian National Petroleum Corporation (NNPC) for a period of six years (1st January, 2008 - 31st December, 2013). The analysis for this study was simulated using MATLAB software, version 8.03.