Forecasting Natural Gas Production Using Various Regression Models

Natural gas is an important energy sources governing the world economy. Therefore, accurate forecasting models for its production rate are needed to provide better planning. In the present study, various modeling approaches are used to model global natural gas production (NGP). The regression models developed are validated using some statistical approaches. The developed models are then compared using a test data set which is not utilized during construction of models. Mean absolute percentage error is used for comparing the developed modes. The results reveal that proposed models are capable of giving adequate prediction for the NGP with an acceptable accuracy level. Additionally, the compared results show that the S regression model is more reliable than the other regression models.