Abstract
One of the challenges in the oil industry is to predict well production in the absence of frequent flow measurement. Many researches have been done to develop production forecasting in the petroleum area. One of the machine learning approach utilizing higher-order neural network (HONN) have been introduced in the previous study. In this study, research focus on normalization impact to the HONN model, specifically for univariate time-series dataset. Normalization is key aspect in the pre-processing stage, moreover in neural network model.
Highlights
Oil production forecasting is important for petroleum industry to deliver planning and investment strategy
In the case studies described in this paper, the Uniform quantile transformation (UQT) has promising method to improve prediction accuracy
Future research may extent to evaluate UQT with various activation function which align with the range of normalized value (0 to 1)
Summary
Oil production forecasting is important for petroleum industry to deliver planning and investment strategy.Many researches have focused to deliver prediction model for the oil production with various approaches.Artificial neural network with imperialist competitive algorithm have been used to predict oil flow rate [1].The utilization of nonlinear autoregressive neural network with exogenous input (NARX) have been used to forecast oil production [2]. Oil production forecasting is important for petroleum industry to deliver planning and investment strategy. Many researches have focused to deliver prediction model for the oil production with various approaches. Artificial neural network with imperialist competitive algorithm have been used to predict oil flow rate [1]. The utilization of nonlinear autoregressive neural network with exogenous input (NARX) have been used to forecast oil production [2]. One variance neural network algorithm, called higher-order neural network (HONN), have been introduced in the previous study [3]. The study introduced dataset of 5 (five) oil production well from Campay Basin Field, India. The research was focused on predicting cumulative production of 5 wells, instead of predicting individual well
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have