... function to evaluate this model. The 70% for Training and 30% for Testing data split commonly used for ANN models was applied and the data set used was normalized. The target (ROP) was made to be attribute 1 (first column) followed by the input attributes as shown in Figure 3 . This was to ensure...

... capacity of the developed ANN model was assessed using 500 randomly generated datasets that were not part of the model training process. The results obtained indicate that the developed model predicted 97% of these new datasets with an MSE of 375.021, RMSE of 19.370, AAPRE of 6.090 and R 2 of 0.9731...

... correlation determination ANN model multiphase flow bottom-hole pressure estimation prediction pressure gradient Upstream Oil & Gas dataset estimation distribution plot bottom-hole pressure algorithm artificial neural network model intelligent model society of petroleum engineers...

... Oladipo et al (2009) also developed an ANN model to predict viscosity and wax deposition potential of Nigerian Crude oil and gas condensates, using six wells for training and five wells for testing. The authors reported better results than those obtained using conventional methods...

... to evaluate the accuracy of the new Artificial Neural Network to the existing empirical correlations. The ANN model outperformed the existing empirical correlations by the statistical parameters used with a lowest rank of 0.855 and better performance plot. artificial intelligence pvt correlation pvt...