Development of Decline Curve Analysis Parameters for Tight Oil Wells Using a Machine Learning Algorithm

Table 4

The optimized network structure for ML-DCA model.

Variables
Number of neurons in input layer	15 parameters	15 parameters and	15 parameters, and
Number of neurons in hidden layer	40	50	60
Output in output layer
Data split	70% for training, 30% for testing
Function performance
Training algorithm	Bayesian regularization
Iterations to achieve optimal structure	185	250	324
Overall	0.966	0.990	0.945