Enhancement of Reflood Test Prediction by Integrating Machine Learning and Data Assimilation Technique

Table 3

The selection of the DNN hyperparameters.

Quantity	Selected values
Number of hidden layers	2
Number of nodes in the hidden layer	256, 128
Loss function	MSE
Activator	ReLU
Optimizer	Adam
Learning rate	0.01
Epochs	200
Validation split	10%