Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs

Table 6

Parameter setting of random-forest model.

Parameters	Values
Number of base classifiers (number of trees)	400
Criterion	Mean squared error (MSE)
Minimum number of samples in each leaf node	1
Minimum number of samples for internal nodes (nonleaf nodes)	2
Minimum weight coefficient of leaf node	0.0
Maximum number of features	15
Maximum number of nodes in leaf	No limitation
Maximum depth of the tree	No limitation
Out-of-pocket score	True
Sampling method	Bootstrap
Random state	Default random number