Table 5 Parameters of the machine learning algorithms used for pan evaporation modeling.

From: Comparative assessment of standalone and hybrid deep neural networks for modeling daily pan evaporation in a semi-arid environment

Model name

Description of parameters

DNN

Batch size-100, Learning rate = 0.3, Momentum = 0.2, Auto build = True, Nominal to Binary = True, Normalize Attributes = True, Normalize Numeric Class = True, Debug = False, Decay = False

AR

Batch size-100, Classifier = Bagging, shrinkage = 1, number of iterations = 30

SVM

Batch size-100, C = 0.1, kernel used = polykernel

RF

Batch size-100, bag Size percent = 100, max depth = 0, numbers of executions slots = 1, number of iterations = 100, random seed = 1

M5 pruned

Batch size-100, Minimum number of instances = 4

RSS

Batch size-100, Classifier = REPTree, random seed-1, subspace size = 0.5, numbers of executions slots = 1, number of iterations = 10

Back to article page