On the Investigation of Monthly River Flow Generation Complexity Using the Applicability of Machine Learning Models

Table 3

The performance metrics of the applied ML predictive models through the training and validating phases when modeling the three investigated rivers.

Model	Upper Zab				Lower Zab				Diyala
	Training		Validating		Training		Validating		Training		Validating
	R^2	RMSE (m^3/s)	R^2	RMSE (m^3/s)	R^2	RMSE (m^3/s)	R^2	RMSE (m^3/s)	R^2	RMSE (m^3/s)	R^2	RMSE (m^3/s)
MART	0.93	85	0.84	113	0.90	62	0.75	95	0.85	66	0.78	73
GMDH	0.81	141	0.64	169	0.47	144	0.46	149	0.51	120	0.42	118
GEP	0.53	222	0.47	208	0.41	151	0.40	157	0.50	121	0.5	109