A Comparative Analysis of Data-Driven Empirical and Artificial Intelligence Models for Estimating Infiltration Rates

Table 3

Comparative statistics for fit of model to the observed infiltration data.

Methods		Training phase					Testing phase
		SSE (cm^2/min^2)	NRMSE	WI	MAE (cm/min)	NSE	SSE (cm^2/min^2)	NRMSE	WI	MAE (cm/min)	NSE
Conventional models	Horton	4.645	0.135	0.610	0.123	0.236	1.650	0.149	0.636	0.127	0.319
	Modified Kostiakov	4.485	0.133	0.613	0.118	0.263	1.474	0.141	0.686	0.119	0.392
	Philip	4.482	0.133	0.616	0.117	0.263	1.474	0.141	0.687	0.119	0.392
MLR		4.710	0.202	0.136	0.123	0.242	1.668	0.210	0.150	0.128	0.312
GRG		3.943	0.184	0.124	0.104	0.352	0.837	0.148	0.106	0.101	0.655
AI-based models	ANN	0.097	0.020	0.996	0.018	0.984	0.380	0.071	0.954	0.051	0.843
	MGGP	0.838	0.057	0.962	0.059	0.862	0.487	0.081	0.938	0.071	0.798
	MGGP-GRG	0.836	0.057	0.962	0.059	0.862	0.483	0.081	0.938	0.070	0.801