Use of Artificial Neural Networks and Multiple Linear Regression Model for the Prediction of Dissolved Oxygen in Rivers: Case Study of Hydrographic Basin of River Nyando, Kenya

Table 4

MLR performance and model equations for water quality parameters and LULC.

	Input model parameters	R	Adjusted R^2	MSE	RMSE	MAE	MLR model equation
1	EC, TP, TN	0.53000	0.240199	0.61105	0.78169	0.58821
2	EC, TP, TN, pH	0.55835	0.258816	0.58483	0.76474	0.58188
3	EC, TP, TN, pH, temperature	0.57025	0.259036	0.57341	0.75724	0.58235
4	All WQ parameters	0.61999	0.281797	0.52310	0.72326	0.53699
5	LULC categories: forest; wetlands; light veg; agric land	0.9917	0.96147	0.00085	0.02929	0.02266