Using algorithm (Levenberg marquardt)‎ as activation function to prediction water quality index (WQI)‎ in Kastamonu City-Turkey

Abstract EN

The computer program of artificial neural network (ANN) to prediction the water quality index (WQI) at Municipality Water of Kastamonu City-Turkey.

WQI demonstrates the overall water quality at a specific site and specific time depending on some water quality factors for 5 years (from Jan 2011 to Dec 2015).

The simple feedforward network is applied with one of the training algorithms the standard back-propagation algorithm (Levenberg-Marquardt) (train-lm).

In this study, one hidden layer has been selected for modelling and the number of the hidden neuron is set (n+1) and (2n+1) of input nodes.

This discovering can be depicted by using the way that the quantity of hidden neurons straightforwardly affects the execution of the system and we can see that model the standard back-propagation algorithm (Levenberg-Marquardt) train-lm as activation function (train-Lm) is optimal to predict of water quality index and as more direct and very effective options to predict surface water quality and other water bodies.