Adaptive Neuro-Fuzzy Inference System for Predicting Norovirus in Drinking Water Supply

Noroviruses represent a leading cause of acute gastroenteritis in most developed countries. Modeling of general microbial occurrence in drinking water is a very active field of study and provides reliable information for predicting microbial risks in drinking water. In this paper, an adaptive neuro-fuzzy inference system (ANFIS) is proposed to generate fuzzy rules from a given input/output data. Trained ANFIS is then used for predicting the total number of Norovirus in raw surface water in terms of new input measurements (i.e., water pH, turbidity, conductivity, temperature and rain). The study is based on the analysis of raw water samples from Nødre Romrike Vannverk water treatment plant in Oslo, Norway. The ANFIS model has shown remarkable prediction ability of the number of Norovirus in drinking water with high accuracy. Significant relationship between Norovirus, turbidity, conductivity and temperature is obtained based on model results. The findings suggest that Norovirus out breaks may be predicted based on certain environmental factors. The ability to predict the Norovirus in drinking water would make the prevention of potential outbreaks possible by applying the proper water treatment for better healthcare management.