Browsing by Author "Kwio-Tamale, Julius Caesar"

Now showing 1 - 2 of 2

Comparison of physical and statistical models in predicting space-time decay of residual chlorine in water distribution system
(Kyambogo University[unpublished work], 2022-10) Kwio-Tamale, Julius Caesar
Chlorine is the most widely used disinfectant in water distribution due to its efficacy, ease of application, low cost and extended disinfection durability. The World Health Organization recommends concentrations of residual chlorine in drinking water to be within 0.2 – 5 mg/l. Concentrations lower than 0.2 mg/l expose water consumers to secondary water-borne diseases. Chlorine concentrations more than 5 mg/l expose consumers to carcinogenic disinfection by-products. Studies on comparative analysis of performance of physical and statistical models in predicting chlorine decay in drinking water distribution system are lacking. The specific objectives of this study were: (1) characterization of residual chlorine decay parameters in water distribution, (2) assessment of space-time decay of chlorine in water distribution, (3) comparison of performance of models in predicting chlorine decay in water distribution and (4) identification of appropriate model(s) for predicting chlorine decay in water distribution system. Performance of EPANET physical model was compared with statistical models of multiple linear regression (MLR), principal component regression (PCR), lasso regression (LR), ridge regression (RR), decision tree (DT), random forest (RF) and artificial neural network (ANN). ANN performed best with R2 of 94% followed by MLR (63%), PCR (61%), RF (55%) and DT (41%). Initial chlorine and electrical conductivity were the two most significant parameters in water distribution that together contributed to about 90% of chlorine decay. Based on generalizability, dimensionality control and interpretability as desired factors for a good model, linear regression with R-squared of 63% and 0.045 mg/l error estimate performed best in predicting residual chlorine. Water zoning is recommended with existing water reservoirs as secondary chlorination points to maintain residual chlorine concentrations within 0.2 – 5 mg/l. In return, high and low dosages that cause carcinogenic disinfection by-products and predispose public health to secondary pathogenic infectious water-borne diseases respectively will both be avoided throughout water distribution network
Space–time prediction of residual chlorine in a water distribution network using artificial intelligence and the EPANET hydraulic model
(Water Practice & Technology, 2024-09-10) Kwio-Tamale, Julius Caesar; Onyutha, Charles
Insufficient knowledge of physical models and difficulty in fitting statistical models impair the choice of models to regulate residual chlorine in water distribution. This paper compared the performance of physical and statistical models in predicting residual chlorine concentrations in drinking water distribution. Drinking water was sampled from the downstream 128 water points water pipeline. Online chlorine concentrations were determined at water draw-off points. EPANET, the physical model, was used because of its efficiency in tracking dissolved chemicals. Statistical models used were regression, decision tree, random forest and artificial neural network. In the whole distribution network, the artificial neural network performed at R2 of 94%, multi-linear regression (62%), random forest (55%), decision tree (41%), and EPANET (24%). However, EPANET yielded improved performance with R2 above 70% when separately applied to individual sub-distribution networks; hence, is recommended for secondary chlorination in small distribution networks. For modelling large distribution networks, statistical models, especially an artificial neural network, are recommended. However, such cases still need support from confirmatory systems of interpretable parametric or hydraulic models that can achieve good performance with R2 80%. Water utilities can use these results to deploy model(s) for managing residual chlorine within safe limits of residual chlorine concentration in water distribution practice.