Application of artificial neural networks and mathematical modeling for the prediction of water quality variables (case study: southwest of Iran)

River water quality monitoring using traditional water sampling and laboratory analyses is expensive and time-consuming. The application of artificial neural network (ANN) models to simulate water quality parameters is cost-effective, quick, and reliable. This study provides two methods of mathemati...

Full description

Saved in:
Bibliographic Details
Published in:Desalination and water treatment 2016-12, Vol.57 (56), p.27073-27084
Main Authors: Salami, E.S., Salari, M., Ehteshami, M., Bidokhti, N.T., Ghadimi, H.
Format: Article
Language:English
Subjects:
Artificial neural networks
Computer simulation
Environmental monitoring
Freshwater
Learning theory
Mathematical analysis
Mathematical models
Modeling
Monitoring
Neural networks
Polynomial
Rivers
Water analysis
Water monitoring
Water quality
Water quality management
Water quality measurements
Water sampling
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:River water quality monitoring using traditional water sampling and laboratory analyses is expensive and time-consuming. The application of artificial neural network (ANN) models to simulate water quality parameters is cost-effective, quick, and reliable. This study provides two methods of mathematical and ANN modeling to simulate and forecast five important river water quality indicators (DO, TDS, SAR, BOD5, HCO3) correlated with variables such as EC, temperature, and pH which can be measured easily and almost with no cost. The mathematical method is based on polynomial fitting with least square method and the neural network model was developed using a feed-forward algorithm. The 35 years’ data were collected from 7 monitoring stations and 5 rivers located in southwest of Iran. DO concentration was simulated using an equation and a neural model. Two equations were calibrated for estimating TDS while SAR is simulated using a mathematical and neural model. Another two neural models were developed for BOD5 and HCO3 simulations. An acceptable precision was achieved, as shown in model verification results. Presented models and equations are reliable/useable tools for studying in similar locations (rivers), as a proper replacement for traditional water quality measuring practices.
ISSN:1944-3986
1944-3994
1944-3986
DOI:10.1080/19443994.2016.1167624