Numerical Study of Back Propagation Learning Algorithms for Forecasting Water Quality Index

Abstract

 Artificial intelligence techniques, such as neural networks are modeling tools that can be applied to predict water quality parameters. Artificial neural networks are frequently used to model various highly variable and nonlinear physical phenomena in the water and environmental engineering fields. This article describes design and application of feed-forward, fully-connected, three-layer perceptron neural network model for computing the water quality index (WQI) for Batlagundu, Dindigul District, Tamilnadu. The modeling efforts showed that the optimal network architecture was 8-3-1 and that the best WQI predictions were associated with the back propagation (BP) algorithm. The WQI predictions of this model had significant, positive, very high correlation with the measured WQI values, implying that the model predictions explain around 95.4% of the variation in the measured WQI values. The approach presented in this article offers useful and powerful alternative to WQI computation and prediction, especially in the case of WQI calculation methods which involve lengthy computations and use of various sub-index formulae for each value or range of values of the constituent water quality variables.

Authors and Affiliations

Sarala Thambavani D

Keywords

Related Articles

 EVALUATION INDEX SYSTEM FOR PERFORMANCE EVALUATION OF ECOINDUSTRIAL THERMAL POWER PLANTS BY USING FUZZY DELPHI METHOD

 In order to promote the clean and sustainable production of coal resources, more and more eco-industrial thermal power plants (ETPPs) are established in China. Considering it is a burgeoning industry, the perf...

 An Exploration of Robotic System

 Robots are not just machines, they are many steps ahead a typical machine. Robots like machines can perform different tough jobs easily but the advancement is that they can do it by their own. Once programmed rob...

EFFECTS OF RICE BRAN OIL AND GAMMA - ORYZANOL ON ANTIOXIDANT DEFENSE IN STREPTOZOTOCIN NICOTINAMIDE INDUCED DIABETIC RATS

Rice bran oil (RBO), a unique cooking oil is produced from the pericarp and germ of Oryza sativa seeds. Oryzanol is a mixture of sterol esters of ferulic acid and is known to have several health benefits. Male albino...

PERFORMANCE IMPROVEMENT OF DIESEL ENGINE THROUGH VARIOUS ADVANCEMENTS IN TURBOCHARGING TECHNOLOGY: A REVIEW

In this paper, the effect of various advancements in turbocharging technology on diesel engine power, fuel consumption, thermal efficiency, volumetric efficiency and emissions are reviewed and analyzed.Turbochargers are...

 THE ELECTROCHEMICAL METHOD FOR OBTAINING THIN COVERINGS OFRHENIUM CHALCOGENIDES

 This paper summarizes the publications in the last years. It analyzes more than 40 scientific papers on theproduction of rhenium chalcogenides by electrochemical method. A review using various electrochemicalmethod...

Download PDF file
  • EP ID EP158824
  • DOI -
  • Views 83
  • Downloads 0

How To Cite

Sarala Thambavani D (30).  Numerical Study of Back Propagation Learning Algorithms for Forecasting Water Quality Index. International Journal of Engineering Sciences & Research Technology, 3(3), 1548-1555. https://europub.co.uk/articles/-A-158824