Download PDFOpen PDF in browser

Prediction of Water Quality Variation Affected by Tributary Inputs in large Rivers Using ANN Model

8 pagesPublished: September 20, 2018

Abstract

In this study, an enhanced ANN model was developed to analyze the water quality variation at the river confluence by incorporating the resilient propagation algorithm to increase the model accuracy. An ensemble modeling with stratified sampling method was also developed in order to reduce the influence of the input data and model parameters on the prediction of river water quality. The water quality parameters such as pH, electric conductivity (EC), DO and chlorophyll-a, were predicted using proposed ANN model in the large river which is affected by pollutant inputs from the tributary river. The results of model simulation showed that the pollutant input from the tributary affected the water quality of the mainstream. The model prediction using water quality data of the tributary river as the input data in addition to the mainstream data produced better results than the simulation using mainstream data only, especially for EC and DO, R2 value was improved by 30.9% and 20.6%, respectively.

Keyphrases: ensemble ann model, tributary inputs, water quality

In: Goffredo La Loggia, Gabriele Freni, Valeria Puleo and Mauro De Marchis (editors). HIC 2018. 13th International Conference on Hydroinformatics, vol 3, pages 1919-1926.

BibTeX entry
@inproceedings{HIC2018:Prediction_Water_Quality_Variation,
  author    = {Il Won Seo and Se Hun Yun},
  title     = {Prediction of Water Quality Variation Affected by Tributary Inputs in large Rivers Using ANN Model},
  booktitle = {HIC 2018. 13th International Conference on Hydroinformatics},
  editor    = {Goffredo La Loggia and Gabriele Freni and Valeria Puleo and Mauro De Marchis},
  series    = {EPiC Series in Engineering},
  volume    = {3},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2516-2330},
  url       = {/publications/paper/h8Fh},
  doi       = {10.29007/tvb3},
  pages     = {1919-1926},
  year      = {2018}}
Download PDFOpen PDF in browser