PMID- 36459893
OWN - NLM
STAT- MEDLINE
DCOM- 20230105
LR  - 20230111
IS  - 1879-2448 (Electronic)
IS  - 0043-1354 (Linking)
VI  - 229
DP  - 2023 Feb 1
TI  - A novel approach for estimating and predicting uncertainty in water quality index 
      model using machine learning approaches.
PG  - 119422
LID - S0043-1354(22)01367-7 [pii]
LID - 10.1016/j.watres.2022.119422 [doi]
AB  - With the significant increase in WQI applications worldwide and lack of specific 
      application guidelines, accuracy and reliability of WQI models is a major issue. 
      It has been reported that WQI models produce significant uncertainties during the 
      various stages of their application including: (i) water quality indicator 
      selection, (ii) sub-index (SI) calculation, (iii) water quality indicator 
      weighting and (iv) aggregation of sub-indices to calculate the overall index. 
      This research provides a robust statistically sound methodology for assessment of 
      WQI model uncertainties. Eight WQI models are considered. The Monte Carlo 
      simulation (MCS) technique was applied to estimate model uncertainty, while the 
      Gaussian Process Regression (GPR) algorithm was utilised to predict uncertainties 
      in the WQI models at each sampling site. The sub-index functions were found to 
      contribute to considerable uncertainty and hence affect the model reliability - 
      they contributed 12.86% and 10.27% of uncertainty for summer and winter 
      applications, respectively. Therefore, the selection of sub-index function needs 
      to be made with care. A low uncertainty of less than 1% was produced by the water 
      quality indicator selection and weighting processes. Significant statistical 
      differences were found between various aggregation functions. The weighted 
      quadratic mean (WQM) function was found to provide a plausible assessment of 
      water quality of coastal waters at reduced uncertainty levels. The findings of 
      this study also suggest that the unweighted root means squared (RMS) aggregation 
      function could be potentially also used for assessment of coastal water quality. 
      Findings from this research could inform a range of stakeholders including 
      decision-makers, researchers, and agencies responsible for water quality 
      monitoring, assessment and management.
CI  - Copyright (c) 2022 The Author(s). Published by Elsevier Ltd.. All rights reserved.
FAU - Uddin, Md Galal
AU  - Uddin MG
AD  - Civil Engineering, School of Engineering, College of Science and Engineering, 
      University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; 
      MaREI Research Centre, University of Galway, Ireland. Electronic address: 
      u.mdgalal1@nuigalway.ie.
FAU - Nash, Stephen
AU  - Nash S
AD  - Civil Engineering, School of Engineering, College of Science and Engineering, 
      University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; 
      MaREI Research Centre, University of Galway, Ireland.
FAU - Rahman, Azizur
AU  - Rahman A
AD  - School of Computing, Mathematics and Engineering, Charles Sturt University, Wagga 
      Wagga, Australia; The Gulbali Institute of Agriculture, Water and Environment, 
      Charles Sturt University, Wagga Wagga, Australia.
FAU - Olbert, Agnieszka I
AU  - Olbert AI
AD  - Civil Engineering, School of Engineering, College of Science and Engineering, 
      University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; 
      MaREI Research Centre, University of Galway, Ireland.
LA  - eng
PT  - Journal Article
DEP - 20221125
PL  - England
TA  - Water Res
JT  - Water research
JID - 0105072
SB  - IM
MH  - *Water Quality
MH  - *Environmental Monitoring/methods
MH  - Reproducibility of Results
MH  - Uncertainty
MH  - Computer Simulation
OTO - NOTNLM
OT  - Cork harbour
OT  - Gaussian processes regression
OT  - Monte Carlo simulation
OT  - Uncertainty
OT  - Water quality index
COIS- Declaration of Competing Interest The authors state that they did not experience 
      competing financial interests or personal relationships that could have been 
      influenced by the work reported in this paper.
EDAT- 2022/12/03 06:00
MHDA- 2023/01/06 06:00
CRDT- 2022/12/02 18:24
PHST- 2022/07/21 00:00 [received]
PHST- 2022/11/20 00:00 [revised]
PHST- 2022/11/23 00:00 [accepted]
PHST- 2022/12/03 06:00 [pubmed]
PHST- 2023/01/06 06:00 [medline]
PHST- 2022/12/02 18:24 [entrez]
AID - S0043-1354(22)01367-7 [pii]
AID - 10.1016/j.watres.2022.119422 [doi]
PST - ppublish
SO  - Water Res. 2023 Feb 1;229:119422. doi: 10.1016/j.watres.2022.119422. Epub 2022 
      Nov 25.