Research Article
Data-Driven Model for the Prediction of Total Dissolved Gas:
Robust Artificial Intelligence Approach
Mohamed Khalid AlOmar ,
1
Mohammed Majeed Hameed ,
1
Nadhir Al-Ansari ,
2
and Mohammed Abdulhakim AlSaadi
3,4
1
Department of Civil Engineering, Al-Maaref University College, Ramadi, Iraq
2
Civil Engineering Department, Environmental and Natural Resources Engineering, Lulea University of Technology,,
97187 Lulea, Sweden
3
National Chair of Materials Science and Metallurgy, University of Nizwa, Nizwa, Oman
4
Nanotechnology&CatalysisResearchCentre(NANOCAT),IPSBuilding,UniversityofMalaya,50603KualaLumpur,Malaysia
CorrespondenceshouldbeaddressedtoMohamedKhalidAlOmar;mohd.alomar@yahoo.com
Received 10 October 2020; Revised 27 November 2020; Accepted 15 December 2020; Published 30 December 2020
AcademicEditor:Yi-ZhangJiang
Copyright © 2020 Mohamed Khalid AlOmar et al. is is an open access article distributed under the Creative Commons
AttributionLicense,whichpermitsunrestricteduse,distribution,andreproductioninanymedium,providedtheoriginalworkis
properly cited.
Saturatedtotaldissolvedgas(TDG)isrecentlyconsideredasaseriousissueintheenvironmentalengineeringfieldsinceitstands
behindthereasonsforincreasingthemortalityratesoffishandaquaticorganisms.eaccurateandmorereliablepredictionof
TDG has a very significant role in preserving the diversity of aquatic organisms and reducing the phenomenon of fish deaths.
Herein,twomachinelearningapproachescalledsupportvectorregression(SVR)andextremelearningmachine(ELM)havebeen
applied to predict the saturated TDG% at USGS 14150000 and USGS 14181500 stations which are located in the USA. For the
USGS14150000station,therecordedsamplesfrom13October2016to14March2019(75%)wereusedfortrainingset,andthe
restfrom15March2019to13October2019(25%)wereusedfortestingrequirements.Similarly,forUSGS14181500station,the
hourlydatasampleswhichcoveredtheperiodfrom9June2017till11March2019wereusedforcalibratingthemodelsandfrom
12 March 2019 until 9 October 2019 were used for testing the predictive models. Eight input combinations based on different
parametershavebeenestablishedaswellasninestatisticalperformancemeasureshavebeenusedforevaluatingtheaccuracyof
adoptedmodels,forinstance,notlimited,correlationofdetermination(R
2
),meanabsoluterelativeerror(MAE),anduncertainty
at95%(U
95
).eobtainedresultsofthestudyforbothstationsrevealedthattheELMmanagedefficientlytoestimatetheTDGin
comparisontoSVRtechnique.ForUSGS14181500station,thestatisticalmeasuresforELM(SVR)were,respectively,reportedas
R
2
of0.986(0.986),MAEof0.316(0.441),and U
95
of3.592(3.869).Lastly,forUSGS14181500station,thestatisticalmeasuresfor
ELM(SVR)were,respectively,reportedas R
2
of0.991(0.991),MAEof0.338(0.396),and U
95
of0.832(0.837).Inaddition,ELM’s
trainingprocesscomputationaltimeisstatedtobemuchshorterthanthatofSVM.eresultsalsoshowedthatthetemperature
parameter was the most significant variable that influenced TDG relative to the other parameters. Overall, the proposed model
(ELM)provedtobeanappropriateandefficientcomputer-assistedtechnologyforsaturatedTDGmodelingthatwillcontributeto
the basic knowledge of environmental considerations.
1. Introduction
Water encounters substantial volumes of air and bubbles
during the flood discharge and is transferred down the
watershedtothedeep-waterbasin.Sincethepressureinthe
quenchingbasinnotonlyincreaseswithincreasingdepthof
water but also with kinetic pressure, and subsequently, the
air and bubbles are under much greater pressure than the
surface atmosphere. Consequently, a significant amount of
airdissolvesinthewaterandthetotaldissolvedgas(TDG)is
supersaturated [1]. e average dissolved gas content in
water is often controlled by two parameters, the water
temperature and the barometric pressure. Many essential
gases, such as oxygen, nitrogen, argon, and carbon dioxide,
Hindawi
Advances in Civil Engineering
Volume 2020, Article ID 6618842, 20 pages
https://doi.org/10.1155/2020/6618842