Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models

Assessing riverine pollutant loads is a more realistic method for analysing point and non-point anthropogenic pollution sources throughout a watershed. This study compares numerous mathematical modelling strategies for estimating riverine loads based on the chosen water quality parameters: Biochemic...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Results in engineering Ročník 22; s. 102072
Hlavní autoři:	Khairudin, Khairunnisa, Ul-Saufie, Ahmad Zia, Senin, Syahrul Fithry, Zainudin, Zaki, Rashid, Ammar Mohd, Abu Bakar, Noor Fitrah, Anas Abd Wahid, Muhammad Zakwan, Azha, Syahida Farhan, Abd-Wahab, Firdaus, Wang, Lei, Sahar, Farisha Nerina, Osman, Mohamed Syazwan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier B.V 01.06.2024 Elsevier
Témata:	Artificial neural network (ANN) Feed-forward backpropagation algorithm Multiple linear regression Radial basis neural network Riverine load Riverine load Radial basis neural network Artificial neural network (ANN) Multiple linear regression Feed-forward backpropagation algorithm
ISSN:	2590-1230, 2590-1230
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Assessing riverine pollutant loads is a more realistic method for analysing point and non-point anthropogenic pollution sources throughout a watershed. This study compares numerous mathematical modelling strategies for estimating riverine loads based on the chosen water quality parameters: Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), Suspended Solids (SS), and Ammoniacal Nitrogen (NH3–N). A riverine load model was developed by employing various input variables including river flow and pollutant concentration values collected at several monitoring sites. Among the mathematical modelling methods employed are artificial neural networks with feed-forward backpropagation algorithms and radial basis functions. The classical multiple linear regression (MLR) statistical model was used for the comparison. Four widely used statistical performance assessment metrics were adopted to evaluate the performance of the various developed models: the root mean square error (RMSE), mean absolute error (MAE), mean relative error (MRE), and coefficient of determination (R2). The considerable number of errors (with RMSE, MAE, and MRE) discovered in estimating riverine loads using the multiple linear regression (MLR) statistical model can be attributed to the nonlinear relationship between the independent variables (Q and Cx) and dependent variables (W). The feed-forward neural network model with a backpropagation algorithm and Bayesian regularisation training algorithm outperformed the radial basis neural network. This finding implies that, in addition to suspended sediment loads, riverine loads may be predicted using an artificial neural network using pollutant concentration (Cx) and river discharge (Q) as input variables. Other geographical and temporal fluctuation characteristics that may impact river water quality, on the other hand, may be incorporated as input variables to enhance riverine load prediction. Finally, riverine load analyses were successfully conducted to reduce the riverine load. •Assessing pollutant load accurately evaluates pollution sources in a watershed.•Artificial neural networks were used to predict riverine loading.•Riverine load model built with discharge & pollutant data from monitoring stations.•Feed-forward neural network with Bayesian Regularisation training is superior to radial basis function and MLR.•The developed riverine load prediction model aids in assigning load reduction allocations.
ISSN:	2590-1230 2590-1230
DOI:	10.1016/j.rineng.2024.102072