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...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Elsevier B.V.
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833350545807507456 |
|---|---|
| author | Khairudin K. Ul-Saufie A.Z. Senin S.F. Zainudin Z. Rashid A.M. Abu Bakar N.F. Anas Abd Wahid M.Z. Azha S.F. Abd-Wahab F. Wang L. Sahar F.N. Osman M.S. |
| author2 | 57838061200 |
| author_facet | 57838061200 Khairudin K. Ul-Saufie A.Z. Senin S.F. Zainudin Z. Rashid A.M. Abu Bakar N.F. Anas Abd Wahid M.Z. Azha S.F. Abd-Wahab F. Wang L. Sahar F.N. Osman M.S. |
| author_sort | Khairudin K. |
| building | UNITEN Library |
| collection | Institutional Repository |
| content_provider | Universiti Tenaga Nasional |
| content_source | UNITEN Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | 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. ? 2024 The Author(s) |
| format | Article |
| id | my.uniten.dspace-36588 |
| institution | Universiti Tenaga Nasional |
| publishDate | 2025 |
| publisher | Elsevier B.V. |
| record_format | dspace |
| spelling | my.uniten.dspace-365882025-03-03T15:43:15Z Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models Khairudin K. Ul-Saufie A.Z. Senin S.F. Zainudin Z. Rashid A.M. Abu Bakar N.F. Anas Abd Wahid M.Z. Azha S.F. Abd-Wahab F. Wang L. Sahar F.N. Osman M.S. 57838061200 55358162200 56644623000 59052812100 57205730172 35110898100 58979033300 56166798400 57208972231 59448610500 58979033400 55319956200 Ammonia Biochemical oxygen demand Dissolved oxygen Errors Mean square error Radial basis function networks River pollution Rivers Suspended sediments Water quality Artificial neural network Feed-forward backpropagation algorithm Feedforward backpropagation Input variables Load predictions Multiple linear regressions Pollutant concentration Radial basis neural networks Riverine load Statistic modeling Multiple linear regression 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. ? 2024 The Author(s) Final 2025-03-03T07:43:15Z 2025-03-03T07:43:15Z 2024 Article 10.1016/j.rineng.2024.102072 2-s2.0-85189939391 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189939391&doi=10.1016%2fj.rineng.2024.102072&partnerID=40&md5=1b41e5180e4e2c5be04e5a5ecaa86eed https://irepository.uniten.edu.my/handle/123456789/36588 22 102072 All Open Access; Gold Open Access Elsevier B.V. Scopus |
| spellingShingle | Ammonia Biochemical oxygen demand Dissolved oxygen Errors Mean square error Radial basis function networks River pollution Rivers Suspended sediments Water quality Artificial neural network Feed-forward backpropagation algorithm Feedforward backpropagation Input variables Load predictions Multiple linear regressions Pollutant concentration Radial basis neural networks Riverine load Statistic modeling Multiple linear regression Khairudin K. Ul-Saufie A.Z. Senin S.F. Zainudin Z. Rashid A.M. Abu Bakar N.F. Anas Abd Wahid M.Z. Azha S.F. Abd-Wahab F. Wang L. Sahar F.N. Osman M.S. Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models |
| title | Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models |
| title_full | Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models |
| title_fullStr | Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models |
| title_full_unstemmed | Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models |
| title_short | Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models |
| title_sort | enhancing riverine load prediction of anthropogenic pollutants: harnessing the potential of feed-forward backpropagation (ffbp) artificial neural network (ann) models |
| topic | Ammonia Biochemical oxygen demand Dissolved oxygen Errors Mean square error Radial basis function networks River pollution Rivers Suspended sediments Water quality Artificial neural network Feed-forward backpropagation algorithm Feedforward backpropagation Input variables Load predictions Multiple linear regressions Pollutant concentration Radial basis neural networks Riverine load Statistic modeling Multiple linear regression |
| url_provider | http://dspace.uniten.edu.my/ |