ANN-based prediction for a sustainable decision model on a combined sewer overflow screen: using a conceptual approach.
Gespeichert in:
| Titel: | ANN-based prediction for a sustainable decision model on a combined sewer overflow screen: using a conceptual approach. |
|---|---|
| Autoren: | Tse H; AtkinsRealis UK Limited, Woodcote, Ashley Road, Epsom, UK E-mail: jeff.tse@atkinsrealis.com. |
| Quelle: | Water science and technology : a journal of the International Association on Water Pollution Research [Water Sci Technol] 2025 Nov; Vol. 92 (9), pp. 1241-1262. Date of Electronic Publication: 2025 Nov 06. |
| Publikationsart: | Journal Article |
| Sprache: | English |
| Info zur Zeitschrift: | Publisher: IWA Publishing Country of Publication: England NLM ID: 9879497 Publication Model: Print-Electronic Cited Medium: Print ISSN: 0273-1223 (Print) Linking ISSN: 02731223 NLM ISO Abbreviation: Water Sci Technol Subsets: MEDLINE |
| Imprint Name(s): | Publication: <1998->: London : IWA Publishing Original Publication: Oxford ; New York : Pergamon Press, 1981- |
| MeSH-Schlagworte: | Neural Networks, Computer* , Sewage* , Waste Disposal, Fluid*/methods , Waste Disposal, Fluid*/instrumentation , Drainage, Sanitary*, Models, Theoretical |
| Abstract: | Competing Interests: The authors declare there is no conflict. Combined sewer overflow (CSO) screens are critical components of sewer and drainage networks, separating sewer solids from overflow spills before they reach receiving waters. Selecting suitable and sustainable CSO screening devices, however, remains a complex task. This process has traditionally depended on conventional design calculations, technical guidance from screen manufacturers and precedents from past projects. Inappropriate screen selections have led to adverse effects on water quality and public health, due to insufficient screening capacity, the unpredictable behaviour of sewer solids of varying densities, low trapping efficiency, frequent screen blinding or high equipment failure rates, particularly at unmanned or remote sites. This paper presents a design methodology for screen selection and formulates an input-output relationship model. Using 50 screen project data, a framework has been proposed to construct a predictive model that integrates sustainability criteria, lessons learnt from historical applications and artificial neural network (ANN) techniques. A Levenberg-Marquardt-based ANN was developed and trained to identify optimal selection between 2 categories of screen solutions, encompassing 12 screen types - 3 within non-powered self-cleaning and 9 within the powered screen category. The framework aims to provide an initial proof-of-concept evidence with a supplementary decision-support tool, enabling design engineers to make intelligent, resilient and sustainable choices in screen application. (© 2025 The Author This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (CC BY-NC 4.0), which permits copying, adaptation and redistribution for non-commercial purposes, provided the original work is properly cited (http://creativecommons.org/licenses/by-nc/4.0/).) |
| References: | Ali S., Riaz S., Liu X. & Wang G. (2023) A Levenberg–Marquardt based neural network for short-term load forecasting, Computers, Materials & Continua, 75 (1), 1783–1800. doi: 10.32604/cmc.2023.035736. Andoh R. Y. G. & Saul A. J. (1999) 'The screen efficiency of a novel self-cleaning CSO', 8th International Conference on Urban Storm Drainage, Sydney, Australia. Aziz M., Imteaz M., Choudhury T. & Philips D. (2011) 'Artificial neural networks for the prediction of trapping efficiency of a new sewer overflow screening device', 19th International Congress on Modeling and Simulation, Perth, Australia. Aziz M., Imteaz M., Huda N. & Naser J. (2013) Understanding functional efficiency of a sewer overflow screening device using combined CFD and analytical modeling, 20th International Congress on Modeling and Simulation, Adelaide, Australia. Brigato L. & Locchi L. (2020) A close look at deep learning with small data, 25th International Conference on Pattern Recognition, Milan, Italy. Bruen M. & Yang J. (2006) Combined hydraulic and black-box models for flood forecasting in urban drainage systems, Journal of Hydrologic Engineering, 11 (6), 589–596. doi: 10.1061/(ASCE)1084-0699(2006)11:6(589). Chan H. S., Horoshenkov K. V., Tareq Bin A. M. & Tait S. J. (2021) An acoustic sensor for combined sewer overflow screen condition monitoring in a drainage infrastructure, Sensors, 21, 404. doi: 10.3390/s21020404. (PMID: 33430049) Chau K. (2006) Particle swarm optimization training algorithm for ANNs in stage prediction of Shing Mun River, Journal of Hydrology, 329 (3–4), 363–367. doi: 10.1016/j.jhydrol.2006.02.025. CIWEM Urban Drainage Group (2006) The Design of CSO Chambers to Incorporate Screens. London, UK: The Chartered Institution of Water & Environment. Available at: https://www.ciwem.org/assets/pdf/Special%20Interest%20Groups/Urban%20Drainage%20Group/The-Design-of-CSO-Chambers-to-Incorporate-Screens.pdf. Galiastatou P., Nikoletos I., Malamtaris D., Zafirakou A., Ganoulis P. J., Gkatzioura A., Kapouniari M. & Katsoulea A. (2025) Assessing climate change impacts on combined sewer overflows: a modelling perspective, Climate, 13 (5), 82. doi: 10.3390/cli13050082. Garzon A., Kapelan Z., Langeveld J. & Taromina R. (2022) Machine learning-based surrogate modeling for urban water networks: review and future research directions, Water Resources Research, 58 (5), e2021WR031808. doi: 10.1002/eesoar.10509791.1. Gasperi J., Dris R., Bonin T., Rocher V. & Tassin B. (2014) Assessment of floating plastic debris in surface water along the Seine River, Environmental Pollution, 195, 163–166. doi: 10.1016/j.envpol.2014.09.001. (PMID: 25240189) Gonzalesz-Ubiema S., Jorge-Mardomingo I., Cruz M., Valverde I. & Casemeiro M. (2013) Sewage sludge application in Mediterranean agricultural soils: effects of dose on soil carbon cycle, International Journal of Environmental and Research, 7 (4), 945–956. Kaya Uyamk G. & Guler N. (2013) A study on multiple linear regression analysis, Procedia – Social and Behavioral Sciences, 106, 234–240. doi: 10.1016/j.sbspro.2013.12.027. Kustova L., Hudenko J. & Lace N. (2024) A systematic review of sustainability criteria in infrastructure development, Sustainability, 16 (11), 4564. doi: 10.3390/su16114564. Li M., Shi X., Lu Z. & Kapelan Z. (2024a) Predicting the urban stormwater drainage system state using the graph-wavenet, Sustainable Cities and Society, 115, 105877. doi: 10.1016/j.scs.2024.105877. Li Z., Liu H., Zhang C. & Fu G. (2024b) Real-time water quality prediction in water distribution networks using graph neural networks with sparse monitoring data, Water Research, 250, 121018. doi: 10.1016/j.watres.2023.121018. Luque A., De Las Heras A., Jesus Avila Gutierrez M. & Zamora Polo F. (2020) ADAPTS: an intelligent sustainable conceptual framework for engineering projects, Sensors, 20 (6), 1553. doi: 10.3390/s20061553. (PMID: 32168788) Ma S., Zayed T., Xing J. & Shao Y. (2023) A start-of-the-art review for prediction of overflow in urban sewer systems, Journal of Cleaner Production, 434 (4), 139923. doi: 10.1016/j.jclepro.2023.139923. Moreno-Rodensas A. M., Duinmeijer A. & Clemens F. H. L. R. (2021) Deep-learning based monitoring of FOG layer dynamics in wastewater pumping stations, Water Research, 202, 117482. doi: 10.1016/j.watres.2021.117482. (PMID: 34365321) Pei S., Hoang L., Fu G. & Butler D. (2024) Real-time control of urban drainage systems using neuro-evolution, Journal of Environmental Management, 360, 121133. doi: 10.1016/j.jenvman.2024.121133. (PMID: 38763119) Philips D. & Simon M. (2007) 'A sewage solids screening system for CSO chambers’, 6th International Conference on Sustainable Techniques and Strategies for Urban Water Management, Lyon, France. Rodriguez M., Fu G., Butler D., Yuan Z. & Cook L. (2023) Global resilience analysis of combined sewer systems under continuous hydrologic simulation, Journal of Environmental Management, 344, 118607. doi: 10.1016/j.jenvman,2023.118607. (PMID: 37453297) Rosin T., Romano M., Keedwell E. & Kapelan Z. (2021) A committee evolutionary neural network for the prediction of combined sewer overflows, Water Resources Management, 35 (4), 1273–1289. doi: 10.1007/s11269-021-02780-z. Saddiqi M. M., Zhao W., Cotterill S. & Kaan Dereli R. (2023) Smart management of combined sewer overflows: from an ancient technology to artificial intelligence, WIREs Water, 10 (3), 1635. doi: 10.1002/aws.1635. Saul A. J. (2002) 'CSO: state of the art review', 9th International Conference on Urban Drainage. Singh P. K. & Sarkar P. (2023) An artificial neural network tool to support the decision making of designers for environmentally conscious product development, Expert Systems with Applications, 212, 118679. doi: 10.1016/j.eswa.2022.118679. Tse H. (2024) Challenges for pumping station design in water industries: an overview of impacts from climate change and energy crisis, Water Research, 253, 121250. doi: 10.1016/j.watres.2024.121250. (PMID: 38341970) USEPA (1999) Combined Sewer Overflow Technology Fact Sheet – Floatables Control. Washington, DC, USA: US EPA. 832-F99-008. USEPA (2008) A Screening Assessment of the Potential Impacts of Climate Change on Combined Sewer Overflow Mitigation in the Great Lakes and New England Regions, EPA/600/R-07/033F. Washington, DC, USA: US Environmental Protection Agency. Weyand M. (2002) Real-time control in combined sewer systems in Germany – some case studies, Urban Water, 4 (4), 347–354. doi: 10.1016/S1462-0758(02)00031-6. Zafeirakou A., Galiatsatou P., Nikoletos I., Gkatzioura A., Kapouniari M., Katoulea A., Malamataris D. & Kavouras I. (2024) Capacity assessment of a combined sewer network under different weather conditions: using nature-based solutions to increase resilience, Water, 16 (19), 2862. doi: 10.3390/w16192862. Zhang C., Li H., Chen M., Shen D. & Niu Y. (2023) Data-driven surrogate modeling: introducing spatial lag to consider spatial autocorrelation of flooding within urban drainage systems, Environmental Modelling & Software, 161, 105623. doi: 10.1016/j.envsoft.2023.105623. |
| Contributed Indexing: | Keywords: combined sewer overflow; neural network; screen; sustainability criteria |
| Substance Nomenclature: | 0 (Sewage) |
| Entry Date(s): | Date Created: 20251114 Date Completed: 20251114 Latest Revision: 20251114 |
| Update Code: | 20251114 |
| DOI: | 10.2166/wst.2025.159 |
| PMID: | 41236062 |
| Datenbank: | MEDLINE |
Nájsť tento článok vo Web of Science | Abstract: | Competing Interests: The authors declare there is no conflict.<br />Combined sewer overflow (CSO) screens are critical components of sewer and drainage networks, separating sewer solids from overflow spills before they reach receiving waters. Selecting suitable and sustainable CSO screening devices, however, remains a complex task. This process has traditionally depended on conventional design calculations, technical guidance from screen manufacturers and precedents from past projects. Inappropriate screen selections have led to adverse effects on water quality and public health, due to insufficient screening capacity, the unpredictable behaviour of sewer solids of varying densities, low trapping efficiency, frequent screen blinding or high equipment failure rates, particularly at unmanned or remote sites. This paper presents a design methodology for screen selection and formulates an input-output relationship model. Using 50 screen project data, a framework has been proposed to construct a predictive model that integrates sustainability criteria, lessons learnt from historical applications and artificial neural network (ANN) techniques. A Levenberg-Marquardt-based ANN was developed and trained to identify optimal selection between 2 categories of screen solutions, encompassing 12 screen types - 3 within non-powered self-cleaning and 9 within the powered screen category. The framework aims to provide an initial proof-of-concept evidence with a supplementary decision-support tool, enabling design engineers to make intelligent, resilient and sustainable choices in screen application.<br /> (© 2025 The Author This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (CC BY-NC 4.0), which permits copying, adaptation and redistribution for non-commercial purposes, provided the original work is properly cited (http://creativecommons.org/licenses/by-nc/4.0/).) |
|---|---|
| ISSN: | 0273-1223 |
| DOI: | 10.2166/wst.2025.159 |