Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Sediment Level Prediction of a Combined Sewer System Using Spatial Features

  • Ribalta Gené, Marc
  • Mateu Piñol, Carles
  • Béjar Torres, Ramón
  • Rubión Soler, Edgar
  • Echeverria, Lluís
  • Varela Alegre, Francisco Javier
  • Corominas, Lluís
The prediction of sediment levels in combined sewer system (CSS) would result in enormous savings in resources for their maintenance as a reduced number of inspections would be needed. In this paper, we benchmark different machine learning (ML) methodologies to improve the maintenance schedules of the sewerage and reduce the number of cleanings using historical sediment level and inspection data of the combined sewer system in the city of Barcelona. Two ML methodologies involve the use of spatial features for sediment prediction at critical sections of the sewer, where the cost of maintenance is high because of the dangerous access; one uses a regression model to predict the sediment level of a section, and the other one a binary classification model to identify whether or not a section needs cleaning. The last ML methodology is a short-term forecast of the possible sediment level in future days to improve the ability of operators to react and solve an imminent sediment level increase. Our study concludes with three different models. The spatial and short-term regression methodologies accomplished the best results with Artificial Neural Networks (ANN) with 0.76 and 0.61 R2 scores, respectively. The classification methodology resulted in a Gradient Boosting (GB) model with an accuracy score of 0.88 and an area under the curve (AUC) of 0.909., The work described in this paper has been conducted within the project SCOREwater. This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement no 820751. R. Béjar also acknowledges funding from project PID2019-111544GB-C22 from the Spanish Government. C. Mateu also acknowledges funding from project RTI2018-093849-B-C31 from the Spanish Government. Lluís Corominas acknowledges the Ministry of Economy and competitiveness for the Ramon and Cajal grant and the corresponding I3 consolidation (RYC-2013-465 14595). ICRA researchers thank funding from the CERCA program and from the Generalitat de Catalunya through the Consolidated Research Group 2017 SGR 1318. Marc Ribalta also acknowledges funding from AGAUR DI-2019-066.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Machine learning solutions in sewer systems: a bibliometric analysis

  • Ribalta Gené, Marc
  • Béjar Torres, Ramón
  • Mateu Piñol, Carles
  • Rubión Soler, Edgar
The use of machine learning solutions has been rising recently, and the water domain is reaping several benefits from its application. However, there is still room in the literature regarding machine learning applied to sewer systems. In this article, we study applied solutions to the predictive problem of four factors in the sewer: pipe defects, sedimentation, and failure and blockage events. Even with the number of publications available to solve each problem, there is still a need for improvement. This article aims to identify existing literature gaps through a bibliometric analysis based on data extracted from Scopus and Web of Science. Results show an increasing trend in published papers studying the domain and identify different knowledge gaps within the literature related to the correct use of data, the need for models capable of generalization, and the identification of novel techniques to be studied in the future., The work described in this paper has been conducted within the project SCOREwater. This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement no 820751. Ramón Béjar acknowledges funding from the Spanish Ministry of Science and Innovation, under project PID2019-111544GB-C22. Marc Ribalta also acknowledges funding from Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR) DI-2019-066
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Sewer sediment deposition prediction using a two-stage machine learning solution

  • Ribalta Gené, Marc
  • Béjar Torres, Ramón
  • Mateu Piñol, Carles
  • Corominas, Lluís
  • Esbrí, Oscar
Sediment accumulation in the sewer is a source of cascading problems if left unattended and untreated, causing pipe failures, blockages, flooding, or odour problems. Good maintenance scheduling reduces dangerous incidents, but it also has financial and human costs. In this paper, we propose a predictive model to support the management of maintenance routines and reduce cost expenditure. The solution is based on an architecture composed of an autoencoder and a feedforward neural network that classifies the future sediment deposition. The autoencoder serves as a feature reduction component that receives the physical properties of a sewer section and reduces them into a smaller number of variables, which compress the most important information, reducing data uncertainty. Afterwards, the feedforward neural network receives this compressed information together with rain and maintenance data, using all of them to classify the sediment deposition in four thresholds: more than 5, 10, 15, and 20% sediment deposition. We use the architecture to train four different classification models, with the best score from the 5% threshold, being 82% accuracy, 70% precision, 76% specificity, and 88% sensitivity. By combining the classifications obtained with the four models, the solution delivers a final indicator that categorizes the deposited sediment into clearly defined ranges., The work described in this paper has been conducted within the project SCOREwater. This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement no 820751. Marc Ribalta acknowledges funding from AGAUR DI-2019-066.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Differences in drug use across three neighbourhoods with varying socioeconomic levels: A wastewater-based surveillance study

  • Corominas, Lluís
  • Bonansea, Rocío Inés
  • González-Mariño, Iria
  • Zammit, Ian
  • Badia, Sergi
  • Rodríguez-Mozaz, Sara
  • Bijlsma, Lubertus
  • Pernas-Fraguela, Carlos
  • Rodil, Rosario
  • Montes, Rosa
  • Estévez-Danta, Andrea
  • Quintana, José Benito
  • Sierra, Marta García
  • Domene, Elena
  • Satorras, Mar
  • López de Alda, Miren
This study measured 39 biomarkers of licit (e.g., alcohol, nicotine, benzodiazepines, antidepressants) and illicit drug consumption (e.g., cocaine, amphetamine, cannabis, new psychoactive substances) in wastewater from three neighbourhoods (NGBs) in Barcelona, each representing different socioeconomic and lifestyle profiles. Four weeklong sampling campaigns were conducted between March 2021 and March 2022. The results revealed significant differences in drug use across neighbourhoods that are not apparent in city-level analyses. These differences were particularly notable for illicit drugs—such as higher morphine and cannabis loads in socioeconomically disadvantaged areas—as well as for specific benzodiazepines and antidepressants, which varied in prevalence between neighbourhoods. Alcohol and nicotine patterns were more strongly associated with the local density of bars and restaurants than with socioeconomic status. A clear weekend peak was observed for substances like alcohol. Temporal analysis over the study period showed increased consumption of certain drugs at the end of 2021, likely linked to the reopening of nightlife venues and elevated anxiety related to the COVID-19 pandemic. This study highlights the value of applying wastewater-based epidemiology (WBE) at the intra-city level. By moving beyond aggregated citywide data, intra-urban WBE can reveal spatial and temporal variations in drug use that may otherwise go unnoticed. This approach also enables the identification of communities or socioeconomic groups at higher risk of substance use or mental health challenges, offering critical insights for public health authorities to develop targeted interventions and preventive strategies., This research was funded by Delegación del Gobierno para el Plan Nacional Sobre Drogas (2020I009), Instituto de Salud Carlos III-Next Generation EU/ERDF (RD21/0009/0012, RD24/0003/0001 & RD24/0003/0020 – RIAPAd Network). L. Bijlsma acknowledges grant RYC2020–028936-I funded by MCIN/AEI/10.13039/501100011033 and by “ESF Investing in your future”. We acknowledge: the SCOREwater project, which received funding from the European Union's Horizon 2020 Research and Innovation Programme under grant agreement no 820751; BCASA, s::can Iberia Sistemas de Medición S.L., Institut Metròpoli and EURECAT for their efforts in setting up and maintaining the SCOREwater stations; the Generalitat de Catalunya through the Consolidated Research Group grants ICRA-Tech 2021-SGR-01283 and 2021 SGR 00753, SA-2021–443, SA-2022–430, and the funding from the CERCA program; the Spanish Agencia Estatal de Investigación, MCIN/AEI/10.13039/501100011033, through grants RED2022–134363-T, PID2022–139446OB-C21, PID2022–139446OB-C22, and PTA2019–017397-I., Peer reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Machine learning solutions in sewer systems: a bibliometric analysis

  • Ribalta Gené, Marc
  • Béjar Torres, Ramón
  • Mateu Piñol, Carles
  • Rubión Soler, Edgar
The use of machine learning solutions has been rising recently, and the water domain is reaping several benefits from its application. However, there is still room in the literature regarding machine learning applied to sewer systems. In this article, we study applied solutions to the predictive problem of four factors in the sewer: pipe defects, sedimentation, and failure and blockage events. Even with the number of publications available to solve each problem, there is still a need for improvement. This article aims to identify existing literature gaps through a bibliometric analysis based on data extracted from Scopus and Web of Science. Results show an increasing trend in published papers studying the domain and identify different knowledge gaps within the literature related to the correct use of data, the need for models capable of generalization, and the identification of novel techniques to be studied in the future., The work described in this paper has been conducted within the project SCOREwater. This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement no 820751. Ramón Béjar acknowledges funding from the Spanish Ministry of Science and Innovation, under project PID2019-111544GB-C22. Marc Ribalta also acknowledges funding from Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR) DI-2019-066
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Sediment Level Prediction of a Combined Sewer System Using Spatial Features

  • Ribalta Gené, Marc
  • Mateu Piñol, Carles
  • Béjar Torres, Ramón
  • Rubión Soler, Edgar
  • Echeverria, Lluís
  • Varela Alegre, Francisco Javier
  • Corominas, Lluís
The prediction of sediment levels in combined sewer system (CSS) would result in enormous savings in resources for their maintenance as a reduced number of inspections would be needed. In this paper, we benchmark different machine learning (ML) methodologies to improve the maintenance schedules of the sewerage and reduce the number of cleanings using historical sediment level and inspection data of the combined sewer system in the city of Barcelona. Two ML methodologies involve the use of spatial features for sediment prediction at critical sections of the sewer, where the cost of maintenance is high because of the dangerous access; one uses a regression model to predict the sediment level of a section, and the other one a binary classification model to identify whether or not a section needs cleaning. The last ML methodology is a short-term forecast of the possible sediment level in future days to improve the ability of operators to react and solve an imminent sediment level increase. Our study concludes with three different models. The spatial and short-term regression methodologies accomplished the best results with Artificial Neural Networks (ANN) with 0.76 and 0.61 R2 scores, respectively. The classification methodology resulted in a Gradient Boosting (GB) model with an accuracy score of 0.88 and an area under the curve (AUC) of 0.909., The work described in this paper has been conducted within the project SCOREwater. This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement no 820751. R. Béjar also acknowledges funding from project PID2019-111544GB-C22 from the Spanish Government. C. Mateu also acknowledges funding from project RTI2018-093849-B-C31 from the Spanish Government. Lluís Corominas acknowledges the Ministry of Economy and competitiveness for the Ramon and Cajal grant and the corresponding I3 consolidation (RYC-2013-465 14595). ICRA researchers thank funding from the CERCA program and from the Generalitat de Catalunya through the Consolidated Research Group 2017 SGR 1318. Marc Ribalta also acknowledges funding from AGAUR DI-2019-066.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Sewer sediment deposition prediction using a two-stage machine learning solution

  • Ribalta Gené, Marc
  • Béjar Torres, Ramón
  • Mateu Piñol, Carles
  • Corominas, Lluís
  • Esbrí, Oscar
Sediment accumulation in the sewer is a source of cascading problems if left unattended and untreated, causing pipe failures, blockages, flooding, or odour problems. Good maintenance scheduling reduces dangerous incidents, but it also has financial and human costs. In this paper, we propose a predictive model to support the management of maintenance routines and reduce cost expenditure. The solution is based on an architecture composed of an autoencoder and a feedforward neural network that classifies the future sediment deposition. The autoencoder serves as a feature reduction component that receives the physical properties of a sewer section and reduces them into a smaller number of variables, which compress the most important information, reducing data uncertainty. Afterwards, the feedforward neural network receives this compressed information together with rain and maintenance data, using all of them to classify the sediment deposition in four thresholds: more than 5, 10, 15, and 20% sediment deposition. We use the architecture to train four different classification models, with the best score from the 5% threshold, being 82% accuracy, 70% precision, 76% specificity, and 88% sensitivity. By combining the classifications obtained with the four models, the solution delivers a final indicator that categorizes the deposited sediment into clearly defined ranges., The work described in this paper has been conducted within the project SCOREwater. This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement no 820751. Marc Ribalta acknowledges funding from AGAUR DI-2019-066.