Johanna Sörensen
Assistant Professor at Lund University
- Report this post
Can Artificial Neural Networks find leaks in pipes? We have tried to answer this question in a scientific paper in the IWA Publishing journal Water Supply. The paper is free to read and download. Enjoy!Thanks to Erik Nilsson, Didrik Nilsson, Ebba Gröndahl, David Rehn and Tommy Giertz for great collaboration.REF: Sörensen, J., Nilsson, E., Nilsson, D., Gröndahl, E., Rehn, D., Giertz, T., 2024. Evaluation of ANN model for pipe status assessment in drinking water management. Water Supply 24, 1985–1998. ABSTRACT: Non-revenue water due to pipe leakages presents a significant global challenge, impacting both the economy and environmental sustainability. The current approach to pipe management for water utilities in Sweden is mainly reactive; leaks are repaired when detected, sometimes with large costs if the leakage is extensive and critical. With this study, we want to focus on proactive pipe network management by using an Artificial Neural Network (ANN) model to estimate the probability of leakage in water pipes. The ANN model was trained on leaks that occurred over 10 years. A comparison with leaks reported after the training shows that the model succeeds in identifying groups of pipes with a higher leakage frequency. Evaluation of both new and historical leaks in four different water pipe networks in Sweden showed that a higher prediction value from the ANN model was linked to a higher occurrence of leakage. This indicates that the ANN model succeeds in identifying some of the combinations of attributes that lead to leakage. An evaluation of the input attributes in the ANN model found that the most important attributes for leakage prediction were pipe material, pipe age, adjacent problems on the pipe stretch, pipe length and pipe dimension.
23
To view or add a comment, sign in
More Relevant Posts
-
Johanna Sörensen
Assistant Professor at Lund University
- Report this post
På onsdag i Almedalen står jag värd för en diskussion om hur vi bäst rustar mot översvämningar. Klimatanpassning med blå-gröna lösningar blir en stor del av diskussionen. Kom och lyssna! Skriv gärna en kommentar nedan om du kommer till Almedalen, så kan vi sammanstråla.
12
Like CommentTo view or add a comment, sign in
-
Johanna Sörensen
Assistant Professor at Lund University
See AlsoJohanna Downs on LinkedIn: We have come a long way in 9 days!! I’m thankful for the care at the UNC…- Report this post
Today I am presenting at the ICUD conference in Delft (Netherlands). What a lovely conference, just as nice as 10 years ago in Kuching on Borneo. Well, the city, the weather and the nature are all different, but the engagement and the spirit are the same. Wish me good luck!(I will talk about barriers to sustainable stormwater management and how to overcome these. At 15.10 in Senaatzaal)
28
Like CommentTo view or add a comment, sign in
-
Johanna Sörensen
Assistant Professor at Lund University
- Report this post
Någon duktig hydraulik-själ som vill bli min kollega? Sök tjänsten som biträdande lektor på LTH!
13
Like CommentTo view or add a comment, sign in
-
Johanna Sörensen
Assistant Professor at Lund University
- Report this post
Vetenskapsradion ville att jag skulle prata om skyfallslösningar i Tokyo, bräddning i Paris och blågrönt i Sverige och samtidigt göra det förståeligt för folk som inte ens vet att spillvatten blandas med regnet i våra stadskärnor, samtidigt som de vill ha det på en vetenskaplig nivå. På cirka fem minuter. Det var en utmaning! Här är resultatet. Jag har inte vågat lyssna ännu, men hoppas jag fick sagt något klokt.
63
10 Comments
Like CommentTo view or add a comment, sign in
-
Johanna Sörensen
Assistant Professor at Lund University
- Report this post
Tips för alla i Stockholm-regionen.
4
Like CommentTo view or add a comment, sign in
-
Johanna Sörensen
Assistant Professor at Lund University
- Report this post
We finally got our paper on Decision Support Indicators (DSIs) and their role in hydrological planning published – hurray! This freely available paper is probably interesting for many who work with decision-making and hydrological indicators.Highlights•Decision Support Indicators (DSI) inform stakeholders of future hydrological hazards.•Based on local knowledge about past events, event-based DSIs are highly informative.•A novel framework for indicator development has been developed.•The framework has been tested in seven case studies on three continents.•The framework can be seen as a decision-support tool, facilitating indicator development.Thanks to all co-authors – it has been great to work together with you: Stephanie Eisner at NVE, Jonas Olsson at SMHI and The Faculty of Engineering at Lund University, Stein Beldring at NVE, Vanessa S.B. Carvalho at Universidade Federal de Itajubá, Maria Elenius at SMHI, Carlos Ruberto Fragoso Júnior at Federal University of Alagoas - UFAL, Anna Hansen at WSP i Norge and NVE, Trine Jahr Hegdahl at NVE, Benedito Cláudio da Silva at Universidade Federal de Itajubá, Michelle S Reboita at Universidade Federal de Itajubá, Daniela Rocha Teixeira Riondet-Costa at Universidade Federal de Itajubá, Nívea Pons at Universidade Federal de Itajubá and Cintia Bertacchi Uvo at Finnish Environment Institute (Syke) - Suomen ympäristökeskus (Syke) and The Faculty of Engineering at Lund UniversityLink: https://lnkd.in/dyT6EekX
33
Like CommentTo view or add a comment, sign in
-
Johanna Sörensen
Assistant Professor at Lund University
- Report this post
Mina tidigare kollegor på Krüger A/S i Köpenhamn var något trötta på läcksökningsprojekt. Alltid mitt i natt, helst när det regnar rejält. DHI verkar gilla det desto mer.
8
Like CommentTo view or add a comment, sign in
-
Johanna Sörensen
Assistant Professor at Lund University
- Report this post
Härligt att våra studenter kan bidra med idéer till de som jobbar professionellt med dagvatten och översvämningar - bra jobbat Tove och Linn!
20
1 Comment
Like CommentTo view or add a comment, sign in
- 177 Posts
View Profile
Follow