Artificial intelligence at the service of asset forecasting for drinking water networks. The case of PRISM software

L’intelligence artificielle au service de la prospective patrimoniale des réseaux d’eau potable. Le cas du logiciel PRISM

Amir Nafi () and François Destanau
Additional contact information
Amir Nafi: BETA - Bureau d'Économie Théorique et Appliquée - AgroParisTech - UNISTRA - Université de Strasbourg - Université de Haute-Alsace (UHA) - Université de Haute-Alsace (UHA) Mulhouse - Colmar - UL - Université de Lorraine - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement
François Destanau: SAGE - Sociétés, acteurs, gouvernement en Europe - ENGEES - École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg - UNISTRA - Université de Strasbourg - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement

Post-Print from HAL

Abstract: Asset foresight consists in the search for asset policies, i.e. management strategies for drinking water networks, that reflect a mix of maintenance and investment actions offering the best trade-off between performance and costs. The aim of this article is to improve asset management practices for drinking water networks, in a context of low data availability, using artificial intelligence and more specifically Prism, a software solution supported by public grants. The performance indicator studied in this article is network efficiency i.e. the proportion of water produced that is distributed, and then therefore not lost "in transit". First, an innovative methodology will be presented to better characterize the origin of water losses. This information will then be fed into the Prism software, which will compare the utilities current practice with a status quo solution, and then with effective asset management policies, which it will estimate using a "costbenefit" approach. The results of this article are based on empirical studies carried out in four French local authorities. They provide valuable information for improving the estimation of network water losses. The proposed methodology, carried out by Prism software, also improves the search for alternative asset management policies and provides an innovative decision-making aid for drinking water network managers.

Keywords: Foresight; Decision support; Artificial intelligence; Assets; Drinking water network; Water loss; Prospective; Aide à la décision; Intelligence artificielle; Patrimoine; Réseau d'eau potable; Perte d’eau (search for similar items in EconPapers)
Date: 2024
New Economics Papers: this item is included in nep-agr
Note: View the original document on HAL open archive server: https://hal.science/hal-04649022v1
References: Add references at CitEc
Citations:

Published in TSM. Techniques Sciences Méthodes – Génie urbain, génie rural, 2024, 4, pp.63-75

Downloads: (external link)
https://hal.science/hal-04649022v1/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04649022

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().