AI-refined thermo-hydraulic model for the improvement of the efficiency and quality of water supply (OptiHyd)
Third party funded individual grant
Acronym: OptiHyd
Start date : 01.11.2023
End date : 31.10.2026
Project details
Short description
In recent decades, the water cycle has been greatly challenged by climate change and the associated weather fluctuations. For example, changes in weather lead to previously unknown behaviors in water supply, increase the severity of seasonal and regional water scarcity, and reduce the safety and quality of drinking water supply. Since 2018, the effects of extreme events such as droughts and heavy rainfall have also been observed in Bavaria. The increasing frequency and severity of extreme weather events have particularly significant impacts on the daily operations of Bavarian water supply companies, as well as on supply security, quality, and drinking water hygiene for citizens. Therefore, the need for deeper knowledge about existing water supply structures is growing with the current challenge posed by the significantly altered environmental influences. Digitalization in water management and the need to economically and socially cope with the challenges of climate change are becoming increasingly important.
To mitigate the impacts of climate change, a resilient water supply must be developed and implemented on a large scale. According to the International Water Association (IWA), 'Resilience in water use is more than the implementation of a single technical solution.' It is an approach that is part of a coherent and holistic strategy to ensure sustainable management of water resources and safe water supply. Therefore, close collaboration between water suppliers, civil engineers, sensor manufacturers, and data scientists is key to developing and implementing novel and applicable water use strategies. The collaboration should lead to benefits for end-users and contribute to the regional, national, and global mission of combating climate change.
The essence of this project is to develop, demonstrate, and evaluate a water supply strategy based on a comprehensive holistic model of a water distribution network (WDN), specifically the Schrobenhausen water network. At its core is the research and development of a hybrid thermo-hydraulic model of the water network, where water and soil temperature are additionally modeled. The applicability and practicality of the model will be demonstrated through various applications, including monitoring and predicting water quality, detecting and locating leaks, and predictive failure detection. Heterogeneous data sources used in the daily operation of WDNs, which include facility management data, data from smart meters, operational and control data (SCADA), and additional temperature measurements (i.e., water and soil temperatures), will be collected and used.
Scientific Abstract
The United Nations' goals for sustainable development have made improving quality of life and access to clean drinking water a political priority. However, in recent decades, the water cycle in Bavaria has also been significantly affected by climate change. Two important aspects of daily drinking water supply and distribution are the assurance of water quality and the increase in usage efficiency. To enhance the resilience and capacity of the water supply in general, numerical simulation, data integration, and artificial intelligence (AI) are necessary. In this project, we aim to develop an AI-refined temperature-hydraulic model using heterogeneous data sources from a Bavarian water supply network. Hybrid AI methods are employed to model the complex relationship between water and soil temperature. The resulting model will serve as the basis for various real applications such as leak detection, anomaly recognition, and monitoring of drinking water quality, with the overarching goal of increasing the efficiency and quality of the water supply while simultaneously contributing to the containment of the impact of climate change on drinking water supply
