WP1. Understanding regional (Nordic, Arctic, and high-altitude) and global climate change and definition of hydroclimatic extreme events.
WP1 will generate hydroclimatic (HC) extreme events based on global and local database handling and climate projection scenarios, define scenario storylines for assessment, simulations, monitoring. The outcome and main results and impacts will be presented and recommendations on adaptation and mitigation strategies for sustainable water management under hydroclimatic extremes with emphasis in the Nordic and Arctic climate.
WP2. Multi-level risk assessment of the entire water and wastewater infrastructure system from inlets to recipients under HC extreme scenarios.
Both traditional and new risk assessment approaches will be developed for risk assessment and management tools for hydroclimatic extreme events on the water quality of water supply systems from inlet to recipients. Risks at all relevant spatial and temporal scales will be assessed, in the way that hydrological and ecosystem services within urban-rural regime are impacted, both directly and indirectly, by extreme events and climate change. Finally, a risk assessment and management tool for hydroclimatic extreme events will be developed and tested at the case sites.
WP3. Improving hydrological and hydraulic modelling by advanced digital technologies.
WP3 shall develop a coupled urban-rural flood simulation system, which will enable flood forecasting and early warning for keeping cities and river basins secure with flash floods, also for modelling and assessment of water pollution under extreme events. In this WP, the machine learning model will be combined with physical models such as hydrology and hydraulic modules to enhance the performance of machine learning. The hybrid model will be at multiple levels, data level, feature level or model level. At each model level, the machine learning model will merge with the physical models by using the physical model as the kernel function or transfer function to develop new types of machine learning that are specific for the hydrological and hydraulic processes. The machine learning model will be computationally efficient and with less uncertainty yielding robust results.
WP4. Design, production and installation of sensors and monitoring the characteristics of water under hydroclimate extremes and pilot testing.
UCEV will design embedded cards to collect data from the sensors and continue to work on long-term data collection by ensuring that the collected data are displayed at real-time in the Cloud. KTUN will be responsible for testing the accuracy of the data obtained from the sensors in the small pilot and operating the small pilot system and performing laboratory analyses. After the accuracy of sensors is determined, in the later stage, the field tests of the sensors will be carried out in the case studies in Norway and Sweden.
WP5. Life Cycle Assessment (LCA) of sustainable water infrastructure systems.
The main focus is on a comparative assessment of different smart digital tools with respect to their environmental performance of water infrastructure systems. Ideally, the new tools will lead to an improvement of many life cycle impact categories and thus contribute to sustainable management and safe operation of water infrastructure systems under extreme hydroclimatic events. Not only the new tools to be studied will be assessed. With a comprehensive understanding of the previous tools, LCA will quantify environmental sustainability and thus inform decision makers and stakeholders about various strengths (and weaknesses) of the newly developed tools. Since LCA is an ISO-defined and globally recognized sustainability assessment tool, this work package will add an additional and peer-recognized perspective to the project.
WP6. Case studies, demonstration and dissemination.
The above concept and methods developed in the WPs will be tested and implemented in the carefully selected case study sites in Norway and in Sweden (representing the Nordic-Arctic climate). Case Study N1 – Flood forecasting and sustainable management of urban drainage infrastructure system and water pollution control under extreme climate in Trondheim; and Case study N2 - Risk assessment of flash flooding in the Arctic region and their impacts on infrastructure systems and local communities in the Arctic in Norway.
WP7. Develop a Machine Learning (ML)-based digital decision support tools (DSTs) and draw recommendations.
All important outputs from WP1-WP6 are inputs to the DSTs to support water utilities, stakeholder and end users for application and disseminations. The main results and findings will draw recommendation to decision makers for sustainable management of urban water and wastewater infrastructure systems, making adaptation and mitigation strategies to climate change impacts.