Integrated hydrological modeling using physical-based models and physical informed neural networks

Please get in touch with us using the provided contact details.

Organisation

University of Turku

Description

Integrated hydrological models are essential for sustainable water resources management, hydro-hazard assessment and water pollution risk assessment. The Nordic eco-hydrological system is complex by nature, and requires more integrated concepts and models to comprehensively understand the underlying processes of it, changes in the system, and the impact of climate and anthropogenic pressure. Current hydrological and hydraulic models show limitations to working with high spatial and temporal resolution data and multidimensional data. New generation of hydrological models, e.g., coupling physical-based models with artificial intelligence and physically informed neural networks provides potential for more integrated and accurate modeling of hydrological and hydrodynamic processes, but requires further research and development. See Gonzales-Inca et al., 2022 for more information.

Gonzales-Inca, C., Calle, M., Croghan, D., Torabi Haghighi, A., Marttila, H., Silander, J., Alho, P., 2022. Geospatial Artificial Intelligence (GeoAI) in Integrated Hydrological and Fluvial Systems Modeling: Review of Current Applications and Trends. Water 14, 2211. https://doi.org/10.3390/w14142211

PhD project description:

The PhD project aims to progress in the development of Physical-based and Physical Informed Neural Networks models applied to hydrological and fluvial studies in the Nordic environment. It will particularly focus on modeling hydrological extreme events and diffuse water pollution risk assessment. The project outputs will also contribute to the construction of Digital Twins for integrated water resources management.

Specific requirements:

We are seeking a doctoral researcher with a good theoretical and modeling background in eco-hydrology and hydraulics. The position also demands good knowledge of hydrological data science and geospatial artificial intelligence (GeoAI) and machine learning methods and Python programming. The position requires an active approach and cooperative work. The candidate should have completed a master’s degree in physical geography, environmental science, water engineering, or related fields. The candidate should also have independent work skills and good scientific writing skills.

Secondment/: 

TBA

Dept./Faculty to which the thesis belongs

Department of Geography and Geology/ Faculty of Science

Principal supervisor

Dr. Carlos Gonzales-Inca (UTU)

2nd supervisor

Adj. Prof. Elina Kasvi

3rd supervisor

Prof. Petteri Alho

Secondment host

TBA

More information:

https://sites.utu.fi/tohtorikoulutuspilotti/diwa-digital-waters-flagship/