Machine learning to improve eel passage design

The pros and cons of hydropower remain relevant and today's power companies are trying to optimise energy extraction while minimising negative impacts on the environment. In Sweden, the issue is highly topical as the environmental conditions of most of the approximately 2,300 Swedish hydropower plants will be renewed over the next 20 years. Measures to restore connectivity at hydropower plants are costly and must be designed correctly and implemented in the right place. The project therefore aims to develop new knowledge that increases the understanding of the movement patterns of silver eels based on prevailing environmental factors and thus contribute to an optimised design of passage measures for eels.

Sustainable use of natural resources involves trade-offs between different ecosystem services. For hundreds of years, humans have used waterways as sources of power, which has meant that energy and economic gains have been made at the expense of environmental values, as constructed dams are migration barriers for aquatic organisms. Today’s society is in great need of energy and as a result of the ongoing increased electrification of society, electricity consumption is increasing. At the same time, public environmental awareness is increasing and with it the demand for a transition to energy sources with limited climate impact. In Sweden, the issue is highly topical as the environmental conditions for most of the approximately 2,300 Swedish hydropower plants will be renewed over the next 20 years. Measures to restore connectivity at hydropower plants are costly and need to be properly designed and implemented in the right place. In this project, researchers will initially analyse an existing dataset containing high-resolution hydraulics and eel migration data as well as abiotic factors from a study in Ätran in 2017 (Kjaerås et al., 2023). A total of 98 silver eels were tagged with acoustic telemetry transmitters with a depth sensor and then tracked as they passed the Herting power plant in Ätran, both via a diverter (β-grid with escape opening) and via spillage into a natural fishway. The flow data has been modelled with CFD and a range of other abiotic parameters are available. All data have been checked and analysed previously, but what remains is to analyse the link between the eel movements and the abiotic parameters including hydrology and hydraulics. This analysis will follow the protocol developed for salmon smolts in Mandalselva within the above mentioned project (Silva et al. 2020). The new knowledge generated will be transferable to other sites, just like previous studies where measures were evaluated. Unlike previous similar studies, here we will be able to study with high resolution how the eels move and how route choice and behavioural response depend on e.g. bottom structure, water movement (speed, direction, turbulence etc), temperature, light etc. This is a unique dataset that is currently unparalleled, as it includes an effective measure for downstream passage (both salmon and eels) in combination with high-resolution data for both eel movements and hydrodynamics. Overall, the results will contribute to a more robust design of measures for downstream migrating eels, an area where there is currently a significant knowledge gap. In addition, the project represents a necessary first step in the process of developing a predictive model that will allow future ‘in silico’ testing, evaluation and improvement of measures before they are implemented at hydropower plants.