Mapping riverine heatwave trends across Europe using reconstructed river temperature time-series

Riverine heatwaves, that is, periods of anomalously high water temperature, have become more frequent and intense over the past decades across Europe. To improve our understanding of their spatial distribution and to analyze potential shifts in the causes of such events, we require long time-series of river temperature over a large spatial domain. However, records of measurement stations are often of limited length or, in some regions of Europe, not available at all. 

To fill these temporal and spatial data gaps, we train a deep learning Long Short-Term Memory (LSTM) model to reconstruct historic time-series (1985-2020) of daily river temperature from meteorological records and catchment characteristics. To train and evaluate the model for the simulation of riverine heatwaves, we use the new TempER (Temperature of European Rivers) dataset that contains over 4000 temperature measurement stations in Europe. TempER covers 26 European countries and contains daily water temperature records of 1 to 72 years length. 48% of the stations additionally provide streamflow observations that we integrate into the model to enhance the fidelity of the reconstructed data. In regions not covered by TempER we use streamflow records from EStreams^[1] to guide the temperature simulation. 

We analyze the reconstructed river temperatures with respect to trends in riverine heatwave characteristics (frequency, duration, intensity) and their spatial distribution across Europe. With our findings we intend to improve the understanding of the hydro-meteorological processes that drive riverine heatwaves and provide a continuous dataset allowing further analysis of river temperatures in Europe. 

 

[1] do Nascimento, T.V.M., Rudlang, J., Höge, M. et al. EStreams: An integrated dataset and catalogue of streamflow, hydro-climatic and landscape variables for Europe. Sci Data 11, 879 (2024).