Preprints
https://doi.org/10.5194/hess-2020-670
https://doi.org/10.5194/hess-2020-670

  14 Jan 2021

14 Jan 2021

Review status: this preprint is currently under review for the journal HESS.

Machine learning methods for stream water temperature prediction

Moritz Feigl1,, Katharina Lebiedzinski1,, Mathew Herrnegger1, and Karsten Schulz1 Moritz Feigl et al.
  • 1Institute for Hydrology and Water Management, University of Natural Resources and Life Sciences, Vienna, Austria
  • These authors contributed equally to this work.

Abstract. Water temperature in rivers is a crucial environmental factor with the ability to alter hydro-ecological as well as socio-economic conditions within a catchment. The development of modelling concepts for predicting river water temperature is and will be essential for an effective integrated water management and the development of adaptation strategies to future global changes (e.g. climate change). This study tests the performance of 6 different machine learning models: step-wise linear regression, Random forest, eXtreme Gradient Boosting (XGBoost), Feedforward neural networks (FNN), and two types of Recurrent neural networks (RNN). All models are applied using different data inputs for daily water temperature prediction in 10 Austrian catchments ranging from 200 km2 to 96000 km2 and exhibiting a wide range of physiographic characteristics. The evaluated input data sets include combinations of daily means of air temperature, runoff, precipitation and global radiation. Bayesian optimization is applied to optimize the hyperparameters of all applied machine learning models. To make the results comparable to previous studies, two widely used benchmark models are applied additionally: linear regression and air2stream.

With a mean root mean squared error (RMSE) of 0.55 °C the tested models could significantly improve water temperature prediction compared to linear regression (1.55 °C) and air2stream (0.98 °C). In general, the results show a very similar performance of the tested machine learning models, with a median RMSE difference of 0.08 °C between the models. From the 6 tested machine learning models both FNNs and XGBoost performed best in 4 of the 10 catchments. RNNs are the best performing models in the largest catchment, indicating that RNNs are mainly performing well when processes with long-term dependencies are important. Furthermore, a wide range of performance was observed for different hyperparameter sets for the tested models, showing the importance of hyperprameter optimization. Especially the FNN model results showed an extremely large RMSE standard deviation of 1.60 °C due to the chosen hyperparamerters.

This study evaluates different sets of input variables, machine learning models and training characteristics for daily stream water temperature prediction, acting as a basis for future development of regional multi-catchment water temperature prediction models. All preprocessing steps and models are implemented into the open source R package wateRtemp, to provide easy access to these modelling approaches and facilitate further research.

Moritz Feigl et al.

Status: open (until 11 Mar 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2020-670', Salim Heddam, 30 Jan 2021 reply
    • AC1: 'Authors answers to RC1', Moritz Feigl, 02 Mar 2021 reply
  • RC2: 'Comment on hess-2020-670', Adrien Michel, 15 Feb 2021 reply
    • AC2: 'Authors answers to RC2', Moritz Feigl, 04 Mar 2021 reply

Moritz Feigl et al.

Model code and software

MoritzFeigl/wateRtemp: paper code Moritz Feigl https://doi.org/10.5281/zenodo.4438575

MoritzFeigl/ML_methods_for_stream_water_temperature_prediction: paper code Moritz Feigl https://doi.org/10.5281/zenodo.4438582

Moritz Feigl et al.

Viewed

Total article views: 521 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
388 124 9 521 4 3
  • HTML: 388
  • PDF: 124
  • XML: 9
  • Total: 521
  • BibTeX: 4
  • EndNote: 3
Views and downloads (calculated since 14 Jan 2021)
Cumulative views and downloads (calculated since 14 Jan 2021)

Viewed (geographical distribution)

Total article views: 405 (including HTML, PDF, and XML) Thereof 401 with geography defined and 4 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 05 Mar 2021
Download
Short summary
In this study we developed machine learning approaches for daily river water temperature prediction, using different data preprocessing methods, 6 model types, a range of different data inputs and 10 study catchments. By comparing to current state of the art models, we could show a significant improvement of prediction performance of the tested approaches. Furthermore, we could gain insight into the relationships between model types, input data and predicted stream water temperature.