Machine-learning methods for stream water temperature prediction
-
Published:2021-05-31
Issue:5
Volume:25
Page:2951-2977
-
ISSN:1607-7938
-
Container-title:Hydrology and Earth System Sciences
-
language:en
-
Short-container-title:Hydrol. Earth Syst. Sci.
Author:
Feigl MoritzORCID, Lebiedzinski KatharinaORCID, Herrnegger MathewORCID, Schulz KarstenORCID
Abstract
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 effective integrated water management and the development of adaptation strategies to future global changes (e.g. climate change). This study tests the performance of six different machine-learning models: step-wise linear regression, random forest, eXtreme Gradient Boosting (XGBoost), feed-forward neural networks (FNNs), and two types of recurrent neural networks (RNNs). All models are applied using different data inputs for daily water temperature prediction in 10 Austrian catchments ranging from 200 to 96 000 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 six 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 mainly perform 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 hyperparameter optimization. Especially the FNN model results showed an extremely large RMSE standard deviation of 1.60 ∘C due to the chosen hyperparameters. 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 in the open-source R package wateRtemp to provide easy access to these modelling approaches and facilitate further research.
Funder
Austrian Science Fund Österreichischen Akademie der Wissenschaften
Publisher
Copernicus GmbH
Subject
General Earth and Planetary Sciences,General Engineering,General Environmental Science
Reference139 articles.
1. Abba, S. I., Hadi, S. J., and Abdullahi, J.: River water modelling prediction using multi-linear regression, artificial neural network, and adaptive neuro-fuzzy inference system techniques, in: Procedia Computer Science, Elsevier B.V., Budapest, Hungary, 75–82, https://doi.org/10.1016/j.procs.2017.11.212, 2017. a, b 2. Ahmadi-Nedushan, B., St-Hilaire, A., Ouarda, T. B. M. J., Bilodeau, L.,
Robichaud, É., Thiémonge, N., and Bobée, B.: Predicting
river water temperatures using stochastic models: case study of the Moisie
River (Québec, Canada), Hydrol. Process., 21, 21–34,
https://doi.org/10.1002/hyp.6353, 2007. a 3. Akaike, H.: Information theory as an extension of the likelihood principle., in: Second Akademiai International Symposium on Information Theory, edited by: Petrov, B. N. and Csaki, F., Kiado, Budapest, 267–281, 1973. a 4. Allaire, J. J. and Tang, Y.: tensorflow: R Interface to “TensorFlow”, available at: https://github.com/rstudio/tensorflow (last access: 13 Jauary 2021), 2020. a 5. Álvarez, D. and Nicieza, A. G.: Compensatory response “defends” energy levels but not growth trajectories in brown trout, Salmo trutta L.,
P. Roy. Soc. B-Biol. Sci., 272, 601–607,
https://doi.org/10.1098/rspb.2004.2991, 2005. a
Cited by
73 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|