Machine-learning methods for stream water temperature prediction

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.

Can machine learning accelerate process understanding and decision‐relevant predictions of river water quality?

“…Stream temperature is a widely measured physical water quality variable and has been successfully predicted using different ML methods. For example, classical ML methods have been used for monthly to daily predictions of stream temperatures in catchments with different characteristics, and include support vector regression (SVR; Rehana, 2019;Weierbach et al, 2022); decision tree-based regression models such as RF, XGBoost, and their variations (Feigl et al, 2021;Lu & Ma, 2020;Weierbach et al, 2022); and simple ANNs (Feigl et al, 2021;Zhu & Piotrowski, 2020). Among DL models, the LSTM deep neural network has become an increasingly popular choice for regional-scale hydrological predictions due to its ability to encode prior system states in the cell memory (e.g., Kratzert et al, 2018).…”

A Review on Snowmelt Models: Progress and Prospect

“…Machine learning has been applied to various aspects of snowmelt modeling, such as filling missing observation data [80,81], generating high accuracy rainfall observation data [82], merging satellite precipitation products and measured precipitation [83,84], forecasting real-time rainfall from radar [85], estimating snow cover from satellite data [86], estimating snow water equivalent [87,88], and calculating soil moisture and soil saturated hydraulic conductivity [89][90][91]. In addition, there are also many applications of machine learning in the field of hydrology, such as river water regime simulation [92][93][94], flood hydrograph prediction [95], groundwater dynamics simulation [96], parameter identification of hydrological models [97], and establishment of hydrological evaluation tools [98].…”

A Near Real-Time Hydrological Information System for the Upper Danube Basin

“…Higher water temperatures of water abstracted for the operation of the power plants lead to a reduction of cooling efficiency on the one hand but can also lead to the violation of legal constraints regarding maximum allowed river temperatures due to ecological reasons. These thresholds may be exceeded when warmed-up water is directed into the river after the power plant [58]. Knowledge of current temperature conditions could therefore help thermal power plant operators to plan accordingly, and the implementation of water temperature simulations in the HIS, e.g., following the methods shown in [58], is feasible for the future.…”

“…These thresholds may be exceeded when warmed-up water is directed into the river after the power plant [58]. Knowledge of current temperature conditions could therefore help thermal power plant operators to plan accordingly, and the implementation of water temperature simulations in the HIS, e.g., following the methods shown in [58], is feasible for the future.…”