Three Environments, One Problem: Forecasting Water Temperature in Central Europe in Response to Climate Change

Water temperature is a fundamental parameter influencing a range of biotic and abiotic processes occurring within various components of the hydrosphere. This study presents a multi-step, data-driven predictive modeling framework to estimate water temperatures for the period 2021–2100 in three aquati...

Full description

Saved in:
Bibliographic Details
Main Authors: Mariusz Ptak, Mariusz Sojka, Katarzyna Szyga-Pluta, Teerachai Amnuaylojaroen
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Forecasting
Subjects:
Online Access:https://www.mdpi.com/2571-9394/7/2/24
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432602099843072
author Mariusz Ptak
Mariusz Sojka
Katarzyna Szyga-Pluta
Teerachai Amnuaylojaroen
author_facet Mariusz Ptak
Mariusz Sojka
Katarzyna Szyga-Pluta
Teerachai Amnuaylojaroen
author_sort Mariusz Ptak
collection DOAJ
description Water temperature is a fundamental parameter influencing a range of biotic and abiotic processes occurring within various components of the hydrosphere. This study presents a multi-step, data-driven predictive modeling framework to estimate water temperatures for the period 2021–2100 in three aquatic environments in Central Europe: the Odra River, the Szczecin Lagoon, and the Baltic Sea. The framework integrates Bayesian Model Averaging (BMA), Random Sample Consensus (RANSAC) regression, Gradient Boosting Regressor (GBR), and Random Forest (RF) machine learning models. To assess the performance of the models, the coefficient of determination (R2), mean absolute error (<i>MAE</i>), and root mean square error (<i>RMSE</i>) were used. The results showed that the application of statistical downscaling methods improved the prediction of air temperatures with respect to the BMA. Moreover, the RF method was used to predict water temperature. The best model performance was obtained for the Baltic Sea and the lowest for the Odra River. Under the SSP2-4.5 and SSP5-8.5 scenario-based simulations, projected air temperature increases in the period 2021–2100 could range from 1.5 °C to 1.7 °C and 4.7 to 5.1 °C. In contrast, the increase in water temperatures by 2100 will be between 1.2 °C and 1.6 °C (SSP2-4.5 scenario) and between 3.5 °C and 4.9 °C (SSP5-8.5).
format Article
id doaj-art-e470eabd69a64811b0b6c2a911c10e8d
institution Kabale University
issn 2571-9394
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Forecasting
spelling doaj-art-e470eabd69a64811b0b6c2a911c10e8d2025-08-20T03:27:18ZengMDPI AGForecasting2571-93942025-05-01722410.3390/forecast7020024Three Environments, One Problem: Forecasting Water Temperature in Central Europe in Response to Climate ChangeMariusz Ptak0Mariusz Sojka1Katarzyna Szyga-Pluta2Teerachai Amnuaylojaroen3Department of Hydrology and Water Management, Adam Mickiewicz University, Krygowskiego 10, 61-680 Poznań, PolandDepartment of Land Improvement, Environmental Development and Spatial Management, Poznań University of Life Sciences, Piątkowska 94E, 60-649 Poznań, PolandDepartment of Meteorology and Climatology, Adam Mickiewicz University, Krygowskiego 10, 61-680 Poznań, PolandSchool of Energy and Environment, University of Phayao, Phayao 56000, ThailandWater temperature is a fundamental parameter influencing a range of biotic and abiotic processes occurring within various components of the hydrosphere. This study presents a multi-step, data-driven predictive modeling framework to estimate water temperatures for the period 2021–2100 in three aquatic environments in Central Europe: the Odra River, the Szczecin Lagoon, and the Baltic Sea. The framework integrates Bayesian Model Averaging (BMA), Random Sample Consensus (RANSAC) regression, Gradient Boosting Regressor (GBR), and Random Forest (RF) machine learning models. To assess the performance of the models, the coefficient of determination (R2), mean absolute error (<i>MAE</i>), and root mean square error (<i>RMSE</i>) were used. The results showed that the application of statistical downscaling methods improved the prediction of air temperatures with respect to the BMA. Moreover, the RF method was used to predict water temperature. The best model performance was obtained for the Baltic Sea and the lowest for the Odra River. Under the SSP2-4.5 and SSP5-8.5 scenario-based simulations, projected air temperature increases in the period 2021–2100 could range from 1.5 °C to 1.7 °C and 4.7 to 5.1 °C. In contrast, the increase in water temperatures by 2100 will be between 1.2 °C and 1.6 °C (SSP2-4.5 scenario) and between 3.5 °C and 4.9 °C (SSP5-8.5).https://www.mdpi.com/2571-9394/7/2/24riversseaclimate changeprediction
spellingShingle Mariusz Ptak
Mariusz Sojka
Katarzyna Szyga-Pluta
Teerachai Amnuaylojaroen
Three Environments, One Problem: Forecasting Water Temperature in Central Europe in Response to Climate Change
Forecasting
rivers
sea
climate change
prediction
title Three Environments, One Problem: Forecasting Water Temperature in Central Europe in Response to Climate Change
title_full Three Environments, One Problem: Forecasting Water Temperature in Central Europe in Response to Climate Change
title_fullStr Three Environments, One Problem: Forecasting Water Temperature in Central Europe in Response to Climate Change
title_full_unstemmed Three Environments, One Problem: Forecasting Water Temperature in Central Europe in Response to Climate Change
title_short Three Environments, One Problem: Forecasting Water Temperature in Central Europe in Response to Climate Change
title_sort three environments one problem forecasting water temperature in central europe in response to climate change
topic rivers
sea
climate change
prediction
url https://www.mdpi.com/2571-9394/7/2/24
work_keys_str_mv AT mariuszptak threeenvironmentsoneproblemforecastingwatertemperatureincentraleuropeinresponsetoclimatechange
AT mariuszsojka threeenvironmentsoneproblemforecastingwatertemperatureincentraleuropeinresponsetoclimatechange
AT katarzynaszygapluta threeenvironmentsoneproblemforecastingwatertemperatureincentraleuropeinresponsetoclimatechange
AT teerachaiamnuaylojaroen threeenvironmentsoneproblemforecastingwatertemperatureincentraleuropeinresponsetoclimatechange