Predictive Modeling of River Water Temperatures in Catu River: A Neural Network-Based Approach

Predicting water temperature (Tw) in tropical environments is crucial for ecosystem monitoring and the sustainable management of water resources. Highly accurate and reliable Tw forecasts are essential for the ecological management of rivers. This study evaluates the performance of machine learning-...

Full description

Saved in:
Bibliographic Details
Main Authors: Carmen Goncalves de Macedo e Silva, José Roberto de Araújo Fontoura, Alarcon Matos de Oliveira, Thais de Souza Neri, Roberto Luiz Souza Monteiro, Thiago Barros Murari, Alexandre do Nascimento Silva, Leandro Brito Santos, Marcos Batista Figueredo
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Applied Computational Intelligence and Soft Computing
Online Access:http://dx.doi.org/10.1155/acis/8810911
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849729561834553344
author Carmen Goncalves de Macedo e Silva
José Roberto de Araújo Fontoura
Alarcon Matos de Oliveira
Thais de Souza Neri
Roberto Luiz Souza Monteiro
Thiago Barros Murari
Alexandre do Nascimento Silva
Leandro Brito Santos
Marcos Batista Figueredo
author_facet Carmen Goncalves de Macedo e Silva
José Roberto de Araújo Fontoura
Alarcon Matos de Oliveira
Thais de Souza Neri
Roberto Luiz Souza Monteiro
Thiago Barros Murari
Alexandre do Nascimento Silva
Leandro Brito Santos
Marcos Batista Figueredo
author_sort Carmen Goncalves de Macedo e Silva
collection DOAJ
description Predicting water temperature (Tw) in tropical environments is crucial for ecosystem monitoring and the sustainable management of water resources. Highly accurate and reliable Tw forecasts are essential for the ecological management of rivers. This study evaluates the performance of machine learning-based predictive models in forecasting Tw in the Catu River. The models were trained using climatic and hydrological data collected from 2009 to 2016 and validated with real data from 2023. The evaluated models include backpropagation neural network (BPNN), Random Forest, Bidirectional LSTM (BiLSTM), Air2Stream, and NARX, employing nine input variables such as atmospheric pressure, air temperature, and water vapor concentration. The results show that the BiLSTM model achieved the best performance, with a root mean square error (RMSE) of 0.12°C and R2 = 0.98, followed by BPNN with an RMSE of 0.18°C and R2 = 0.91, and the Random Forest model, which obtained an NSE of 0.95. These models demonstrated a strong ability to predict Tw under both normal and extreme conditions, capturing the thermal dynamics of the Catu River with high precision during events involving minor thermal variations. Conversely, the NARX and Air2Stream models exhibited lower performance, proving more prone to errors under conditions of extreme variability. The findings of this study provide valuable scientific insights for river Tw prediction and the protection of aquatic ecosystems, with practical applications in water resource management in tropical regions.
format Article
id doaj-art-72bb5d4a222440f0866f6541cf85c4de
institution DOAJ
issn 1687-9732
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Applied Computational Intelligence and Soft Computing
spelling doaj-art-72bb5d4a222440f0866f6541cf85c4de2025-08-20T03:09:12ZengWileyApplied Computational Intelligence and Soft Computing1687-97322025-01-01202510.1155/acis/8810911Predictive Modeling of River Water Temperatures in Catu River: A Neural Network-Based ApproachCarmen Goncalves de Macedo e Silva0José Roberto de Araújo Fontoura1Alarcon Matos de Oliveira2Thais de Souza Neri3Roberto Luiz Souza Monteiro4Thiago Barros Murari5Alexandre do Nascimento Silva6Leandro Brito Santos7Marcos Batista Figueredo8Modeling and Simulations of BiosystemsModeling and Simulations of BiosystemsModeling and Simulations of BiosystemsModeling and Simulations of BiosystemsComputational ModelingIndustrial Management and TechnologyModeling and Simulations of BiosystemsCenter for Science and Technology in Energy and SustainabilityModeling and Simulations of BiosystemsPredicting water temperature (Tw) in tropical environments is crucial for ecosystem monitoring and the sustainable management of water resources. Highly accurate and reliable Tw forecasts are essential for the ecological management of rivers. This study evaluates the performance of machine learning-based predictive models in forecasting Tw in the Catu River. The models were trained using climatic and hydrological data collected from 2009 to 2016 and validated with real data from 2023. The evaluated models include backpropagation neural network (BPNN), Random Forest, Bidirectional LSTM (BiLSTM), Air2Stream, and NARX, employing nine input variables such as atmospheric pressure, air temperature, and water vapor concentration. The results show that the BiLSTM model achieved the best performance, with a root mean square error (RMSE) of 0.12°C and R2 = 0.98, followed by BPNN with an RMSE of 0.18°C and R2 = 0.91, and the Random Forest model, which obtained an NSE of 0.95. These models demonstrated a strong ability to predict Tw under both normal and extreme conditions, capturing the thermal dynamics of the Catu River with high precision during events involving minor thermal variations. Conversely, the NARX and Air2Stream models exhibited lower performance, proving more prone to errors under conditions of extreme variability. The findings of this study provide valuable scientific insights for river Tw prediction and the protection of aquatic ecosystems, with practical applications in water resource management in tropical regions.http://dx.doi.org/10.1155/acis/8810911
spellingShingle Carmen Goncalves de Macedo e Silva
José Roberto de Araújo Fontoura
Alarcon Matos de Oliveira
Thais de Souza Neri
Roberto Luiz Souza Monteiro
Thiago Barros Murari
Alexandre do Nascimento Silva
Leandro Brito Santos
Marcos Batista Figueredo
Predictive Modeling of River Water Temperatures in Catu River: A Neural Network-Based Approach
Applied Computational Intelligence and Soft Computing
title Predictive Modeling of River Water Temperatures in Catu River: A Neural Network-Based Approach
title_full Predictive Modeling of River Water Temperatures in Catu River: A Neural Network-Based Approach
title_fullStr Predictive Modeling of River Water Temperatures in Catu River: A Neural Network-Based Approach
title_full_unstemmed Predictive Modeling of River Water Temperatures in Catu River: A Neural Network-Based Approach
title_short Predictive Modeling of River Water Temperatures in Catu River: A Neural Network-Based Approach
title_sort predictive modeling of river water temperatures in catu river a neural network based approach
url http://dx.doi.org/10.1155/acis/8810911
work_keys_str_mv AT carmengoncalvesdemacedoesilva predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach
AT joserobertodearaujofontoura predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach
AT alarconmatosdeoliveira predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach
AT thaisdesouzaneri predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach
AT robertoluizsouzamonteiro predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach
AT thiagobarrosmurari predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach
AT alexandredonascimentosilva predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach
AT leandrobritosantos predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach
AT marcosbatistafigueredo predictivemodelingofriverwatertemperaturesincaturiveraneuralnetworkbasedapproach