Urban flood forecasting with multi-output neural networks: a physically-based and data-driven approach

ABSTRACT Physically based models for spatial flood prediction are time and computationally expensive. Data-driven models, while faster, require large amounts of data for adjustment. This study presents an original methodology combining these two approaches, using a physically-based model (HEC-RAS 2D...

Full description

Saved in:
Bibliographic Details
Main Authors: Renata Bulling Magro, Olavo Correa Pedrollo, Silvio Luis Rafaeli Neto
Format: Article
Language:English
Published: Associação Brasileira de Recursos Hídricos 2025-05-01
Series:Revista Brasileira de Recursos Hídricos
Subjects:
Online Access:http://www.scielo.br/scielo.php?script=sci_arttext&pid=S2318-03312025000100216&lng=en&tlng=en
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325686179758080
author Renata Bulling Magro
Olavo Correa Pedrollo
Silvio Luis Rafaeli Neto
author_facet Renata Bulling Magro
Olavo Correa Pedrollo
Silvio Luis Rafaeli Neto
author_sort Renata Bulling Magro
collection DOAJ
description ABSTRACT Physically based models for spatial flood prediction are time and computationally expensive. Data-driven models, while faster, require large amounts of data for adjustment. This study presents an original methodology combining these two approaches, using a physically-based model (HEC-RAS 2D), adjusted with known events, to generate water depth data at control points and multi-output artificial neural networks (ANNs) for flood forecasting at these points. The performance of the ANN in this research, with application to the urban area of Lages-SC, southern Brazil, resulted in average mean absolute errors of 3.9, 9.8, and 46 cm, with corresponding Nash-Sutcliffe coefficients of 0.99, 0.98, and 0.75 at lead times of 3 h, 8 h, and 20 h, respectively. Multi-output ANNs exhibited greater robustness compared to single-output ANNs for spatial flood prediction. The methodology is suitable for developing models for spatial predictions of urban flooding, with sufficient agility to take necessary measures.
format Article
id doaj-art-e9a7f0ca5e914364a65717b1d2d5f56b
institution Kabale University
issn 2318-0331
language English
publishDate 2025-05-01
publisher Associação Brasileira de Recursos Hídricos
record_format Article
series Revista Brasileira de Recursos Hídricos
spelling doaj-art-e9a7f0ca5e914364a65717b1d2d5f56b2025-08-20T03:48:19ZengAssociação Brasileira de Recursos HídricosRevista Brasileira de Recursos Hídricos2318-03312025-05-013010.1590/2318-0331.302520240089Urban flood forecasting with multi-output neural networks: a physically-based and data-driven approachRenata Bulling Magrohttps://orcid.org/0000-0003-2433-100XOlavo Correa Pedrollohttps://orcid.org/0000-0001-7264-0259Silvio Luis Rafaeli Netohttps://orcid.org/0000-0002-6640-1961ABSTRACT Physically based models for spatial flood prediction are time and computationally expensive. Data-driven models, while faster, require large amounts of data for adjustment. This study presents an original methodology combining these two approaches, using a physically-based model (HEC-RAS 2D), adjusted with known events, to generate water depth data at control points and multi-output artificial neural networks (ANNs) for flood forecasting at these points. The performance of the ANN in this research, with application to the urban area of Lages-SC, southern Brazil, resulted in average mean absolute errors of 3.9, 9.8, and 46 cm, with corresponding Nash-Sutcliffe coefficients of 0.99, 0.98, and 0.75 at lead times of 3 h, 8 h, and 20 h, respectively. Multi-output ANNs exhibited greater robustness compared to single-output ANNs for spatial flood prediction. The methodology is suitable for developing models for spatial predictions of urban flooding, with sufficient agility to take necessary measures.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S2318-03312025000100216&lng=en&tlng=enUrban floodingHydrodynamic modelingComputational intelligenceForecasting model
spellingShingle Renata Bulling Magro
Olavo Correa Pedrollo
Silvio Luis Rafaeli Neto
Urban flood forecasting with multi-output neural networks: a physically-based and data-driven approach
Revista Brasileira de Recursos Hídricos
Urban flooding
Hydrodynamic modeling
Computational intelligence
Forecasting model
title Urban flood forecasting with multi-output neural networks: a physically-based and data-driven approach
title_full Urban flood forecasting with multi-output neural networks: a physically-based and data-driven approach
title_fullStr Urban flood forecasting with multi-output neural networks: a physically-based and data-driven approach
title_full_unstemmed Urban flood forecasting with multi-output neural networks: a physically-based and data-driven approach
title_short Urban flood forecasting with multi-output neural networks: a physically-based and data-driven approach
title_sort urban flood forecasting with multi output neural networks a physically based and data driven approach
topic Urban flooding
Hydrodynamic modeling
Computational intelligence
Forecasting model
url http://www.scielo.br/scielo.php?script=sci_arttext&pid=S2318-03312025000100216&lng=en&tlng=en
work_keys_str_mv AT renatabullingmagro urbanfloodforecastingwithmultioutputneuralnetworksaphysicallybasedanddatadrivenapproach
AT olavocorreapedrollo urbanfloodforecastingwithmultioutputneuralnetworksaphysicallybasedanddatadrivenapproach
AT silvioluisrafaelineto urbanfloodforecastingwithmultioutputneuralnetworksaphysicallybasedanddatadrivenapproach