Cargando…
Optimized Design of Neural Networks for a River Water Level Prediction System
In this paper, a Multi-Objective Genetic Algorithm (MOGA) framework for the design of Artificial Neural Network (ANN) models is used to design 1-step-ahead prediction models of river water levels. The design procedure is a near-automatic method that, given the data at hand, can partition it into dat...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8512320/ https://www.ncbi.nlm.nih.gov/pubmed/34640822 http://dx.doi.org/10.3390/s21196504 |
_version_ | 1784582962572951552 |
---|---|
author | Lineros, Miriam López Luna, Antonio Madueño Ferreira, Pedro M. Ruano, Antonio E. |
author_facet | Lineros, Miriam López Luna, Antonio Madueño Ferreira, Pedro M. Ruano, Antonio E. |
author_sort | Lineros, Miriam López |
collection | PubMed |
description | In this paper, a Multi-Objective Genetic Algorithm (MOGA) framework for the design of Artificial Neural Network (ANN) models is used to design 1-step-ahead prediction models of river water levels. The design procedure is a near-automatic method that, given the data at hand, can partition it into datasets and is able to determine a near-optimal model with the right topology and inputs, offering a good performance on unseen data, i.e., data not used for model design. An example using more than 11 years of water level data (593,178 samples) of the Carrión river collected at Villoldo gauge station shows that the MOGA framework can obtain low-complex models with excellent performance on unseen data, achieving an RMSE of 2.5 × 10(−3), which compares favorably with results obtained by alternative design. |
format | Online Article Text |
id | pubmed-8512320 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-85123202021-10-14 Optimized Design of Neural Networks for a River Water Level Prediction System Lineros, Miriam López Luna, Antonio Madueño Ferreira, Pedro M. Ruano, Antonio E. Sensors (Basel) Article In this paper, a Multi-Objective Genetic Algorithm (MOGA) framework for the design of Artificial Neural Network (ANN) models is used to design 1-step-ahead prediction models of river water levels. The design procedure is a near-automatic method that, given the data at hand, can partition it into datasets and is able to determine a near-optimal model with the right topology and inputs, offering a good performance on unseen data, i.e., data not used for model design. An example using more than 11 years of water level data (593,178 samples) of the Carrión river collected at Villoldo gauge station shows that the MOGA framework can obtain low-complex models with excellent performance on unseen data, achieving an RMSE of 2.5 × 10(−3), which compares favorably with results obtained by alternative design. MDPI 2021-09-29 /pmc/articles/PMC8512320/ /pubmed/34640822 http://dx.doi.org/10.3390/s21196504 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Lineros, Miriam López Luna, Antonio Madueño Ferreira, Pedro M. Ruano, Antonio E. Optimized Design of Neural Networks for a River Water Level Prediction System |
title | Optimized Design of Neural Networks for a River Water Level Prediction System |
title_full | Optimized Design of Neural Networks for a River Water Level Prediction System |
title_fullStr | Optimized Design of Neural Networks for a River Water Level Prediction System |
title_full_unstemmed | Optimized Design of Neural Networks for a River Water Level Prediction System |
title_short | Optimized Design of Neural Networks for a River Water Level Prediction System |
title_sort | optimized design of neural networks for a river water level prediction system |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8512320/ https://www.ncbi.nlm.nih.gov/pubmed/34640822 http://dx.doi.org/10.3390/s21196504 |
work_keys_str_mv | AT linerosmiriamlopez optimizeddesignofneuralnetworksforariverwaterlevelpredictionsystem AT lunaantoniomadueno optimizeddesignofneuralnetworksforariverwaterlevelpredictionsystem AT ferreirapedrom optimizeddesignofneuralnetworksforariverwaterlevelpredictionsystem AT ruanoantonioe optimizeddesignofneuralnetworksforariverwaterlevelpredictionsystem |