Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico)

Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico)

Urías Estuary, a coastal lagoon in northwestern Mexico, is impacted by multiple anthropogenic stressors. Its hydrodynamics (and consequent contaminant dispersion) is mainly controlled by tidal currents. To better manage the coastal lagoon, accurate tidal-level forecasting is needed. Here we compare...

Descrizione completa

Salvato in:
Dettagli Bibliografici
Autori principali: Molino-Minero-Re, Erick, Cardoso-Mohedano, José Gilberto, Ruiz-Fernández, Ana Carolina, Sanchez-Cabeza, Joan-Albert
Natura: info:eu-repo/semantics/article
Lingua:eng
Pubblicazione: Iniversidad Autónoma de Baja California 2015
Accesso online:https://www.cienciasmarinas.com.mx/index.php/cmarinas/article/view/2463
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne! !
id repositorioinstitucional-20.500.12930-7468
record_format dspace
spelling repositorioinstitucional-20.500.12930-74682023-05-09T14:30:58Z Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico) Comparación de redes neuronales artificiales y análisis armónico para el pronóstico del nivel del mar (estero de Urías, Mazatlán, México) Molino-Minero-Re, Erick Cardoso-Mohedano, José Gilberto Ruiz-Fernández, Ana Carolina Sanchez-Cabeza, Joan-Albert Urías Estuary, a coastal lagoon in northwestern Mexico, is impacted by multiple anthropogenic stressors. Its hydrodynamics (and consequent contaminant dispersion) is mainly controlled by tidal currents. To better manage the coastal lagoon, accurate tidal-level forecasting is needed. Here we compare the predictions of sea level rise simulated by a conventional harmonic analysis, through Fourier spectral analysis, and by nonlinear autoregressive models based on artificial neural networks, both calibrated and validated using field data. Results showed that nonlinear autoregressive networks are useful to simulate the sea level over a time scale of several days (<10 days), in comparison to harmonic analysis, which can be used for longer time scales (>10 days). We concluded that the joint use of both methods may lead to a more robust strategy to forecast the sea level in the coastal lagoon.  El estero de Urías, una laguna costera localizada en el noroeste de México, está sometido a una gran variedad de impactos ambientales. Su hidrodinámica (y la dispersión de los contaminantes) es controlada principalmente por las corrientes de marea. El primer paso para comprender los procesos estuarinos de la laguna costera es contar con una previsión precisa de las elevaciones del nivel del mar. En el presente trabajo se comparan las predicciones del nivel del mar simuladas por un modelo tradicional de análisis armónico, a través de un análisis espectral de Fourier, con modelos autorregresivos no lineales basados en redes neuronales artificiales, ambos validados y calibrados con datos de campo. Nuestros resultados mostraron que las redes autorregresivas no lineales son útiles para simular la elevación del nivel del mar con una escala relativamente corta de tiempo (<10 días), mientras que el modelo basado en el análisis armónico se puede utilizar para simular escalas temporales grandes (>10 días). Concluimos que el uso conjunto de ambos métodos podría conducir a una estrategia más robusta para predecir las elevaciones del nivel del mar en la laguna costera. 2015-03-05 2021-06-03T03:55:23Z 2021-06-03T03:55:23Z info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Peer-reviewed Article Artículo Arbitrado https://www.cienciasmarinas.com.mx/index.php/cmarinas/article/view/2463 10.7773/cm.v40i4.2463 https://hdl.handle.net/20.500.12930/7468 eng https://www.cienciasmarinas.com.mx/index.php/cmarinas/article/view/2463/1534 Copyright (c) 2015 Ciencias Marinas application/pdf Iniversidad Autónoma de Baja California Ciencias Marinas; Vol. 40 No. 4 (2014); 251-261 Ciencias Marinas; Vol. 40 Núm. 4 (2014); 251-261 2395-9053 0185-3880
institution Repositorio Institucional
collection DSpace
language eng
description Urías Estuary, a coastal lagoon in northwestern Mexico, is impacted by multiple anthropogenic stressors. Its hydrodynamics (and consequent contaminant dispersion) is mainly controlled by tidal currents. To better manage the coastal lagoon, accurate tidal-level forecasting is needed. Here we compare the predictions of sea level rise simulated by a conventional harmonic analysis, through Fourier spectral analysis, and by nonlinear autoregressive models based on artificial neural networks, both calibrated and validated using field data. Results showed that nonlinear autoregressive networks are useful to simulate the sea level over a time scale of several days (<10 days), in comparison to harmonic analysis, which can be used for longer time scales (>10 days). We concluded that the joint use of both methods may lead to a more robust strategy to forecast the sea level in the coastal lagoon. 
format info:eu-repo/semantics/article
author Molino-Minero-Re, Erick
Cardoso-Mohedano, José Gilberto
Ruiz-Fernández, Ana Carolina
Sanchez-Cabeza, Joan-Albert
spellingShingle Molino-Minero-Re, Erick
Cardoso-Mohedano, José Gilberto
Ruiz-Fernández, Ana Carolina
Sanchez-Cabeza, Joan-Albert
Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico)
author_facet Molino-Minero-Re, Erick
Cardoso-Mohedano, José Gilberto
Ruiz-Fernández, Ana Carolina
Sanchez-Cabeza, Joan-Albert
author_sort Molino-Minero-Re, Erick
title Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico)
title_short Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico)
title_full Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico)
title_fullStr Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico)
title_full_unstemmed Comparison of artificial neural networks and harmonic analysis for sea level forecasting (Urias coastal lagoon, Mazatlan, Mexico)
title_sort comparison of artificial neural networks and harmonic analysis for sea level forecasting (urias coastal lagoon, mazatlan, mexico)
publisher Iniversidad Autónoma de Baja California
publishDate 2015
url https://www.cienciasmarinas.com.mx/index.php/cmarinas/article/view/2463
_version_ 1792610586351108096

Documenti analoghi