Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ UPCommons. Portal de...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

Modelización predictiva de los cambios de la turbidez del agua del Río Llobregat

Authors: Aguilera Martínez, David;

Modelización predictiva de los cambios de la turbidez del agua del Río Llobregat

Abstract

Aquest estudi analitza la predicció d'episodis d'alta terbolesa en el riu Llobregat mitjançant models de machine learning. S'aplica un model de processos de Hawkes per a capturar el comportament autoexcitat dels episodis. Posteriorment s'avaluen diferents models mitjançant la llibreria H2O en R, incorporant variables com a pluja acumulada i volatilitat estimada mitjançant models GARCH. El millor acompliment s'aconsegueix amb un model Stacked Ensemble, que aconsegueix un 98% de precisió. Els resultats permeten anticipar fenòmens crítics i millorar la gestió de l'aigua, amb potencial d'aplicació a altres sistemes fluvials.

Este estudio analiza la predicción de episodios de alta turbidez en el río Llobregat mediante modelos de machine learning. Se aplica un modelo de procesos de Hawkes para capturar el comportamiento autoexcitado de los episodios. Posteriormente se evalúan distintos modelos mediante la librería H2O en R, incorporando variables como lluvia acumulada y volatilidad estimada mediante modelos GARCH. El mejor desempeño se alcanza con un modelo Stacked Ensemble, que logra un 98% de precisión. Los resultados permiten anticipar fenómenos críticos y mejorar la gestión del agua, con potencial de aplicación a otros sistemas fluviales.

This study analyzes the prediction of high turbidity episodes in the Llobregat River using machine learning models. A Hawkes process model is applied to capture the self-exciting behavior of the episodes. Subsequently, various models are evaluated using the H2O library in R, incorporating variables such as accumulated rainfall and volatility estimated through GARCH models. The best performance is achieved with a Stacked Ensemble model, reaching 98% accuracy. The results make it possible to anticipate critical phenomena and improve water management, with potential applications to other river systems.

Country
Spain
Related Organizations
Keywords

Turbidez, Classificació AMS::86 Geophysics, Àrees temàtiques de la UPC::Matemàtiques i estadística, GARCH., Hawkes, río Llobregat, Time series analysis, Water quality — Mathematical models, predicción, machine learning, Classificació AMS::68 Computer science::68T Artificial intelligence, Machine learning, Aprenentatge automàtic, Classificació AMS::62 Statistics::62M Inference from stochastic processes, Sèries temporals, Hidrologia — Models matemàtics

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green