Modeling of hydrological processes applying artificial intelligence techniques: a systematic literature review
Cargando...
Fecha
Director
Enlace al recurso
DOI
ORCID
Google Scholar
Cvlac
gruplac
Descripción Dominio:
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Santo Tomás. Seccional Bucaramanga
Compartir
Descripción
El campo de la hidrología es una de las ciencias que se enfoca en el estudio, la planificación y la cuantificación del recurso hídrico, generando una magnitud significativa de datos, los cuales son indispensables en la rama de la ingeniería civil. Actualmente dichos datos son analizados por una variedad de técnicas, que entre las predominantes son las de inteligencia artificial (IA) exclusivamente aplicadas al modelamiento de procesos hidrológicos como lluvia-escorrentía, inundaciones, sequías, evapotranspiración, nivel de lagos y predicción de caudales. El presente documento realizó una revisión sistemática de la literatura publicadas entre los años 2015 al 2021 en las diversas bases de datos como, Scopus, Springer Link, EBSCOhost, SciELO y ScienceDirect. Para ello se estableció un proceso de protocolo en el cual se introduce la base de datos seleccionada, definición de términos de búsqueda y filtros de selección. En efecto después de considerar el proceso de protocolo se obtuvieron 50 artículos indexados además de 4 artículos y 1 libro de páginas web. Como consecuencia se encontró que las redes neuronales artificiales (RNA) son las técnicas más utilizadas para el modelamiento de procesos hidrológicos donde con innovadores lenguajes de programación se pueden codificar con mucha mayor versatilidad. A la fecha el uso de RNA se las está implementando con otras técnicas para generar modelos híbridos que permiten obtener mejores estimaciones.
The field of hydrology is one of the sciences that focuses on the study, planning and quantification of water resources, generating a significant amount of data, which are indispensable in the branch of civil engineering. Currently these data are analyzed by a variety of techniques, among the predominant ones are artificial intelligence (IA) exclusively applied to the modeling of hydrological processes such as rain-runoff, floods, droughts, evapotranspiration, lake level and flow prediction. This document carried out a systematic review of the literature published between the years 2015 to 2021 in the various databases such as Scopus, Springer Link, EBSCOhost, SciELO and ScienceDirect. For this, a protocol process was established in which the selected database, definition of search terms and selection filters are entered. Indeed, after considering the protocol process, 50 indexed articles were obtained in addition to 4 articles and 1 book of web pages. As a consequence, it was found that artificial neural networks (ANNs) are the most widely used techniques for modeling hydrological processes where, with innovative programming languages, they can be encoded with much greater versatility. To date, the use of RNA is being implemented with other techniques to generate hybrid models that allow obtaining better estimates.
The field of hydrology is one of the sciences that focuses on the study, planning and quantification of water resources, generating a significant amount of data, which are indispensable in the branch of civil engineering. Currently these data are analyzed by a variety of techniques, among the predominant ones are artificial intelligence (IA) exclusively applied to the modeling of hydrological processes such as rain-runoff, floods, droughts, evapotranspiration, lake level and flow prediction. This document carried out a systematic review of the literature published between the years 2015 to 2021 in the various databases such as Scopus, Springer Link, EBSCOhost, SciELO and ScienceDirect. For this, a protocol process was established in which the selected database, definition of search terms and selection filters are entered. Indeed, after considering the protocol process, 50 indexed articles were obtained in addition to 4 articles and 1 book of web pages. As a consequence, it was found that artificial neural networks (ANNs) are the most widely used techniques for modeling hydrological processes where, with innovative programming languages, they can be encoded with much greater versatility. To date, the use of RNA is being implemented with other techniques to generate hybrid models that allow obtaining better estimates.
Abstract
Idioma
Palabras clave
Hydrological modeling, Artificial intelligence, Machine learning, Neural network, Evapotranspiration, Runoff, rainfall, Rainfall, Modelamiento hidrológico, Inteligencia artificial, Aprendizaje automático, Red Neuronal, Evapotranspiración, Escorrentía, Precipitación
Citación
Colecciones
Licencia Creative Commons
Copyright (c) 2022 ITECKNE