Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.

The techniques for forecasting meteorological variables are highly studied since prior knowledge of them allows for the efficient management of renewable energies, and also for other applications of science such as agriculture, health, engineering, energy, etc. In this research, the de sign, impleme...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Autor principal: Segovia Tapia, Jenny Aracely (author)
Outros Autores: Toaquiza Camalle, Jonathan Fernando (author)
Formato: article
Idioma:eng
Publicado em: 2023
Assuntos:
Acesso em linha:http://repositorio.espe.edu.ec/handle/21000/35763
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
_version_ 1839981020142632960
author Segovia Tapia, Jenny Aracely
author2 Toaquiza Camalle, Jonathan Fernando
author2_role author
author_facet Segovia Tapia, Jenny Aracely
Toaquiza Camalle, Jonathan Fernando
author_role author
collection Repositorio Universidad de las Fuerzas Armadas
dc.contributor.none.fl_str_mv Llanos Proaño, Jacqueline del Rosario
Rivas Lalaleo, David Raimundo
dc.creator.none.fl_str_mv Segovia Tapia, Jenny Aracely
Toaquiza Camalle, Jonathan Fernando
dc.date.none.fl_str_mv 2023-03-16T14:48:18Z
2023-03-16T14:48:18Z
2023-02-13
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.identifier.none.fl_str_mv Segovia Tapia, Jenny Aracely. Toaquiza Camalle, Jonathan Fernando (2023). Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre. Carrera de Ingeniería Electrónica e Instrumentación. Universidad de las Fuerzas Armadas ESPE. Extensión Latacunga.
ENI-0503
http://repositorio.espe.edu.ec/handle/21000/35763
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Universidad de las Fuerzas Armadas ESPE. Extensión Latacunga. Carrera de Ingeniería en Electrónica e Instrumentación.
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
dc.source.none.fl_str_mv reponame:Repositorio Universidad de las Fuerzas Armadas
instname:Universidad de las Fuerzas Armadas
instacron:ESPE
dc.subject.none.fl_str_mv APRENDISAJE AUTOMÁTICO
MODELOS DE PRONÓSTICOS
VARIABLES METEOROLÓGICAS
PYTHON - LEGUAJE DE PROGRAMACIÓN
dc.title.none.fl_str_mv Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description The techniques for forecasting meteorological variables are highly studied since prior knowledge of them allows for the efficient management of renewable energies, and also for other applications of science such as agriculture, health, engineering, energy, etc. In this research, the de sign, implementation, and comparison of forecasting models for meteorological variables have been performed using different Machine Learning techniques as part of Python open-source software. The techniques implemented include multiple linear regression, polynomial regression, random forest, decision tree, XGBoost, and multilayer perceptron neural network (MLP). To identify the best technique, the mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and coefficient of determination (R 2) are used as evaluation metrics. The most efficient techniques depend on the variable to be forecasting, however, it is noted that for most of them, random forest and XGBoost techniques present better performance. For temperature, the best per forming technique was Random Forest with an R 2 of 0.8631, MAE of 0.4728 °C, MAPE of 2.73%, and RMSE of 0.6621 °C; for relative humidity, was Random Forest with an R 2 of 0.8583, MAE of 2.1380RH, MAPE of 2.50 % and RMSE of 2.9003 RH; for solar radiation, was Random Forest with an R 2 of 0.7333, MAE of 65.8105 W/m2, and RMSE of 105.9141 W/m2 ; and for wind speed, was Random Forest with an R 2 of 0.3660, MAE of 0.1097 m/s, and RMSE of 0.2136 m/s.
eu_rights_str_mv openAccess
format article
id ESPE_b2f926440c1e9050a48634ecfc7659ce
identifier_str_mv Segovia Tapia, Jenny Aracely. Toaquiza Camalle, Jonathan Fernando (2023). Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre. Carrera de Ingeniería Electrónica e Instrumentación. Universidad de las Fuerzas Armadas ESPE. Extensión Latacunga.
ENI-0503
instacron_str ESPE
institution ESPE
instname_str Universidad de las Fuerzas Armadas
language eng
network_acronym_str ESPE
network_name_str Repositorio Universidad de las Fuerzas Armadas
oai_identifier_str oai:repositorio.espe.edu.ec:21000/35763
publishDate 2023
publisher.none.fl_str_mv Universidad de las Fuerzas Armadas ESPE. Extensión Latacunga. Carrera de Ingeniería en Electrónica e Instrumentación.
reponame_str Repositorio Universidad de las Fuerzas Armadas
repository.mail.fl_str_mv .
repository.name.fl_str_mv Repositorio Universidad de las Fuerzas Armadas - Universidad de las Fuerzas Armadas
repository_id_str 2042
spelling Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.Segovia Tapia, Jenny AracelyToaquiza Camalle, Jonathan FernandoAPRENDISAJE AUTOMÁTICOMODELOS DE PRONÓSTICOSVARIABLES METEOROLÓGICASPYTHON - LEGUAJE DE PROGRAMACIÓNThe techniques for forecasting meteorological variables are highly studied since prior knowledge of them allows for the efficient management of renewable energies, and also for other applications of science such as agriculture, health, engineering, energy, etc. In this research, the de sign, implementation, and comparison of forecasting models for meteorological variables have been performed using different Machine Learning techniques as part of Python open-source software. The techniques implemented include multiple linear regression, polynomial regression, random forest, decision tree, XGBoost, and multilayer perceptron neural network (MLP). To identify the best technique, the mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and coefficient of determination (R 2) are used as evaluation metrics. The most efficient techniques depend on the variable to be forecasting, however, it is noted that for most of them, random forest and XGBoost techniques present better performance. For temperature, the best per forming technique was Random Forest with an R 2 of 0.8631, MAE of 0.4728 °C, MAPE of 2.73%, and RMSE of 0.6621 °C; for relative humidity, was Random Forest with an R 2 of 0.8583, MAE of 2.1380RH, MAPE of 2.50 % and RMSE of 2.9003 RH; for solar radiation, was Random Forest with an R 2 of 0.7333, MAE of 65.8105 W/m2, and RMSE of 105.9141 W/m2 ; and for wind speed, was Random Forest with an R 2 of 0.3660, MAE of 0.1097 m/s, and RMSE of 0.2136 m/s.ESPE-LUniversidad de las Fuerzas Armadas ESPE. Extensión Latacunga. Carrera de Ingeniería en Electrónica e Instrumentación.Llanos Proaño, Jacqueline del RosarioRivas Lalaleo, David Raimundo2023-03-16T14:48:18Z2023-03-16T14:48:18Z2023-02-13info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfapplication/pdfSegovia Tapia, Jenny Aracely. Toaquiza Camalle, Jonathan Fernando (2023). Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre. Carrera de Ingeniería Electrónica e Instrumentación. Universidad de las Fuerzas Armadas ESPE. Extensión Latacunga.ENI-0503http://repositorio.espe.edu.ec/handle/21000/35763enginfo:eu-repo/semantics/openAccessreponame:Repositorio Universidad de las Fuerzas Armadasinstname:Universidad de las Fuerzas Armadasinstacron:ESPE2024-07-27T10:37:24Zoai:repositorio.espe.edu.ec:21000/35763Institucionalhttps://repositorio.espe.edu.ec/Universidad públicahttps://www.espe.edu.ec/https://repositorio.espe.edu.ec/oai.Ecuador...opendoar:20422024-07-27T10:37:24Repositorio Universidad de las Fuerzas Armadas - Universidad de las Fuerzas Armadasfalse
spellingShingle Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.
Segovia Tapia, Jenny Aracely
APRENDISAJE AUTOMÁTICO
MODELOS DE PRONÓSTICOS
VARIABLES METEOROLÓGICAS
PYTHON - LEGUAJE DE PROGRAMACIÓN
status_str publishedVersion
title Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.
title_full Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.
title_fullStr Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.
title_full_unstemmed Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.
title_short Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.
title_sort Sistema de predicción de variables meteorológicas utilizando Machine Learning y Software Libre.
topic APRENDISAJE AUTOMÁTICO
MODELOS DE PRONÓSTICOS
VARIABLES METEOROLÓGICAS
PYTHON - LEGUAJE DE PROGRAMACIÓN
url http://repositorio.espe.edu.ec/handle/21000/35763