Uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem

Many studies have shown that by using nonlinear methods, the relationship between tree-ring parameters and the environment can be described (modelled) better and in more detail. In our study, (multiple) linear regression (MLR) with four nonlinear machine learning methods are compared: artif...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jernej Jevšenak, Sašo Džeroski, Tom Levanič
Formato:	article
Lenguaje:	DE EN ES FR SL
Publicado:	Slovenian Forestry Institute 2017
Materias:	Forestry SD1-669.5 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/e62aee6dd03b45ea8919671b3e2cd43c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e62aee6dd03b45ea8919671b3e2cd43c
record_format	dspace
spelling	oai:doaj.org-article:e62aee6dd03b45ea8919671b3e2cd43c2021-11-15T12:34:52ZUporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem2335-31122335-395310.20315/ASetL.114.2https://doaj.org/article/e62aee6dd03b45ea8919671b3e2cd43c2017-01-01T00:00:00Zhttp://dirros.openscience.si/IzpisGradiva.php?id=8175https://doaj.org/toc/2335-3112https://doaj.org/toc/2335-3953 Many studies have shown that by using nonlinear methods, the relationship between tree-ring parameters and the environment can be described (modelled) better and in more detail. In our study, (multiple) linear regression (MLR) with four nonlinear machine learning methods are compared: artificial neural networks (ANN), model trees (MT), bagging of model trees (BMT) and random forests of regression trees (RF). To compare the different regression methods, four datasets were used. The performance of the learned models was estimated by using 10-fold cross-validation and an additional hold-out test. For all datasets, better results were obtained by the nonlinear machine learning regression methods, which can explain more variance and yield lower error. However, none of the considered methods outperformed all other methods for all datasets. Therefore, we suggest testing several different methods before selecting the best one, e.g. for climate reconstruction.Jernej JevšenakSašo DžeroskiTom LevaničSlovenian Forestry InstitutearticleForestrySD1-669.5Environmental sciencesGE1-350DEENESFRSLActa Silvae et Ligni, Vol 114, Pp 21-24 (2017)
institution	DOAJ
collection	DOAJ
language	DE EN ES FR SL
topic	Forestry SD1-669.5 Environmental sciences GE1-350
spellingShingle	Forestry SD1-669.5 Environmental sciences GE1-350 Jernej Jevšenak Sašo Džeroski Tom Levanič Uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem
description	Many studies have shown that by using nonlinear methods, the relationship between tree-ring parameters and the environment can be described (modelled) better and in more detail. In our study, (multiple) linear regression (MLR) with four nonlinear machine learning methods are compared: artificial neural networks (ANN), model trees (MT), bagging of model trees (BMT) and random forests of regression trees (RF). To compare the different regression methods, four datasets were used. The performance of the learned models was estimated by using 10-fold cross-validation and an additional hold-out test. For all datasets, better results were obtained by the nonlinear machine learning regression methods, which can explain more variance and yield lower error. However, none of the considered methods outperformed all other methods for all datasets. Therefore, we suggest testing several different methods before selecting the best one, e.g. for climate reconstruction.
format	article
author	Jernej Jevšenak Sašo Džeroski Tom Levanič
author_facet	Jernej Jevšenak Sašo Džeroski Tom Levanič
author_sort	Jernej Jevšenak
title	Uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem
title_short	Uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem
title_full	Uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem
title_fullStr	Uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem
title_full_unstemmed	Uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem
title_sort	uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem
publisher	Slovenian Forestry Institute
publishDate	2017
url	https://doaj.org/article/e62aee6dd03b45ea8919671b3e2cd43c
work_keys_str_mv	AT jernejjevsenak uporabametodstrojnegaucenjazapreucevanjeodnosovmedznacilnostmibranikinokoljem AT sasodzeroski uporabametodstrojnegaucenjazapreucevanjeodnosovmedznacilnostmibranikinokoljem AT tomlevanic uporabametodstrojnegaucenjazapreucevanjeodnosovmedznacilnostmibranikinokoljem
_version_	1718428467694927872

Uporaba metod strojnega učenja za preučevanje odnosov med značilnostmi branik in okoljem

Ejemplares similares