Evolutionary feature selection to estimate forest stand variablesusing LiDAR

Light detection and ranging (LiDAR) has become an important tool in forestry. LiDAR-derived models are mostly developed by means of multiple linear regression (MLR) after stepwise selection of predictors. An increasing interest in machine learning and evolutionary computation has recently arisen to...

Descripción completa

Detalles Bibliográficos
Autores: García Gutiérrez, Jorge, González Ferreiro, Eduardo, Riquelme Santos, José Cristóbal, Miranda, David, Diéguez Aranda, Ulises, Navarro Cerrillo, Rafael M.
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2014
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/43570
Acceso en línea:http://hdl.handle.net/11441/43570
https://doi.org/10.1016/j.jag.2013.06.005
Access Level:acceso abierto
Palabra clave:Evolutionary computation
Forest-stand variables
LiDAR
regression
Stepwise selection
id ES_6d2f5c6dec99183e58df6edf96033b2b
oai_identifier_str oai:idus.us.es:11441/43570
network_acronym_str ES
network_name_str España
repository_id_str
spelling Evolutionary feature selection to estimate forest stand variablesusing LiDARGarcía Gutiérrez, JorgeGonzález Ferreiro, EduardoRiquelme Santos, José CristóbalMiranda, DavidDiéguez Aranda, UlisesNavarro Cerrillo, Rafael M.Evolutionary computationForest-stand variablesLiDARregressionStepwise selectionLight detection and ranging (LiDAR) has become an important tool in forestry. LiDAR-derived models are mostly developed by means of multiple linear regression (MLR) after stepwise selection of predictors. An increasing interest in machine learning and evolutionary computation has recently arisen to improve regression use in LiDAR data processing. Although evolutionary machine learning has already proven to be suitable for regression, evolutionary computation may also be applied to improve parametric models such as MLR. This paper provides a hybrid approach based on joint use of MLR and a novel genetic algorithm for the estimation of the main forest stand variables. We show a comparison between our genetic approach and other common methods of selecting predictors. The results obtained from several LiDAR datasets with different pulse densities in two areas of the Iberian Peninsula indicate that genetic algorithms perform better than the other methods statistically. Preliminary studies suggest that a lack of parametric conditions in field data and possible misuse of parametric tests may be the main reasons for the better performance of the genetic algorithm. This research confirms the findings of previous studies that outline the importance of evolutionary computation in the context of LiDAR analisys of forest data, especially when the size of fieldwork datatasets is reduced.Ministerio de Ciencia y Tecnología TIN2007- 68084-C-00Ministerio de Ciencia y Tecnología TIN2011-28956-C02Xunta de Galicia 09MRU022291PXunta de Galicia CGL2011-30285-C02-02Xunta de Galicia FP7-SME-2011-BSGElsevierLenguajes y Sistemas Informáticos2014info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/11441/43570https://doi.org/10.1016/j.jag.2013.06.005reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésInternational Journal of Applied Earth Observation and Geoinformation, 26, 119-131.TIN2007- 68084-C-00TIN2011-28956-C0209MRU022291PCGL2011-30285-C02-02FP7-SME-2011-BSGhttp://dx.doi.org/10.1016/j.jag.2013.06.005info:eu-repo/semantics/openAccessoai:idus.us.es:11441/435702026-06-17T12:51:07Z
dc.title.none.fl_str_mv Evolutionary feature selection to estimate forest stand variablesusing LiDAR
title Evolutionary feature selection to estimate forest stand variablesusing LiDAR
spellingShingle Evolutionary feature selection to estimate forest stand variablesusing LiDAR
García Gutiérrez, Jorge
Evolutionary computation
Forest-stand variables
LiDAR
regression
Stepwise selection
title_short Evolutionary feature selection to estimate forest stand variablesusing LiDAR
title_full Evolutionary feature selection to estimate forest stand variablesusing LiDAR
title_fullStr Evolutionary feature selection to estimate forest stand variablesusing LiDAR
title_full_unstemmed Evolutionary feature selection to estimate forest stand variablesusing LiDAR
title_sort Evolutionary feature selection to estimate forest stand variablesusing LiDAR
dc.creator.none.fl_str_mv García Gutiérrez, Jorge
González Ferreiro, Eduardo
Riquelme Santos, José Cristóbal
Miranda, David
Diéguez Aranda, Ulises
Navarro Cerrillo, Rafael M.
author García Gutiérrez, Jorge
author_facet García Gutiérrez, Jorge
González Ferreiro, Eduardo
Riquelme Santos, José Cristóbal
Miranda, David
Diéguez Aranda, Ulises
Navarro Cerrillo, Rafael M.
author_role author
author2 González Ferreiro, Eduardo
Riquelme Santos, José Cristóbal
Miranda, David
Diéguez Aranda, Ulises
Navarro Cerrillo, Rafael M.
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
dc.subject.none.fl_str_mv Evolutionary computation
Forest-stand variables
LiDAR
regression
Stepwise selection
topic Evolutionary computation
Forest-stand variables
LiDAR
regression
Stepwise selection
description Light detection and ranging (LiDAR) has become an important tool in forestry. LiDAR-derived models are mostly developed by means of multiple linear regression (MLR) after stepwise selection of predictors. An increasing interest in machine learning and evolutionary computation has recently arisen to improve regression use in LiDAR data processing. Although evolutionary machine learning has already proven to be suitable for regression, evolutionary computation may also be applied to improve parametric models such as MLR. This paper provides a hybrid approach based on joint use of MLR and a novel genetic algorithm for the estimation of the main forest stand variables. We show a comparison between our genetic approach and other common methods of selecting predictors. The results obtained from several LiDAR datasets with different pulse densities in two areas of the Iberian Peninsula indicate that genetic algorithms perform better than the other methods statistically. Preliminary studies suggest that a lack of parametric conditions in field data and possible misuse of parametric tests may be the main reasons for the better performance of the genetic algorithm. This research confirms the findings of previous studies that outline the importance of evolutionary computation in the context of LiDAR analisys of forest data, especially when the size of fieldwork datatasets is reduced.
publishDate 2014
dc.date.none.fl_str_mv 2014
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11441/43570
https://doi.org/10.1016/j.jag.2013.06.005
url http://hdl.handle.net/11441/43570
https://doi.org/10.1016/j.jag.2013.06.005
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv International Journal of Applied Earth Observation and Geoinformation, 26, 119-131.
TIN2007- 68084-C-00
TIN2011-28956-C02
09MRU022291P
CGL2011-30285-C02-02
FP7-SME-2011-BSG
http://dx.doi.org/10.1016/j.jag.2013.06.005
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869410333576134656
score 15.301603

Similares en LA Referencia