Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes?
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/s00226-022-01404-y http://hdl.handle.net/11449/240628 |
Resumo: | Due to increasing global trade of timber commodities and illegal logging activities, wood species listed in the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) appendices are facing extinction, and their international trade has been banned or is under supervision. Reliable and applicable species-level discrimination methods have become urgent to protect global forest resources and promote the legal trade of timbers. This study aims to discriminate CITES-listed species from their look-alikes in international trade using quantitative wood anatomy (QWA) data coupled with machine learning (ML) analysis. Herein, the QWA data of 14 CITES-listed species and 15 of their look-alike species were collected from microscope slide collection, and four ML classifiers, J48, Multinomial Naïve Bayes, Random Forest, and SMO, were used to analyze the QWA data. The results indicated that ML classifiers exhibited better performance than traditional wood identification methods. Specifically, Multinomial Naïve Bayes outperformed other classifiers, and successfully discriminated CITES-listed Pterocarpus species from their look-alike species with an accuracy of 95.83%. Furthermore, the discrimination accuracy was affected by the combinations of wood anatomical features, and combinations with fewer features included could result in higher accuracy at the species level. In conclusion, the QWA data coupled with ML analysis could unlock the potential of wood anatomy to discriminate CITES species from their look-alikes for forensic applications. |
id |
UNSP_f5070cbef4a5e5bf05a8642732808465 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/240628 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes?Due to increasing global trade of timber commodities and illegal logging activities, wood species listed in the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) appendices are facing extinction, and their international trade has been banned or is under supervision. Reliable and applicable species-level discrimination methods have become urgent to protect global forest resources and promote the legal trade of timbers. This study aims to discriminate CITES-listed species from their look-alikes in international trade using quantitative wood anatomy (QWA) data coupled with machine learning (ML) analysis. Herein, the QWA data of 14 CITES-listed species and 15 of their look-alike species were collected from microscope slide collection, and four ML classifiers, J48, Multinomial Naïve Bayes, Random Forest, and SMO, were used to analyze the QWA data. The results indicated that ML classifiers exhibited better performance than traditional wood identification methods. Specifically, Multinomial Naïve Bayes outperformed other classifiers, and successfully discriminated CITES-listed Pterocarpus species from their look-alike species with an accuracy of 95.83%. Furthermore, the discrimination accuracy was affected by the combinations of wood anatomical features, and combinations with fewer features included could result in higher accuracy at the species level. In conclusion, the QWA data coupled with ML analysis could unlock the potential of wood anatomy to discriminate CITES species from their look-alikes for forensic applications.Department of Wood Anatomy and Utilization Research Institute of Wood Industry Chinese Academy of ForestryWood Collections Chinese Academy of ForestryCenter for Wood Anatomy Research Forest Products Laboratory USDA Forest ServiceDepartment of Botany University of WisconsinDepartment of Forestry and National Resources Purdue UniversityCiências Biológicas (Botânica) Universidade Estadual Paulista, São PauloDepartment of Sustainable Biomaterials Mississippi State UniversityCiências Biológicas (Botânica) Universidade Estadual Paulista, São PauloChinese Academy of ForestryUSDA Forest ServiceUniversity of WisconsinPurdue UniversityUniversidade Estadual Paulista (UNESP)Mississippi State UniversityLiu, ShoujiaHe, TuoWang, JiajunChen, JiabaoGuo, JuanJiang, XiaomeiWiedenhoeft, Alex C. [UNESP]Yin, Yafang2023-03-01T20:25:42Z2023-03-01T20:25:42Z2022-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1007/s00226-022-01404-yWood Science and Technology.1432-52250043-7719http://hdl.handle.net/11449/24062810.1007/s00226-022-01404-y2-s2.0-85135798152Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengWood Science and Technologyinfo:eu-repo/semantics/openAccess2023-03-01T20:25:42Zoai:repositorio.unesp.br:11449/240628Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-03-01T20:25:42Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes? |
title |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes? |
spellingShingle |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes? Liu, Shoujia |
title_short |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes? |
title_full |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes? |
title_fullStr |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes? |
title_full_unstemmed |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes? |
title_sort |
Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes? |
author |
Liu, Shoujia |
author_facet |
Liu, Shoujia He, Tuo Wang, Jiajun Chen, Jiabao Guo, Juan Jiang, Xiaomei Wiedenhoeft, Alex C. [UNESP] Yin, Yafang |
author_role |
author |
author2 |
He, Tuo Wang, Jiajun Chen, Jiabao Guo, Juan Jiang, Xiaomei Wiedenhoeft, Alex C. [UNESP] Yin, Yafang |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Chinese Academy of Forestry USDA Forest Service University of Wisconsin Purdue University Universidade Estadual Paulista (UNESP) Mississippi State University |
dc.contributor.author.fl_str_mv |
Liu, Shoujia He, Tuo Wang, Jiajun Chen, Jiabao Guo, Juan Jiang, Xiaomei Wiedenhoeft, Alex C. [UNESP] Yin, Yafang |
description |
Due to increasing global trade of timber commodities and illegal logging activities, wood species listed in the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) appendices are facing extinction, and their international trade has been banned or is under supervision. Reliable and applicable species-level discrimination methods have become urgent to protect global forest resources and promote the legal trade of timbers. This study aims to discriminate CITES-listed species from their look-alikes in international trade using quantitative wood anatomy (QWA) data coupled with machine learning (ML) analysis. Herein, the QWA data of 14 CITES-listed species and 15 of their look-alike species were collected from microscope slide collection, and four ML classifiers, J48, Multinomial Naïve Bayes, Random Forest, and SMO, were used to analyze the QWA data. The results indicated that ML classifiers exhibited better performance than traditional wood identification methods. Specifically, Multinomial Naïve Bayes outperformed other classifiers, and successfully discriminated CITES-listed Pterocarpus species from their look-alike species with an accuracy of 95.83%. Furthermore, the discrimination accuracy was affected by the combinations of wood anatomical features, and combinations with fewer features included could result in higher accuracy at the species level. In conclusion, the QWA data coupled with ML analysis could unlock the potential of wood anatomy to discriminate CITES species from their look-alikes for forensic applications. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-01-01 2023-03-01T20:25:42Z 2023-03-01T20:25:42Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1007/s00226-022-01404-y Wood Science and Technology. 1432-5225 0043-7719 http://hdl.handle.net/11449/240628 10.1007/s00226-022-01404-y 2-s2.0-85135798152 |
url |
http://dx.doi.org/10.1007/s00226-022-01404-y http://hdl.handle.net/11449/240628 |
identifier_str_mv |
Wood Science and Technology. 1432-5225 0043-7719 10.1007/s00226-022-01404-y 2-s2.0-85135798152 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Wood Science and Technology |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803046600140914688 |