文献类型：期刊文献

英文题名：Can quantitative wood anatomy data coupled with machine learning analysis discriminate CITES species from their look-alikes?

作者：Liu, Shoujia[1,2] He, Tuo[1,2] Wang, Jiajun[1] Chen, Jiabao[1,2] Guo, Juan[1,2] Jiang, Xiaomei[1,2] Wiedenhoeft, Alex C.[3,4,5,6,7] Yin, Yafang[1,2]

第一作者：Liu, Shoujia

通信作者：He, T[1];He, T[2]

机构：[1]Chinese Acad Forestry, Res Inst Wood Ind, Dept Wood Anat & Utilizat, Beijing 100091, Peoples R China;[2]Chinese Acad Forestry, Wood Collect, Beijing 100091, Peoples R China;[3]USDA, Ctr Wood Anat Res, Forest Prod Lab, Forest Serv, Madison, WI 53726 USA;[4]Univ Wisconsin, Dept Bot, Madison, WI 53706 USA;[5]Purdue Univ, Dept Forestry & Natl Resources, W Lafayette, IN 47907 USA;[6]Univ Estadual Paulista, Ciencias Biol Bot, BR-18610034 Botucatu, SP, Brazil;[7]Mississippi State Univ, Dept Sustainable Biomat, Starkville, MS 39759 USA

年份：2022

卷号：56

期号：5

起止页码：1567-1583

外文期刊名：WOOD SCIENCE AND TECHNOLOGY

收录：;EI(收录号：20223312584862);Scopus(收录号：2-s2.0-85135798152);WOS:【SCI-EXPANDED(收录号:WOS:000840022800001)】；

基金：Project of Natural Science Foundation of Beijing, 6224064, Tuo He, Project of Chinese Academy of Forestry, CAFYBB2021ZD002, Yafang Yin

语种：英文

外文关键词：Classifiers - Conservation - Decision trees - Machine learning - Timber

摘要：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 Naive 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 Naive 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.