文献类型：期刊文献

英文题名：Machine learning algorithms for rapid estimation of holocellulose content of poplar clones based on Raman spectroscopy

作者：Gao, Wenli[1,2] Zhou, Liang[1,2] Liu, Shengquan[1,2] Guan, Ying[1,2] Gao, Hui[1,2] Hu, Jianjun[3]

第一作者：Gao, Wenli

通信作者：Zhou, L[1]

机构：[1]Anhui Agr Univ, Sch Forestry & Landscape Architecture, Hefei 230036, Anhui, Peoples R China;[2]State Forest & Grassland Adm Wood Qual Improvemen, Key Lab, Hefei 230036, Anhui, Peoples R China;[3]Chinese Acad Forestry, State Key Lab Tree Genet & Breeding, Key Lab Tree Breeding & Cultivat, Natl Forestry & Grassland Adm,Res Inst Forestry, Beijing, Peoples R China

年份：2022

卷号：292

外文期刊名：CARBOHYDRATE POLYMERS

收录：;EI(收录号：20222112158201);Scopus(收录号：2-s2.0-85130542772);WOS:【SCI-EXPANDED(收录号:WOS:000806363700009)】；

基金：This work was supported by National Key Research and Development Program (2017YFD0600201) ; the National Natural Science Foundation of China (No. 31770596) ; the State Key Laboratory of Bio-Fibers and Eco-Textiles (grant no. K2019-13) .

语种：英文

外文关键词：Holocellulose content; Machine learning algorithms; Raman spectroscopy; CatBoost; XGBoost

摘要：In this study, regularization algorithms (RR, LR, and ENR), classical ML algorithms (SVR, DT, and RF), and advanced GBM algorithms (LightGBM, CatBoost, and XGBoost) were applied to build the holocellulose content predictive models of poplar based on features extracted from Raman spectra. Evaluation results of models indicate that classical ML algorithms show higher predictive accuracy than regularization algorithms, and the advanced GBM algorithms better than the classical ML algorithms. Furthermore, models built by CatBoost and XGBoost can estimate holocellulose content with high predictive accuracy of test R(2 )above 0.93 and test RMSE less than 0.29%. It provides the heretofore best precision of holocellulose content predictive model based on Raman spectroscopy so far for our knowledge. Therefore, it is suggested that Raman spectroscopy coupled with ML algorithms is a promising tool for predicting the holocellulose content in poplar which can be applied in large-scale tree genetic and breeding programs.