Comparison of various chemometric methods on visible and near-infrared spectral analysis for wood density prediction among different tree species and geographical origins
Visible and near-infrared (Vis-NIR) spectroscopy has been widely applied in many fields for the qualitative and quantitative analysis. Chemometric techniques including pre-processing, variable selection, and multivariate calibration models play an important role to better extract useful information...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-03-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1121287/full |
| _version_ | 1811155447266148352 |
|---|---|
| author | Ying Li Brian K. Via Feifei Han Yaoxiang Li Zhiyong Pei |
| author_facet | Ying Li Brian K. Via Feifei Han Yaoxiang Li Zhiyong Pei |
| author_sort | Ying Li |
| collection | DOAJ |
| description | Visible and near-infrared (Vis-NIR) spectroscopy has been widely applied in many fields for the qualitative and quantitative analysis. Chemometric techniques including pre-processing, variable selection, and multivariate calibration models play an important role to better extract useful information from spectral data. In this study, a new de-noising method (lifting wavelet transform, LWT), four variable selection methods, as well as two non-linear machine learning models were simultaneously analyzed to compare the impact of chemometric approaches on wood density determination among various tree species and geographical locations. In addition, fruit fly optimization algorithm (FOA) and response surface methodology (RSM) were employed to optimize the parameters of generalized regression neural network (GRNN) and particle swarm optimization-support vector machine (PSO-SVM), respectively. As for various chemometric methods, the optimal chemometric method was different for the same tree species collected from different locations. FOA-GRNN model combined with LWT and CARS deliver the best performance for Chinese white poplar of Heilongjiang province. In contrast, PLS model showed a good performance for Chinese white poplar collected from Jilin province based on raw spectra. However, for other tree species, RSM-PSO-SVM models can improve the performance of wood density prediction compared to traditional linear and FOA-GRNN models. Especially for Acer mono Maxim, when compared to linear models, the coefficient of determination of prediction set (Rp2) and relative prediction deviation (RPD) were increased by 47.70% and 44.48%, respectively. And the dimensionality of Vis-NIR spectral data was decreased from 2048 to 20. Therefore, the appropriate chemometric technique should be selected before building calibration models. |
| first_indexed | 2024-04-10T04:34:09Z |
| format | Article |
| id | doaj.art-b128e1b7f45e43ca868edbecf4e86caf |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-10T04:34:09Z |
| publishDate | 2023-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-b128e1b7f45e43ca868edbecf4e86caf2023-03-10T05:10:41ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-03-011410.3389/fpls.2023.11212871121287Comparison of various chemometric methods on visible and near-infrared spectral analysis for wood density prediction among different tree species and geographical originsYing Li0Brian K. Via1Feifei Han2Yaoxiang Li3Zhiyong Pei4College of Energy and Transportation Engineering, Inner Mongolia Agricultural University, Hohhot, ChinaForest Products Development Center, School of Forestry and Wildlife Sciences, Auburn University, Auburn, AL, United StatesLaboratory Zhejiang Huadong Forestry Engineering Consulting and Design Corporation, Hangzhou, ChinaCollege of Engineering and Technology, Northeast Forestry University, Harbin, ChinaCollege of Energy and Transportation Engineering, Inner Mongolia Agricultural University, Hohhot, ChinaVisible and near-infrared (Vis-NIR) spectroscopy has been widely applied in many fields for the qualitative and quantitative analysis. Chemometric techniques including pre-processing, variable selection, and multivariate calibration models play an important role to better extract useful information from spectral data. In this study, a new de-noising method (lifting wavelet transform, LWT), four variable selection methods, as well as two non-linear machine learning models were simultaneously analyzed to compare the impact of chemometric approaches on wood density determination among various tree species and geographical locations. In addition, fruit fly optimization algorithm (FOA) and response surface methodology (RSM) were employed to optimize the parameters of generalized regression neural network (GRNN) and particle swarm optimization-support vector machine (PSO-SVM), respectively. As for various chemometric methods, the optimal chemometric method was different for the same tree species collected from different locations. FOA-GRNN model combined with LWT and CARS deliver the best performance for Chinese white poplar of Heilongjiang province. In contrast, PLS model showed a good performance for Chinese white poplar collected from Jilin province based on raw spectra. However, for other tree species, RSM-PSO-SVM models can improve the performance of wood density prediction compared to traditional linear and FOA-GRNN models. Especially for Acer mono Maxim, when compared to linear models, the coefficient of determination of prediction set (Rp2) and relative prediction deviation (RPD) were increased by 47.70% and 44.48%, respectively. And the dimensionality of Vis-NIR spectral data was decreased from 2048 to 20. Therefore, the appropriate chemometric technique should be selected before building calibration models.https://www.frontiersin.org/articles/10.3389/fpls.2023.1121287/fullvisible and near infrared spectroscopylifting wavelet transformvariable selectionresponse surface methodologywood density |
| spellingShingle | Ying Li Brian K. Via Feifei Han Yaoxiang Li Zhiyong Pei Comparison of various chemometric methods on visible and near-infrared spectral analysis for wood density prediction among different tree species and geographical origins Frontiers in Plant Science visible and near infrared spectroscopy lifting wavelet transform variable selection response surface methodology wood density |
| title | Comparison of various chemometric methods on visible and near-infrared spectral analysis for wood density prediction among different tree species and geographical origins |
| title_full | Comparison of various chemometric methods on visible and near-infrared spectral analysis for wood density prediction among different tree species and geographical origins |
| title_fullStr | Comparison of various chemometric methods on visible and near-infrared spectral analysis for wood density prediction among different tree species and geographical origins |
| title_full_unstemmed | Comparison of various chemometric methods on visible and near-infrared spectral analysis for wood density prediction among different tree species and geographical origins |
| title_short | Comparison of various chemometric methods on visible and near-infrared spectral analysis for wood density prediction among different tree species and geographical origins |
| title_sort | comparison of various chemometric methods on visible and near infrared spectral analysis for wood density prediction among different tree species and geographical origins |
| topic | visible and near infrared spectroscopy lifting wavelet transform variable selection response surface methodology wood density |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1121287/full |
| work_keys_str_mv | AT yingli comparisonofvariouschemometricmethodsonvisibleandnearinfraredspectralanalysisforwooddensitypredictionamongdifferenttreespeciesandgeographicalorigins AT briankvia comparisonofvariouschemometricmethodsonvisibleandnearinfraredspectralanalysisforwooddensitypredictionamongdifferenttreespeciesandgeographicalorigins AT feifeihan comparisonofvariouschemometricmethodsonvisibleandnearinfraredspectralanalysisforwooddensitypredictionamongdifferenttreespeciesandgeographicalorigins AT yaoxiangli comparisonofvariouschemometricmethodsonvisibleandnearinfraredspectralanalysisforwooddensitypredictionamongdifferenttreespeciesandgeographicalorigins AT zhiyongpei comparisonofvariouschemometricmethodsonvisibleandnearinfraredspectralanalysisforwooddensitypredictionamongdifferenttreespeciesandgeographicalorigins |