Browse

Feature importance measures from random forest regressor using near-infrared spectra for predicting carbonization characteristics of kraft lignin-derived hydrochar

Cited 0 time in Web of Science Cited 0 time in Scopus
Issue Date
2023-01-05
Publisher
Springer Open
Citation
Journal of Wood Science. 2023 Jan 05;69(1):1
Keywords
Feature importance measuresHydrocharHydrothermal carbonizationLigninNear-infrared spectroscopyRandom forest
Abstract
This study investigated the feature importance of near-infrared spectra from random forest regression models constructed to predict the carbonization characteristics of hydrochars produced by hydrothermal carbonization of kraft lignin. The model achieved high coefficients of determination of 0.989, 0.988, and 0.985 with root mean square errors of 0.254, 0.003, and 0.008 when predicting the carbon content, atomic O/C ratio, and H/C ratio, respectively. The random forest models outperformed the multilayer perceptron models for all predictions. In the feature importance analysis, the spectral regions at 1600–1800 nm, the first overtone of C–H stretching vibrations, and 2000–2300 nm, the combination bands, were highly important for predicting the carbon content and O/C predictions, whereas the region at 1250–1711 nm contributed to predicting H/C. The random forest models trained with the high-importance regions achieved better prediction performances than those trained with the entire spectral range, demonstrating the usefulness of the feature importance yielded by the random forest and the feasibility of selective application of the spectral data.
ISSN
1611-4663
Language
English
URI
https://doi.org/10.1186/s10086-022-02073-y

https://hdl.handle.net/10371/189000
DOI
https://doi.org/10.1186/s10086-022-02073-y
Files in This Item:
Appears in Collections:
College of Agriculture and Life Sciences (농업생명과학대학)Dept. of Forest Sciences (산림과학부)Journal Papers (저널논문_산림과학부)
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse