文献类型：期刊文献

英文题名：Machine learning algorithms for in-line monitoring during yeast fermentations based on Raman spectroscopy

作者：Wu, Debiao[1];Xu, Yaying[1];Xu, Feng[1];Shao, Minghao[1];Huang, Mingzhi[1]

机构：[1]East China Univ Sci & Technol, State Key Lab Bioreactor Engn, 130 Meilong Rd, Shanghai 200237, Peoples R China

年份：2024

卷号：132

外文期刊名：VIBRATIONAL SPECTROSCOPY

收录：;EI(收录号：20241315800437);WOS:【SCI-EXPANDED(收录号:WOS:001246231500001)】；

基金：This work was financially supported by a grant from National Nat- ural Science Foundation of China (Grant NO. 32071461) , National Key Research and Development Program of China (Grant NO. 2019YFA0904300) .

语种：英文

外文关键词：Machine learning; Raman spectroscopy; Yeast fermentation; Process analytical technology

摘要：Given the intricacies and nonlinearity inherent to industrial fermentation systems, the application of process analytical technology presents considerable benefits for the direct, real-time monitoring, control, and assessment of synthetic processes. In this study, we introduce an in-line monitoring approach utilizing Raman spectroscopy for ethanol production by Saccharomyces cerevisiae. Initially, we employed feature selection techniques from the realm of machine learning to reduce the dimensionality of the Raman spectral data. Our findings reveal that feature selection results in a noteworthy reduction of over 90% in model training time, concurrently enhancing the predictive performance of glycerol and cell concentration by 14.20% and 17.10% at the root mean square error (RMSE) level. Subsequently, we conducted model retraining using 15 machine learning algorithms, with hyperparameters optimized through grid search. Our results illustrate that the post-hyperparameter adjustment model exhibits improvements in RMSE for ethanol, glycerol, glucose, and biomass by 9.73%, 4.33%, 22.22%, and 13.79%, respectively. Finally, specific machine learning algorithms, namely BaggingRegressor, Support Vector Regression, BayesianRidge, and VotingRegressor, were identified as suitable models for predicting glucose, ethanol, glycerol, and cell concentrations, respectively. Notably, the coefficient of determination (R2) ranged from 0.89 to 0.97, and RMSE values ranged from 0.06 to 2.59 g/L on the testing datasets. The study highlights machine learning's effectiveness in Raman spectroscopy data analysis for improved industrial fermentation monitoring, enhancing efficiency, and offering novel modeling insights.