Open Access Article
This Open Access Article is licensed under a Creative Commons Attribution 3.0 Unported Licence
Correction: Artificial intelligence-driven dynamic regulation for high-efficiency gentamicin C1a production
Feng Xuabc,
Yuan Wangab,
Hao Gaoab,
Kaihao Huab,
Rong Benab,
Ali Mohsinab,
Yuanxin Guoab,
Xu Lia,
Hui Wuab,
Haifeng Hangabc,
Ju Chuabc and
Xiwei Tian*abc
aState Key Laboratory of Bioreactor Engineering, Qingdao Innovation Institute of East China University of Science and Technology, East China University of Science and Technology, Shanghai 200237, China. E-mail: xiweitian@ecust.edu.cn; Tel: +86-21-64253021
bNational Center of Bio-Engineering & Technology (Shanghai), East China University of Science and Technology, Shanghai 200237, China
cShanghai Collaborative Innovation Center for Biomanufacturing Technology, East China University of Science and Technology, Shanghai 200237, China
First published on 29th May 2026
Abstract
Correction for ‘Artificial intelligence-driven dynamic regulation for high-efficiency gentamicin C1a production’ by Feng Xu et al., Green Chem., 2025, 27, 13436–13454, https://doi.org/10.1039/D5GC02507A.
The authors note that the original article had an error in the sentence ‘The number of neurons in the input layer was determined based on key variables influencing the fermentation process, including total sugar concentration (TS), reducing sugar (RS), ammonium ion concentration (AN), DO, pH, OUR, and CER (Fig. 1b)’. The correct sentence is ‘The number of neurons in the input layer was determined based on key variables influencing the fermentation process, including total sugar concentration (TS), reducing sugar (RS), ammonium ion concentration (AN), DO, pH, OUR, and CER (Fig. S1b)’.
The authors also note an error in the layout of Fig. 3. The correct figure with the caption is given here.
 | ||
| Fig. 1 Feature importance analysis and NSGA-II optimization. (a) Feature importance analysis with μ as prediction matrix; (b) feature importance ranking and index with μ as prediction matrix; (c) Pareto front analysis of qS and μ for multi-objective optimization; (d) feature importance analysis with qP as prediction matrix; (e) feature importance ranking and index with qP as prediction matrix; (f) Pareto front analysis of qS and qP for multi-objective optimization. | ||
In addition, the authors also note an error in the caption of Fig. 4 in the original article. Fig. 4 and the correct caption are given here.
 | ||
| Fig. 2 Online spectral monitoring model validation and BPNN model prediction validation. (a) Development of a multi-source spectral model. (b) Predicted AN based on multi-source spectral model versus offline values; (c) predicted total sugars based on multi-source spectral model versus offline values; (d) trend of μ in the control group; (e) trend of μ in the experimental group; (f) trend of qP in the control group; (g) trend of qP in the experimental group; (h) trend of qS in the control group; (i) trends of qS in the experimental group. | ||
The Royal Society of Chemistry apologises for these errors and any consequent inconvenience to authors and readers.
| This journal is © The Royal Society of Chemistry 2026 |