Data-efficient and interpretable machine learning for iridium-catalyzed methanol carbonylation: Ru-enabled operating windows and process-ready guidance

Zhou Xiaokun; Yang Tao; Qin Yao; Li Yue; Wei Qiyue; Xie Jinhui; Wu Yanxun; Liu Yuchang; Wei Zengxi; Zhao Shuangliang

doi:null

Your Location：

Home >

Browse articles >

Data-efficient and interpretable machine learning for iridium-catalyzed methanol carbonylation: Ru-enabled operating windows and process-ready guidance

Updated：2026-08-24

- Data-efficient and interpretable machine learning for iridium-catalyzed methanol carbonylation: Ru-enabled operating windows and process-ready guidance
- Data-efficient and interpretable machine learning for iridium-catalyzed methanol carbonylation: Ru-enabled operating windows and process-ready guidance
- 中国化学工程学报（英文） 2026年94卷第6期页码：147-155
- Affiliations：
  
  University Engineering Research Center of Green Chemical New Materials, School of Chemistry and Chemical Engineering, Guangxi University, Nanning 530004, China
- Author bio：
  
  Corresponding authors. E-mail addresses: zengxiwei@gxu.edu.cn(Z. Wei)
  szhao@gxu.edu.cn(S. Zhao)
- Funds：
  
  S. Zhao and Z. Wei thanks the support from Guangxi Science and Technology Major Program(AA23062019;AA23073019;AA23062020);the National Natural Science Foundation of China(22308063;22178072);Z. Wei also thanks the support from the Dean Project of Guangxi Key Laboratory of Petrochemical Resource Processing and Process Intensification Technology. This work is also supported by the Guangxi Major Talent Project(2023Z007)
- DOI：
  中图分类号：
- 收稿：2025-11-07，
  
  修回：2026-01-06，
  
  录用：2026-01-06，
  
  网络首发：2026-02-26，
  
  纸质出版：2026-06
- Accepted：
Scan QR Code
Zhou Xiaokun, Yang Tao, Qin Yao, 等. Data-efficient and interpretable machine learning for iridium-catalyzed methanol carbonylation: Ru-enabled operating windows and process-ready guidance[J]. 中国化学工程学报（英文）, 2026,94(6):147-155.

Zhou Xiaokun, Yang Tao, Qin Yao, et al. Data-efficient and interpretable machine learning for iridium-catalyzed methanol carbonylation: Ru-enabled operating windows and process-ready guidance[J]. Chinese Journal of Chemical Engineering, 2026, 94(6): 147-155.
Zhou Xiaokun, Yang Tao, Qin Yao, 等. Data-efficient and interpretable machine learning for iridium-catalyzed methanol carbonylation: Ru-enabled operating windows and process-ready guidance[J]. 中国化学工程学报（英文）, 2026,94(6):147-155. DOI：

Zhou Xiaokun, Yang Tao, Qin Yao, et al. Data-efficient and interpretable machine learning for iridium-catalyzed methanol carbonylation: Ru-enabled operating windows and process-ready guidance[J]. Chinese Journal of Chemical Engineering, 2026, 94(6): 147-155. DOI：

摘要

Abstract

Methanol carbonylation is the primary method for producing acetic acid

but the formulation screening and process control for homogeneous iridium systems are hindered by limited and heterogeneous datasets. We compile literature and patent records and construct stratified models based on the presence of a ruthenium cocatalyst

integrating data augmentation with Bayesian model selection to achieve high-accuracy

interpretable predictors of formation rate. Multi-scale interpretation

(including rank correlations and SHAP analysis

reveals that the addition of ruthenium (Ru) alters rate control: the

insitu

water level emerges as the primary driver through its influence on acidity/iodide activity and methyl iodide (MeI) regeneration. Consequently

the marginal effectiveness of iridium (Ir) increases

whereas the independent impact of initial acetic acid (AcOH)/MeI is diminished due to the swift establishment of solvent and MeI pools. Guided by these findings

we define Ru-enabled operating windows for Ru-containing systems

prioritizing

in-situ

concentration management by keeping H

O at a relatively low but non-zero level and maintaining MeOAc in a MeOAc-rich region where the SHAP curves begin to flatten

indicating diminishing returns. On this basis

fine-tune Ir loading and pressure in small i

ncrements to enhance per-Ir effective turnover without disturbing the established

in-situ

balance.

关键词

Keywords

references

A. Haynes, Catalytic methanol carbonylation, Advances in Catalysis, Elsevier (2010).

A.C. Dimian, A.A. Kiss, Enhancing the separation efficiency in acetic ac id manufacturing by methanol carbonylation, Chem. Eng. Technol. 44 (10) (2021) 1792-1802.

A. Haynes, Acetic acid synthesis by catalytic carbonylation of methanol, Catalytic Carbonylation Reactions, Springer, (2006).

P. Kalck, C. Le Berre, P. Serp, Recent advances in the methanol carbonylation reaction into acetic acid, Coord. Chem. Rev. 402 (2020) 213078.

J.H. Jones, The cativa™process for the manufacture of acetic acid, Platin. Met. Rev. 44 (2000) 94-105.

P.I.P. Elliott, S. Haak, A.J.H.M. Meijer, G.J. Sunley, A. Haynes, Reactivity of Ir(III) carbonyl complexes with water: alternative by-product formation pathways in catalytic methanol carbonylation, Dalton Trans. 42 (47) (2013) 16538-16546.

H. Cheung, M.E. Huckman, G.P. Torrence, Low water methanol carbonylation process for high acetic acid production and for water balance control, US Patent 7005541B2(2006).

S.S. Zhang, W.X. Ji, N. Feng, L.P. Lan, Y.Y. Li, Y.L. Ma, Study on Rh(I)/Ru(III) bimetallic catalyst catalyzed carbonylation of methanol to acetic acid, Materials 13 (18) (2020) 4026.

N. Yoneda, S. Kusano, M. Yasui, P. Pujado, S. Wilcher, Recent advances in processes and catalysts for the production of acetic acid, Appl. Catal. Gen. 221 (1-2) (2001) 253-265.

M. Volpe, G. Wu, A. Iretskii, P.C . Ford, Photochemical and time resolved spectroscopic studies of intermediates relevant to iridium-catalyzed methanol carbonylation: photoinduced CO migratory insertion, Inorg. Chem. 45 (4) (2006) 1861-1870.

A. Haynes, P.M. Maitlis, G.E. Morris, G.J. Sunley, H. Adams, P.W. Badger, C.M. Bowers, D.B. Cook, P.I.P. Elliott, T. Ghaffar, H. Green, T.R. Griffin, M. Payne, J. M. Pearson, M.J. Taylor, P.W. Vickers, R.J. Watt, Promotion of iridium-catalyzed methanol carbonylation: mechanistic studies of the cativa process, J. Am. Chem. Soc. 126 (9) (2004) 2847-2861.

V. Hosseinpour, M. Kazemeini, A. Mohammadrezaee, Optimisation of Rupromoted Ir-catalysed methanol carbonylation utilising response surface methodology, Appl. Catal. Gen. 394 (1-2) (2011) 166-175.

L.A. Key, M.J. Payne, A.D. Poole, Process for the production of acetic acid, Pat WO2004026805A1(2004).

M.J.R.C.W. Baker, M.F. Giles, C.S. Garland, M.J. Muskett, Process for the production of acetic acid by carbonylation, Pat.EP0752406A1 (1997).

M. Kazemeini, V. Hosseinpour, Minimizing CO 2 formation in Ir-catalyzed methanol carbonylation process, Procedia Eng. 42 (2012) 1179-1188.

G. Lyall-Brookes, A.C. Padgham, A.G. Slater, Flow chemistry as a tool for high throughput experimentation, Digit. Discov. 4 (9) (2025) 2364-2400.

G. Tom, S.P. Schmid, S.G. Baird, Y. Cao, K. Darvish, H. Hao, S. Lo, S. Pablo-García, E.M. Rajaonson, M. Skreta, N. Yoshikawa, S. Corapi, G.D. Akkoc, F. Strieth-Kalthoff, M. Seifrid, A. Aspuru-Guzik, Self-driving laboratories for chemistry and materials science, Chem. Rev. 124 (16) (2024) 9633-9732.

R. Nsouli, G. Galiyan, L.K.G. Ackerman-Biegasiewicz, Advancing organic chemistry using high-throughput experimentation, Angew. Chem. Int. Ed. 64 (40) (2025) e202506588.

Z.J. Lin, T.Y. Wang, Q. Li, Designing active and stable Ir-based catalysts for the acidic oxygen evolution reaction, Ind. Chem. Mater. 1 (3) (2023) 299-311.

P. Raccuglia, K.C. Elbert, P.D.F. Adler, C. Falk, M.B. Wenny, A. Mollo, M. Zeller, S.A. Friedler, J. Schrier, A.J. Norquist, Machine-learning-assisted materials discovery using failed experiments, Nature 533 (7601) (2016) 73-76.

Y.K. Lee, Density functional theory (DFT) calculations and catalysis, Catalysts 11 (4) (2021) 454.

B.M. Abraham, M.V. Jyothirmai, P. Sinha, F. Viñes, J.K. Singh, F. Illas, Catalysis in the digital age: unlocking the power of data with machine learning, Wires Comput. Mol. Sci. 14 (5) (2024) e1730.

B.Z. Dou, Z.L. Zhu, E. Merkurjev, L. Ke, L. Chen, J. Jiang, Y.Y. Zhu, J. Liu, B.G. Zhang, G.W. Wei, Machine learning methods for small data challenges in molecular science, Chem. Rev. 123 (13) (2023) 8736-8780.

E. Shim, A. Tewari, T. Cernak, P.M. Zimmerman, Machine learning strategies for reaction development: toward the low-data limit, J. Chem. Inf. Model. 63 (12) (2023) 3659-3668.

S.J. Pan, Q. Yang, A survey on transfer learning, IEEE Trans. Knowl. Data Eng. 22 (10) (2010) 1345-1359.

J.E. van Engelen, H.H. Hoos, A survey on semi-supervised learning, Mach. Learn. 109 (2) (2020) 373-440.

C. Shorten, T.M. Khoshgoftaar, A survey on image data augmentation for deep learning, J. Big Data 6 (1) (2019) 60.

X. Jin, H. Zhu, S. Li, Z. Wang, Z. Liu, J. Tian, C. Yu, H. Qin, S.Z. Li, A Survey on Mixup Augmentations and Beyond, 2025, https://doi.org/10.48550/arXiv. 2409.05202.

J. Smucny, G. Shi, T.A. Lesh, C.S. Carter, I. Davidson, Data augmentation with mixup: enhancing performance of a functional neuroimaging-based prognostic deep learning classifier in recent onset psychosis, Neuroimage Clin 36 (2022) 103214.

Z.M. Dong, Q. Hu, Y.J. Guo, M. Cordy, M. Papadakis, Z.Y. Zhang, Y. Le Traon, J.J. Zhao, MixCode: enhancing code classification by mixup-based data augmentation, in:2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER). Taipa, Macao, China, IEEE, 2023, pp. 379-390.

Z.D. Wang, S.Q. Yang, H.F. Qin, Y.K. Liu, J.Q. Wang, MixCFormer: a CNN-transformer hybrid with m ixup augmentation for enhanced finger vein attack detection, Electronics 14 (2) (2025) 362.

L.J. Zhang, Z. Deng, K. Kawaguchi, A. Ghorbani, J. Zou, How Does Mixup Help with Robustness and Generalization? , 2020, https://doi.org/10.48550/arXiv. 2010.04819 arXiv: 2010.04819.

L. Carratino, M. Cissé, R. Jenatton, J.P. Vert, On mixup regularization 23 (1) (2022)14632-14662.

B. Shahriari, K. Swersky, Z.Y. Wang, R.P. Adams, N. de Freitas, Taking the human out of the loop: a review of Bayesian optimization, Proc. IEEE 104 (1) (2016) 148-175.

T. Yang, J. Liang, Y. Qin, X.K. Zhou, J. He, Y. Wang, Y.Q. Zhu, Z.X. Wei, S.L. Zhao, Machine learning-driven prediction of ethylene homopolymerization reaction performance: FI catalyst activity, polyethylene molecular weight, and molecular weight distribution, Chem. Eng. J. 511 (2025) 162198.

Q. Wang, Y. Qin, J.C. Xie, Y.F. Kong, Q. Sun, Z.X. Wei, S.L. Zhao, Size-controllable high-entropy alloys toward stable hydrogen production at industrialscale current densities, Adv. Mater. 37 (10) (2025) e2420173.

E. Štrumbelj, I. Kononenko, Explaining prediction models and individual predictions with feature contributions, Knowl. Inf. Syst. 41 (3) (2014) 647-665.

S.M. Lundberg, G. Erion, H. Chen, A. DeGrave, J.M. Prutkin, B. Nair, R. Katz, J. Himmelfarb, N. Bansal, S.I. Lee, From local explanations to global understa nding with explainable AI for trees, Nat. Mach. Intell. 2 (1) (2020) 56-67.

E.F. El-Hashash, R.H. Ali Shiekh, A comparison of the Pearson, spearman rank and Kendall tau correlation coefficients using quantitative variables, Asian J. Probab. Stat 20 (3) (2022) 36-48.

I. Couso, O. Strauss, H. Saulnier, Kendall's rank correlation on quantized data:an interval-valued approach, Fuzzy Sets Syst 343 (2018) 50-64.

G.J. Sunley, D.J. Watson, High productivity methanol carbonylation catalysis using iridium, Catal. Today 58 (4) (2000) 293-307.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Machine learning for adsorption-related parameters prediction of electronic specialty gases: DFT-based dataset construction and balanced data augmentation

High-performance 19-channel monolithic CHA zeolite membranes for vapor-permeation dehydration of acetic acid

Steam reforming of acetic acid over Ni/biochar of low metal-loading: Involvement of biochar in tailoring reaction intermediates renders superior catalytic performance

Acetic acid- and furfural-based adaptive evolution of Saccharomyces cerevisiae strains for improving stress tolerance and lignocellulosic ethanol production

Immobilization of trophic anaerobic acetogen for semi-continuous syngas fermentation