An interpretable ensemble learning framework based on Bayesian optimization for the optimal design of ammonia decomposition catalysts

Wang Zhao; Guan Jingsong; Hu Jun; Guo Qiwen; Zhang Dawei; Yang Qingchun

doi:null

Your Location：

Home >

Browse articles >

An interpretable ensemble learning framework based on Bayesian optimization for the optimal design of ammonia decomposition catalysts

Updated：2026-08-24

- An interpretable ensemble learning framework based on Bayesian optimization for the optimal design of ammonia decomposition catalysts
- An interpretable ensemble learning framework based on Bayesian optimization for the optimal design of ammonia decomposition catalysts
- 中国化学工程学报（英文） 2026年94卷第6期页码：156-171
- Affiliations：
  
  School of Chemistry and Chemical Engineering, Hefei University of Technology, Hefei 230009, China
- Author bio：
  
  Corresponding author. E-mail address: ceqcyang@hfut.edu.cn(Q. Yang)
- Funds：
  
  The authors are grateful for financial support from the Natural Science Foundation of Anhui Province(2508085MB029);National Natural Science Foundation of China(22108052);High-end chemicals and cutting-edge new materials Technology Innovation Center of Hefei(HCHC202309)
- DOI：
  中图分类号：
- 收稿：2025-09-09，
  
  修回：2026-01-07，
  
  录用：2026-01-08，
  
  网络首发：2026-02-19，
  
  纸质出版：2026-06
- Accepted：
Scan QR Code
Wang Zhao, Guan Jingsong, Hu Jun, 等. An interpretable ensemble learning framework based on Bayesian optimization for the optimal design of ammonia decomposition catalysts[J]. 中国化学工程学报（英文）, 2026,94(6):156-171.

Wang Zhao, Guan Jingsong, Hu Jun, et al. An interpretable ensemble learning framework based on Bayesian optimization for the optimal design of ammonia decomposition catalysts[J]. Chinese Journal of Chemical Engineering, 2026, 94(6): 156-171.
Wang Zhao, Guan Jingsong, Hu Jun, 等. An interpretable ensemble learning framework based on Bayesian optimization for the optimal design of ammonia decomposition catalysts[J]. 中国化学工程学报（英文）, 2026,94(6):156-171. DOI：

Wang Zhao, Guan Jingsong, Hu Jun, et al. An interpretable ensemble learning framework based on Bayesian optimization for the optimal design of ammonia decomposition catalysts[J]. Chinese Journal of Chemical Engineering, 2026, 94(6): 156-171. DOI：

摘要

Abstract

Green ammonia offers a viable hydrogen carrier due to its high energy density

established infrastructure

and cost-effectiveness. However

the decomposition process for hydrogen production relies on highly efficient catalysts. This study aims to overcome experimental limitations in catalyst design by developing a Bayesian optimization-based interpretab

le ensemble learning framework for multiobjective optimization of ammonia decomposition catalysts. A dataset covering the intrinsic properties of catalysts

preparation parameters

and reaction conditions for ammonia decomposition is constructed to develop six various ensemble learning models. The hyperparameters of these models are automatically and optimally configured using the Bayesian optimization-based Optuna method. The results demonstrate the effectiveness of this hyperparameter automatic optimization strategy

as the average

across the six models improved by 0.086 compared to the pre-optimization values. In particular

the CatBoost model emerges as the optimal model with test

＞0.9188. The Shapley additive explanations reveal the regulatory mechanism of performance by reaction conditions (with a contribution of 48.14%

where temperature and space velocity are dominant) and intrinsic characteristics of the catalyst (33.79%). The partial dependence plots analyses are further conducted to expound the effect of these key parameters on the catalytic performance. The optimal model is integrated with the reference vector guided evolutionary algorithm to minimize the total metal content while maximizing the space-time yield of hydrogen in ammonia decomposition catalysts. Three newly optimized catalysts demonstrate superior performance

offering an improved efficiency-cost balance compared to existing catalysts. External validation with unseen data further confirms the model's robustness

with prediction errors ＜5.06%.

关键词

Keywords

references

S.C. Sun, Q.Q. Jiang, D.Y. Zhao, T.T. Cao, H. Sha, C.K. Zhang, H.T. Song, Z.J. Da, Ammonia as hydrogen carrier: advances in ammonia decomposition catalysts for promising hydrogen production, Renew. Sustain. Energy Rev. 169 (2022) 112918.

J.E. Lee, J. Lee, H. Jeong, Y.K. Park, B.S. Kim, Catalytic ammonia decomposition to produce hydrogen: a mini-review, Chem. Eng. J. 475 (2023) 146108.

T. Han, L. Wei, S.H. Xie, Y.X. Liu, H.X. Dai, J.G. Deng, Catalyst design for ammonia decomposition: an overview, Ind. Chem. Mater. 3 (3) (2025) 311-331.

Y. Zhao, B.P. Setzler, J.H. Wang, J. Nash, T. Wang, B.J. Xu, Y.S. Yan, An efficient direct ammonia fuel cell for affordable carbon-neutral transportation, Joule 3 (10) (2019) 2472-2484.

M. Perr on, K. Krawczyk, M. Młotek, Plasma-catalytic decomposition of highly concentrated ammonia for a chemical hydrogen storage, Chem. Eng. Sci. 314 (2025) 121815.

H.H. Fang, S. Wu, T. Ayvali, J.W. Zheng, J. Fellowes, P.L. Ho, K.C. Leung, A. Large, G. Held, R. Kato, K. Suenaga, Y.I.A. Reyes, H.V. Thang, H.T. Chen, S.C.E. Tsang, Dispersed surface Ru ensembles on MgO(111) for catalytic ammonia decomposition, Nat. Commun. 14 (2023) 647.

X.C. Wang, X.T. Zhao, G.Z. Zhou, T. Chen, Q. Chen, N. Alonso-Vante, Z. Huang, Y.R. Zhang, H. Lin, Electrically driven gaseous ammonia decomposition for hydrogen production over SiC-mediated catalyst without external heating, ACS Catal. 15 (3) (2025) 2389-2401.

M.Y. Yang, U. Raucci, M. Parrinello, Reactant-induced dynamics of lithium imide surfaces during the ammonia decomposition process, Nat. Catal. 6 (9) (2023) 829-836.

C.Z. Zheng, B. Guan, J.F. Guo, T.X. Su, J.F. Zhou, J.Y. Chen, Y.Y. Zhang, Y.H. Yuan, W.K. Xie, N.X. Zhou, Z. Huang, Research status, optimization strategies, and future prospects of ammonia decomposition catalysts for CO x -free hydrogen, Ind. Eng. Chem. Res. 62 (29) (2023) 11305-11336.

H.W. Liu, R.R. Zhang, S.B. Liu, G.Z. Liu, CeO 2 /Ni inverse catalyst as a highly active and stable Ru-free catalyst for ammonia decomposition, ACS Catal. 14 (13) (2024) 9927-9939.

K. Xu, Y.Y. Zhang, W.W. Wang, M. Peng, J.C . Liu, C. Ma, Y.W. Zhang, C.J. Jia, D. Ma, C.H. Yan, Single-atom barium promoter enormously enhanced non-noble metal catalyst for ammonia decomposition, Angew. Chem. Int. Ed. 64 (4) (2025) e202416195.

R.J. Bao, Z. Wang, Q.W. Guo, X.Y. Wu, Q.C. Yang, Bio-digital catalyst design:generative deep learning for multi-objective optimization and chemical insights in CO 2 methanation, ACS Catal. 15 (15) (2025) 12691-12714.

Q.C. Yang, D.W. Rong, Q.W. Guo, R.J. Bao, D.W. Zhang, Ensemble learning-driven multi-objective optimization of the co-pyrolysis process of biomass and coal for high economic and environmental performance, Chin. J. Chem. Eng. 84 (2025) 23-34.

Q.C. Yang, L. Zhao, Q.W. Guo, Z. Wang, D.W. Zhang, A hybrid encoding-enhanced machine learning and multioptimization framework for the optimal catalyst design of the methane-to-ethylene process, Ind. Eng. Chem. Res. 64 (29) (2025) 14512-14533.

H.T. Cao, Y. Li, C.L. Chang, X.P. Zhang, A. Yang, W.F. Shen, A deep learning hybrid framework combining an efficient evolutionary algorithm for complex many-objective optimization of sustainable triple CO 2 feed methanol production, ACS Sustainable Chem. Eng. 12 (17) (2024) 6682-6696.

C. Bozal-Ginesta, S. Pablo-García, C. Choi, A. Tarancón, A. Aspuru-Guzik, Developing machine learning for heterogeneous catalysis with experimental and computational data, Nat. Rev. Chem 9 (9) (2025) 601-61 6.

A.F. Zahrt, J.J. Henle, B.T. Rose, Y. Wang, W.T. Darrow, S.E. Denmark, Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning, Science 363 (6424) (2019) eaau5631.

A. Yang, S.R. Sun, Y. Su, Z.Y. Kong, J.Z. Ren, W.F. Shen, Insight to the prediction of CO 2 solubility in ionic liquids based on the interpretable machine learning model, Chem. Eng. Sci. 297 (2024) 120266.

W.J. Guo, A. Shafizadeh, H. Shahbeik, S. Rafiee, S. Motamedi, S.A. Ghafarian Nia, M.H. Nadian, F.H. Li, J.T. Pan, M. Tabatabaei, M. Aghbashlo, Machine learning for predicting catalytic ammonia decomposition: an approach for catalyst design and performance prediction, J. Energy Storage 89 (2024) 111688.

X.M. Chen, A. Shafizadeh, H. Shahbeik, M.H. Nadian, M. Golvirdizadeh, W.X. Peng, S.S. Lam, M. Tabatabaei, M. Aghbashlo, Enhanced bio-oil production from biomass catalytic pyrolysis using machine learning, Renew. Sustain. Energy Rev. 209 (2025) 115099.

S. Azadvar, O. Tavakoli, Data-driven interpretation, comparison and optimization of hydrogen production from supercritical water gasification of biomass and polymer waste: applying ensemble and differential evolution in machine learning algorithms, Int. J. Hydrogen Energy 85 (2024) 511-525.

J. Kumar, G. Selvan, R. Saranya, R.K. Gupta, M. Anusuya, G. Kalra, Optimising silver-enhanced BiFeO 3 nanoparticle catalysts using random forests and ge netic algorithms, in: 2024 International Conference on Distributed Systems,Computer Networks and Cybersecurity (ICDSCNC). Bengaluru, India, IEEE, 2025, pp. 1-6.

R.Y. Zuo, Y. Li, S.A. Wei, Z.M. Li, T. Shi, W.L. Du, W.F. Shen, Calibration-augmented and mechanism-driven deep learning hybrid framework for modeling actual distillation processes, Ind. Eng. Chem. Res. 64 (7) (2025) 3856-3870.

J. Zhang, Q. Wang, Y. Su, S.M. Jin, J.Z. Ren, M. Eden, W.F. Shen, An accurate and interpretable deep learning model for environmental properties prediction using hybrid molecular representations, AIChE J. 68 (6) (2022) e17634.

N.S. Lai, Y.S. Tew, X.L. Zhong, J. Yin, J.L. Li, B.H. Yan, X.N. Wang, Artificial intelligence (AI) workflow for catalyst design and optimization, Ind. Eng. Chem. Res. 62 (43) (2023) 17835-17848.

D.W. Rong, Z. Wang, Q.W. Guo, R.J. Bao, Q.C. Yang, An auto-configurable and interpretable ensemble learning framework for optimal catalyst design of green methanol production via Bayesian optimization, J. Clean. Prod. 488 (2025) 144666.

S.H. Nan, Z.M. Li, S.M. Jin, W.L. Du, W.F. Shen, Machine learning-based multimodal and multi-granularity feature fusion framework for accurate prediction of molecular properties, Ind. Eng. Chem. Res. 64 (5) (2025) 3045-3056.

Q.C. Yang, R.J. Bao, D.W. Rong, J.X. Xiao, J.L. Zhou, L. Zhao, D.W. Zhan g, Interpretable machine learning for accelerating reverse design and optimizing CO 2 methanation catalysts with high activity at low temperatures, Ind. Eng. Chem. Res. 63 (33) (2024) 14727-14747.

Z.H. Jaffari, A. Abbas, S.M. Lam, S. Park, K. Chon, E.S. Kim, K.H. Cho, Machine learning approaches to predict the photocatalytic performance of bismuth ferrite-based materials in the removal of malachite green, J. Hazard. Mater. 442 (2023) 130031.

S.Y. Jiang, W. Xu, Q. Xia, M. Yi, Y.R. Zhou, J.W. Shang, X.W. Cheng, Application of machine learning in the study of cobalt-based oxide catalysts for antibiotic degradation: an innovative reverse synthesis strategy, J. Hazard. Mater. 471 (2024) 134309.

C. Martínez-Alonso, V. Vassilev-Galindo, B.M. Comer, F. Abild-Pedersen, K.T. Winther, J. Llorca, Application of machine learning to discover new intermetallic catalysts for the hydrogen evolution and the oxygen reduction reactions, Catal. Sci. Technol. 14 (13) (2024) 3784-3799.

M.F. Tahir, M.Z. Yousaf, A. Tzes, M.S. El Moursi, T.H.M. El-Fouly, Enhanced solar photovoltaic power prediction using diverse machine learning algorithms with hyperparameter optimization, Renew. Sustain. Energy Rev. 200 (2024) 114581.

L. Salt, M. Gallagher, Hyperparameter optimisation with practical interpretability and explanation methods in probabilistic curriculum learning, arXiv:2504.06683 (2025), https://doi.org/10.48550/arXiv.2504.06683.

T. Terlouw, C. Bauer, R. McKenna, M. Mazzotti, Large-scale hydrogen production via water electrolysis: a techno-economic and environmental assessment, Energy Environ. Sci. 15 (9) (2022) 3583-3602.

Y.X. Wu, A.C.Y. Yuen, C.M. Mo, Q. Chen, X.Y. Huang, An advanced BPNN/RVEA coupled control strategy for novel immersed liquid cooling battery thermal management system, J. Energy Storage 125 (2025) 117008.

B. Kang, Z.L. Chang, R.D. Zhang, Z.G. Shen, K. Wang, X.N. Guo, H.T. Wu, D.Q. Li, D.X. Liu, Y. Wei, J.B. Jia, Z.J. Wang, Synergistic catalysis of CoN sites and Co nanoparticles for efficient CO x-free hydrogen production from ammonia decomposition, Fuel 396 (2025) 135311.

H.J. Lee, E.D. Park, Ammonia decomposition over Ru/SiO 2 catalysts, Catalysts 12 (10) (2022) 1203.

Z. Zhang, M.H. Yu, M.Q. Shen, W. Li, G.R. Shen, Promoting effect of alkaline earth metals on Ni/CeO 2 catalysts for ammonia decomposition reaction, Mol. Catal. 578 (2025) 115016.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Preparation of anodic catalysts via in situ exsolution of Pt nanoparticles for a methane oxidation enhanced SOEC process

The integration of artificial intelligence and high-throughput experiments: An innovative driving force in catalyst design

Performance improvement of ultra-low Pt proton exchange membrane fuel cell by catalyst layer structure optimization

Coupling effect of bifunctional ZnCe@SBA-15 catalyst in 1,3-butadiene production from bioethanol

Synergism of highly graphitic N-doped graphene-like carbon and Pt@PtCo core-shell structure for efficient oxygen reduction reaction