Iranian Journal of Chemical Engineering (IJChE)
Scientific Journal

Application of Artificial Neural Networks and Machine Learning in Syngas Production via Hydrocarbon Reforming

Articles in Press

Document Type : Review Article

Authors

Mohadeseh Zarei 1
Jamshid Khorshidi 2
Hamed Hemmati 1

1 Department of Chemical Engineering, Faculty of Chemical and Petroleum Engineering, University of Hormozgan, Bandar Abbas, Iran

2 Faculty Of Engineering, Department of Mechanical Engineering, University of Hormozgan, Bandar Abbas, Iran

10.22034/ijche.2026.599855.1612
Abstract
Hydrocarbon reforming processes are important routes for the production of synthesis gas and hydrogen. However, the complex interactions among operating conditions, reaction kinetics, transport phenomena, and catalyst properties make process prediction challenging. This review examines the applications of machine learning (ML) and artificial neural networks (ANNs) in the modeling, prediction, and optimization of hydrocarbon reforming processes, with emphasis on methane reforming. Studies employing ANN, Random Forest, Support Vector Machine, Gradient Boosting, XGBoost, and CatBoost were reviewed and compared based on statistical metrics, validation strategies, dataset size and quality, overfitting, and model generalizability. The results indicate that model performance depends on the reforming process, target output, data structure, and validation strategy, and no single algorithm is universally superior. Although MLP has shown better statistical performance than RBF in some dry methane reforming studies, independent test datasets may reveal limitations in ANN generalizability. Ensemble methods, including Random Forest, CatBoost, and Gradient Boosting, have demonstrated competitive performance, although the best model varies with the predicted output. Furthermore, SHAP and Partial Dependence Plots can identify influential factors such as reaction temperature, feed ratio, and metal loading. Overall, rigorous validation, independent testing, overfitting control, and interpretability are essential for reliable ML applications in reforming processes.

Keywords

Machine learning
Artificial neural networks
Hydrocarbon reforming
Dry methane reforming
Syngas production
Subjects
[1]   Kiani P, Rahimpour MR. Syngas production from natural gas by reforming process: Dry, steam, partial oxidation, tri, and autothermal.  Advances in Natural Gas: Formation, Processing, and Applications Volume 7: Natural Gas Products and Uses: Elsevier; 2024. p. 95-117.https://doi.org/10.1016/B978-0-443-19227-2.00002-2
[2]   Farsi M. Reforming process design and modeling: Steam, dry, and autothermal reforming.  Advances in synthesis gas: methods, technologies and applications: Elsevier; 2023. p. 123-40.https://doi.org/10.1016/B978-0-323-91879-4.00003-5
[3]   Saad M, Abdurahman N, Yunus RM, Kamil M, Awad OI. An Overview of Reforming Technologies and the Effect of Parameters on the Catalytic Performance of Mesoporous Silica/Alumina Supported Nickel Catalysts for Syngas Production by Methane Dry Reforming. Recent Innovations in Chemical Engineering (Formerly Recent Patents on Chemical Engineering). 2020;13(4):303-22.https://doi.org/10.2174/2405520413666200313130420
[4]   Boscherini M, Storione A, Minelli M, Miccio F, Doghieri F. New perspectives on catalytic hydrogen production by the reforming, partial oxidation and decomposition of methane and biogas. Energies. 2023;16(17):6375.https://doi.org/10.3390/en16176375
[5]   Filimonova A, Chichirov A, Chichirova N, Pechenkin A. Reforming of hydrocarbon fuel in electrochemical systems. Thermal Engineering. 2023;70(8):615-23.https://doi.org/10.1134/S0040601523080025
[6]   Kaydouh M-N, El Hassan N, Chalhoub E, Bukharin N, El Hassan M. A review of Computational Fluid Dynamics modeling of dry reforming of methane for improved catalyst and reactor design. Fuel. 2024;366:131290.https://doi.org/10.1016/j.fuel.2024.131290
[7]   Elserfy K, Farooqi AS, El-Adawy M, Hamdy M, Shahid MZ, Elserfy Z, et al. Heat transfer and reaction kinetics in porous reacting media for steam methane reforming: a critical review and thermodynamic analysis. Engineering Applications of Computational Fluid Mechanics. 2026;20(1):2628975.https://doi.org/10.1080/19942060.2026.2628975
[8]   Sedaghat MH, Rahimpour MR. Computational fluid dynamics simulation of natural gas reformers. Advances in Synthesis Gas: Methods, Technologies and Applications. 2023:103-21.https://doi.org/10.1016/B978-0-323-91879-4.00013-8
[9]   Chen Y, Liu X, Liu X, Lu H, Wang Z. Machine Learning Applications in Fuel Reforming for Hydrogen Production in Marine Propulsion Systems. Journal of Marine Science and Engineering. 2025;14(1):85.https://doi.org/10.3390/jmse14010085
[10]                       Yuan B, Zhu T, Han Y, Zhang X, Wang M, Li C. Deactivation mechanism and anti-deactivation measures of metal catalyst in the dry reforming of methane: a review. Atmosphere. 2023;14(5):770.https://doi.org/10.3390/atmos14050770
[11]                       Ge Z, Lu Q, Xia K, Feng B, Lin G, Zhang H. Structural evolution and coke deposition-driven deactivation mechanism of industrial-scale steam methane reforming catalysts. International Journal of Hydrogen Energy. 2025;185:152028.https://doi.org/10.1016/j.ijhydene.2025.152028
[12]                       Vellayappan K, Yue Y, Lim KH, Cao K, Tan JY, Cheng S, et al. Impacts of catalyst and process parameters on Ni-catalyzed methane dry reforming via interpretable machine learning. Applied Catalysis B: Environmental. 2023;330:122593.https://doi.org/10.1016/j.apcatb.2023.122593
[13]                       Liu Z, Tian W, Cui Z, Liu B. A universal microkinetic-machine learning bimetallic catalyst screening method for steam methane reforming. Separation and Purification Technology. 2023;311:123270.https://doi.org/10.1016/j.seppur.2023.123270
[14]                       Devasahayam S, Thella JS, Mohanty MK. Predicting methane dry reforming performance via multi-output machine learning: a comparative study of regression models. Energies. 2025;18(18):4807.https://doi.org/10.3390/en18184807
[15]                       Jafarizadeh A, Panjepour M, Emami MD. Advanced modelling and optimization of steam methane reforming: From CFD simulation to machine learning-Driven optimization. International Journal of Hydrogen Energy. 2024;96:1262-80.https://doi.org/10.1016/j.ijhydene.2024.11.352
[16]                       Coşgun A, Günay ME, Yıldırım R. Explainable machine learning analysis of tri-reforming of biogas for sustainable syngas production. International Journal of Hydrogen Energy. 2025;127:595-607.https://doi.org/10.1016/j.ijhydene.2025.04.213
[17]                       Huang J, Liang Z, Liu Y. Smart reforming for hydrogen production via machine learning. Chemical Engineering Science. 2025;304:120959.https://doi.org/10.1016/j.ces.2024.120959
[18]                       Cherbański R, Kotkowski T, Molga E. Hydrogen and syngas production from methane via thermochemical conversion: a mini review of artificial neural network applications. Chemical and Process Engineering: New Frontiers. 2026;47(2):e135-e.https://doi.org/10.24425/cpe.2026.158133
[19]                       Madhiarasan M, Louzazni M. Analysis of artificial neural network: architecture, types, and forecasting applications. Journal of Electrical and Computer Engineering. 2022;2022(1):5416722.https://doi.org/10.1155/2022/5416722
[20]                       Rahman MH, Biswas M. Modeling of dry reforming of methane using artificial neural networks. Hydrogen. 2024;5(4):800-18.https://doi.org/10.3390/hydrogen5040042
[21]                       Deng H, Guo Y. Artificial neural network model for the prediction of methane Bi-reforming products using CO2 and steam. Processes. 2022;10(6):1052.https://doi.org/10.3390/pr10061052
[22]                       Cherbański R, Kotkowski T, Murgrabia S, Molga E, Stankiewicz A. ANN-based prediction of equilibrium gas composition and carbon yield in methane pyrolysis and reforming methods. Reaction Chemistry & Engineering. 2026;11(3):691-706.https://doi.org/10.1039/d5re00322a
[23]                       Pizoń Z, Kimijima S, Brus G. Bridging equilibrium and kinetics prediction with a data-weighted neural network model of methane steam reforming. International Journal of Hydrogen Energy. 2025;175:151367.https://doi.org/10.1016/j.ijhydene.2025.151367
[24]                       Nabavi SR, Guo Z, Wang Z. Machine learning assisted surrogate modeling with multi objective optimization and decision making of a steam methane reforming reactor. Scientific Reports. 2026.https://doi.org/10.1038/s41598-026-64776-2
[25]                       Alotaibi FN, Berrouk AS, Saeed M. Optimization of yield and conversion rates in methane dry reforming using artificial neural networks and the multiobjective genetic algorithm. Industrial & Engineering Chemistry Research. 2023;62(42):17084-99.https://doi.org/10.1021/acs.iecr.3c01813
[26]                       Devasahayam S. Interpretable SHAP Analysis of Key Operating Parameters in Methane Dry Reforming. Energies. 2026;19(11):2618.https://doi.org/10.3390/en19112618
[27]                       de Souza PA, Muhammad Afzal R, Gomes Camacho F, Mahinpey N. Random forest regression for catalyst performance prediction and validation of tri‐reforming of methane (TRM). The Canadian Journal of Chemical Engineering. 2025.https://doi.org/10.1002/cjce.70215
[28]                       Elmaz F, Yücel Ö, Mutlu AY. Predictive modeling of the syngas production from methane dry reforming over cobalt catalyst with statistical and machine learning based approaches. International Journal of Advances in Engineering and Pure Sciences. 2020;32(1):8-14.https://doi.org/10.7240/jeps.558373
[29]                       Hossain MA, Ayodele BV, Cheng CK, Khan MR. Artificial neural network modeling of hydrogen-rich syngas production from methane dry reforming over novel Ni/CaFe2O4 catalysts. International Journal of Hydrogen Energy. 2016;41(26):11119-30.https://doi.org/10.1016/j.ijhydene.2016.04.034
[30]                       Lee J, Hong S, Cho H, Lyu B, Kim M, Kim J, et al. Machine learning-based energy optimization for on-site SMR hydrogen production. Energy Conversion and Management. 2021;244:114438.https://doi.org/10.1016/j.enconman.2021.114438
[31]                       Nkulikiyinka P, Yan Y, Güleç F, Manovic V, Clough PT. Prediction of sorption enhanced steam methane reforming products from machine learning based soft-sensor models. Energy and AI. 2020;2:100037.https://doi.org/10.1016/j.egyai.2020.100037
[32]                       Bishnu SK, Alnouri SY, Al Mohannadi DM. Stochastic algorithm-based optimization using artificial intelligence/machine learning models for sorption enhanced steam methane reformer reactor. Computers & Chemical Engineering. 2025;196:109060.https://doi.org/10.1016/j.compchemeng.2025.109060
[33]                       Adeniyi AG, Ighalo JO, Marques G. Utilisation of machine learning algorithms for the prediction of syngas composition from biomass bio-oil steam reforming. International Journal of Sustainable Energy. 2021;40(4):310-25.https://doi.org/10.1080/14786451.2020.1803862
[34]                       Wang L, Li H, Du C, Hong W. Optimizing hydrogen yield in sorption-enhanced steam methane reforming: A novel framework integrating chemical reaction model, ensemble learning method, and whale optimization algorithm. Journal of the Energy Institute. 2024;114:101649.https://doi.org/10.1016/j.joei.2024.101649
 
Iranian Journal of Chemical Engineering (IJChE)

Articles in Press, Accepted Manuscript
Available Online from 26 September 2026

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us