Artificial Neural Network Surrogate Modelling for Predicting and Optimising CO2 Conversion to Methanol Under Uncertainty

Abstract

This study introduces a data-driven surrogate modelling framework that combines an artificial neural network (ANN) with particle swarm optimisation (PSO) and a genetic algorithm (GA) to optimise methanol production under uncertain conditions. A steady-state Aspen Plus model was developed and converted into dynamic mode by applying ± 5% uncertainty across 12 key process variables, generating 3880 data points that reflect realistic operational variability. The ANN model was trained and validated on the samples, achieving predictive accuracy (R ² = 0.988, RMSE = 28.59) on unseen test data. Key features of the work include the use of the ANN as a surrogate model, its integration within PSO and GA optimisation frameworks and its application alongside Sobol and Fourier amplitude sensitivity test (FAST) methods to identify the most influential process variables affecting the methanol production rate. The proposed framework resulted in performance improvements, with PSO achieving an increase of 38.63% and GA 33.14% in methanol production. Cross-validation with the Aspen Plus model confirmed the reliability of the optimised operating conditions, with relative errors ranging from 0.07% to 2.15%. Overall, the study demonstrates the effectiveness of integrating surrogate modelling with intelligent optimisation techniques to improve the efficiency and robustness of methanol production processes under uncertainty.

Keywords

artificial neural networks (ANN) / CO2 hydrogenation / genetic algorithm / methanol production / particle swarm optimisation / surrogate modelling

Funding

The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University, Arar, KSA for funding this research work through the project number “NBU-FFR-2025-1243-07”.

Conflicts of Interest

The authors declare no conflicts of interest.

Data Availability Statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

References

[1] G. Bozzano and F. Manenti, “Efficient Methanol Synthesis: Perspectives, Technologies and Optimization Strategies,” Progress in Energy and Combustion Science 56 (2016): 71-105, https://doi.org/10.1016/j.pecs.2016.06.001.

[2] X. Fang, Y. Men, F. Wu, et al., Moderate-Pressure Conversion of H2 and CO2 to Methanol via Adsorption Enhanced Hydrogenation,” International Journal of Hydrogen Energy 44, no. 39 (2019): 21913-21925, https://doi.org/10.1016/j.ijhydene.2019.06.176.

[3] C. Song, Q. Liu, S. Deng, H. Li, and Y. Kitamura, “Cryogenic-Based CO2 Capture Technologies: State-of-the-Art Developments and Current Challenges,” Renewable and Sustainable Energy Reviews 101 (2019): 265-278, https://doi.org/10.1016/j.rser.2018.11.018.

[4] É. S. Van-Dal and C. Bouallou, “Design and Simulation of a Methanol Production Plant From CO2 Hydrogenation,” Journal of Cleaner Production 57 (2013): 38-45, https://doi.org/10.1016/j.jclepro.2013.06.008.

[5] M. Yousaf, A. Mahmood, A. Elkamel, M. Rizwan, and M. Zaman, “Techno-Economic Analysis of Integrated Hydrogen and Methanol Production Process by CO2 Hydrogenation,” International Journal of Greenhouse Gas Control 115 (2022): 103615, https://doi.org/10.1016/j.ijggc.2022.103615.

[6] J. Nyári, D. Izbassarov, Á. I. Toldy, V. Vuorinen, and A. Santasalo-Aarnio, “Choice of the Kinetic Model Significantly Affects the Outcome of Techno-Economic Assessments of CO2-Based Methanol Synthesis,” Energy Conversion and Management 271 (2022): 116200, https://doi.org/10.1016/j.enconman.2022.116200.

[7] M. Zulkefal, A. Ayub, and H. Sethi, “Exergy Analysis of Methanol Production Plant From Hydrogenation of Carbon Dioxide,” Materials Proceedings 17, no. 1 (2024): 15, https://doi.org/10.3390/materproc2024017015.

[8] G. T. Whiting, S. A. Kondrat, C. Hammond, et al., Methyl Formate Formation From Methanol Oxidation Using Supported Gold-Palladium Nanoparticles,” ACS Catalysis 5, no. 2 (2015): 637-644, https://doi.org/10.1021/cs501728r.

[9] C.-L. Chiang and K.-S. Lin, “Preparation and Characterization of CuOAl2O3 Catalyst for Dimethyl Ether Production via Methanol Dehydration,” International Journal of Hydrogen Energy 42, no. 37 (2017): 23526-23538, https://doi.org/10.1016/j.ijhydene.2017.01.063.

[10] A. Sánchez, L. M. Gil, and M. Martín , “Sustainable DMC Production From CO2 and Renewable Ammonia and Methanol,” Journal of CO2 Utilization 33 (2019): 521-531, https://doi.org/10.1016/j.jcou.2019.08.010.

[11] Q. Qian, J. Zhang, M. Cui, and B. Han, “Synthesis of Acetic Acid via Methanol Hydrocarboxylation With CO2 and H2,” Nature Communications 7, no. 1 (2016): 11481, https://doi.org/10.1038/ncomms11481.

[12] H. He, T. Wang, and S. Zhu, “Continuous Production of Biodiesel Fuel From Vegetable Oil Using Supercritical Methanol Process,” Fuel 86, no. 3 (2007): 442-447, https://doi.org/10.1016/j.fuel.2006.07.035.

[13] E. Chornet, B. Valsecchi, Y. Avila, B. Nguyen, and J.-M. Lavoie , Production of Ethanol from Methanol (Google Patents, 2011).

[14] G. A. Olah, A. Goeppert, and G. K. S. Prakash, “Chemical Recycling of Carbon Dioxide to Methanol and Dimethyl Ether: From Greenhouse Gas to Renewable, Environmentally Carbon Neutral Fuels and Synthetic Hydrocarbons,” Journal of Organic Chemistry 74, no. 2 (2009): 487-498, https://doi.org/10.1021/jo801260f.

[15] O.-S. Joo, K. D. Jung, I. Moon, et al., Carbon Dioxide Hydrogenation to Form Methanol via a Reverse-Water-Gas-Shift Reaction (The CAMERE Process),” Industrial & Engineering Chemistry Research 38, no. 5 (1999): 1808-1812, https://doi.org/10.1021/ie9806848.

[16] D. Mignard, M. Sahibzada, J. M. Duthie, and H. W. Whittington, “Methanol Synthesis From Flue-Gas CO2 and Renewable Electricity: A Feasibility Study,” International Journal of Hydrogen Energy 28, no. 4 (2003): 455-464, https://doi.org/10.1016/s0360-3199(02)00082-4.

[17] D. Mignard and C. Pritchard, “Processes for the Synthesis of Liquid Fuels From CO2 and Marine Energy,” Chemical Engineering Research and Design 84, no. 9 (2006): 828-836, https://doi.org/10.1205/cherd.05204.

[18] L. G. J. van der Ham, H. van den Berg, A. Benneker, G. Simmelink, J. Timmer, and S. van Weerden, “Hydrogenation of Carbon Dioxide for Methanol Production,” Chemical Engineering Transactions 29 (2012), https://doi.org/10.3303/CET1229031.

[19] C. Su, H. Wei, Z. Wang, H. Ayed, A. Mouldi, and A. A. Shayesteh, “Economic Accounting and High-Tech Strategy for Sustainable Production: A Case Study of Methanol Production From CO2 Hydrogenation,” International Journal of Hydrogen Energy 47, no. 62 (2022): 25929-25944, https://doi.org/10.1016/j.ijhydene.2022.01.124.

[20] N. Von der Assen, J. Jung, and A. Bardow, “Life-Cycle Assessment of Carbon Dioxide Capture and Utilization: Avoiding the Pitfalls,” Energy & Environmental Science 6, no. 9 (2013): 2721-2734, https://doi.org/10.1039/c3ee41151f.

[21] I. Ahmad, A. Sana, M. Kano, et al., Machine Learning Applications in Biofuels’ Life Cycle: Soil, Feedstock, Production, Consumption, and Emissions,” Energies 14, no. 16 (2021): 5072, https://doi.org/10.3390/en14165072.

[22] Y. Xie, M. Ebad Sichani, J. E. Padgett, and R. DesRoches, “The Promise of Implementing Machine Learning in Earthquake Engineering: A State-of-the-Art Review,” Earthquake Spectra 36, no. 4 (2020): 1769-1801, https://doi.org/10.1177/8755293020919419.

[23] U. K. Jadoon, I. Ahmad, T. Noor, M. Kano, H. Caliskan, and M. Ahsan, “An Intelligent Sensing System for Estimation of Efficiency of Carbon-Capturing Unit in a Cement Plant,” Journal of Cleaner Production 377 (2022): 134359, https://doi.org/10.1016/j.jclepro.2022.134359.

[24] A. Samad, H. Saghir, A. Musawwir, and M. Zulkefal, “An Intelligent System for Predicting the Methanol Conversion Rate From the Direct Hydrogenation of CO2 Under Uncertainty,” Materials Proceedings 17, no. 1 (2024): 3, https://doi.org/10.3390/materproc2024017003.

[25] I. Ahmad, A. Ayub, U. Ibrahim, M. K. Khattak, and M. Kano, “Data-Based Sensing and Stochastic Analysis of Biodiesel Production Process,” Energies 12, no. 1 (2018): 63, https://doi.org/10.3390/en12010063.

[26] I. Ahmad, M. Kano, S. Hasebe, H. Kitada, and N. Murata, “Gray-Box Modeling for Prediction and Control of Molten Steel Temperature in Tundish,” Journal of Process Control 24, no. 4 (2014): 375-382, https://doi.org/10.1016/j.jprocont.2014.01.018.

[27] Z. Ge, Z. Song, S. X. Ding, and B. Huang, “Data Mining and Analytics in the Process Industry: The Role of Machine Learning,” IEEE Access 5 (2017): 20590-20616, https://doi.org/10.1109/access.2017.2756872.

[28] R. De, A. Rajan, K. Govindaraj, et al. , System and Method for Industrial Process Automation Controller Farm With Flexible Redundancy Schema and Dynamic Resource Management Through Machine Learning (U.S. Patent 10,416,630, 2019).

[29] A. Ayub, M. Zulkefal, and H. Sethi, “Artificial-Intelligence-Assisted Investigation of Quality and Yield of Cumene Production,” Materials Proceedings 17, no. 1 (2024): 10, https://doi.org/10.3390/materproc2024017010.

[30] K. N. Bhanu, H. J. Jasmine, and H. S. Mahadevaswamy , Machine Learning Implementation in IoT Based Intelligent System for Agriculture (IEEE, 2020), 1-5.

[31] M. A. Khademi, J. Shariati, M. Bahmani, and S. Talati, “Investigating the Capability of Artificial Neural Network to Modify and Optimize an Industrial Methanol Production Process,” Petroleum & Coal 58, no. 4 (2016): 465-475, https://vurup.sk/download/2944/2983?_gl=1*jk4f04*_up*MQ..*_ga*OTg0ODE1NjMzLjE3NzU3OTk1OTU.*_ga_T958WW7JL5*czE3NzU3OTk1OTIkbzEkZzAkdDE3NzU3OTk1OTIkajYwJGwwJGgw.

[32] D. Chuquin-Vasco, F. Parra, N. Chuquin-Vasco, J. Chuquin-Vasco, and V. Lo-Iacono-Ferreira, “Prediction of Methanol Production in a Carbon Dioxide Hydrogenation Plant Using Neural Networks,” Energies 14, no. 13 (2021): 3965, https://doi.org/10.3390/en14133965.

[33] P. Vanjari, R. Kamesh, and K. Y. Rani, “Machine Learning Models Representing Catalytic Activity for Direct Catalytic CO2 Hydrogenation to Methanol,” Materials Today: Proceedings 72 (2023): 524-532, https://doi.org/10.1016/j.matpr.2022.11.265.

[34] G. Zahedi, A. Elkamel, A. Lohi, A. Jahanmiri, and M. R. Rahimpor, “Hybrid Artificial Neural Network-First Principle Model Formulation for the Unsteady State Simulation and Analysis of a Packed Bed Reactor for CO2 Hydrogenation to Methanol,” Chemical Engineering Journal 115, no. 1-2 (2005): 113-120, https://doi.org/10.1016/j.cej.2005.08.018.

[35] E. G. Aklilu and T. Bounahmidi, “Machine Learning Applications in Catalytic Hydrogenation of Carbon Dioxide to Methanol: A Comprehensive Review,” International Journal of Hydrogen Energy 61 (2024): 578-602, https://doi.org/10.1016/j.ijhydene.2024.02.309.

[36] S. Zendehboudi, N. Rezaei, and A. Lohi, “Applications of Hybrid Models in Chemical, Petroleum, and Energy Systems: A Systematic Review,” Applied Energy 228 (2018): 2539-2566, https://doi.org/10.1016/j.apenergy.2018.06.051.

[37] A. M. Schweidtmann, E. Esche, A. Fischer, et al., Machine Learning in Chemical Engineering: A Perspective,” Chemie Ingenieur Technik 93, no. 12 (2021): 2029-2039, https://doi.org/10.1002/cite.202100083.

[38] B. Hu, C. Guild, and S. L. Suib, “Thermal, Electrochemical, and Photochemical Conversion of CO2 to Fuels and Value-Added Products,” Journal of CO2 Utilization 1 (2013): 18-27, https://doi.org/10.1016/j.jcou.2013.03.004.

[39] K. M. V. Bussche and G. F. Froment, “A Steady-State Kinetic Model for Methanol Synthesis and the Water Gas Shift Reaction on a Commercial Cu/ZnO/Al2O3 Catalyst,” Journal of Catalysis 161, no. 1 (1996): 1-10, https://doi.org/10.1006/jcat.1996.0156.

[40] A. Al-Shathr, Z. M. Shakor, H. S. Majdi, A. A. AbdulRazak, and T. M. Albayati, “Comparison Between Artificial Neural Network and Rigorous Mathematical Model in Simulation of Industrial Heavy Naphtha Reforming Process,” Catalysts 11, no. 9 (2021): 1034, https://doi.org/10.3390/catal11091034.

[41] A. Bhardwaj, A. S. Ahluwalia, K. K. Pant, and S. Upadhyayula, “A Principal Component Analysis Assisted Machine Learning Modeling and Validation of Methanol Formation Over Cu-Based Catalysts in Direct CO2 Hydrogenation,” Separation and Purification Technology 324 (2023): 124576, https://doi.org/10.1016/j.seppur.2023.124576.

[42] P. Borisut and A. Nuchitprasittichai, “Process Configuration Studies of Methanol Production via Carbon Dioxide Hydrogenation: Process Simulation-Based Optimization Using Artificial Neural Networks,” Energies 13, no. 24 (2020): 6608, https://doi.org/10.3390/en13246608.

[43] Z. Zhang, D.-N. Vo, T. B. H. Nguyen, J. Sun, and C.-H. Lee, “Advanced Process Integration and Machine Learning-Based Optimization to Enhance Techno-Economic-Environmental Performance of CO2 Capture and Conversion to Methanol,” Energy 293 (2024): 130758, https://doi.org/10.1016/j.energy.2024.130758.

[44] V. D. Nguyen, J. Chang, S.-H. Hong, and C.-H. Lee, “Performance and ANN-based Optimization of an Advanced Process for Wet CO2-to-Methanol Using a Catalytic Fluidized Bed Reactor Integrated With Separators,” Fuel 343 (2023): 128045, https://doi.org/10.1016/j.fuel.2023.128045.

[45] A. Samad, I. Ahmad, M. Kano, and H. Caliskan, “Prediction and Optimization of Exergetic Efficiency of Reactive Units of a Petroleum Refinery Under Uncertainty Through Artificial Neural Network-Based Surrogate Modeling,” Process Safety and Environmental Protection 177 (2023): 1403-1414, https://doi.org/10.1016/j.psep.2023.07.046.

[46] B. Iooss and P. Lemaître, “A Review on Global Sensitivity Analysis Methods,” in Uncertainty Management in Simulation-Optimization of Complex Systems: Algorithms and Applications (Springer, 2015), 101-122.

[47] H. Q. Chohan, I. Ahmad, N. Mohammad, D. Manca, and H. Caliskan, “An Integrated Approach of Artificial Neural Networks and Polynomial Chaos Expansion for Prediction and Analysis of Yield and Environmental Impact of Oil Shale Retorting Process Under Uncertainty,” Fuel 329 (2022): 125351, https://doi.org/10.1016/j.fuel.2022.125351.

[48] I. Ahmad, A. Ayub, M. H. Rashid, F. Ansari, and N. Mohammad , Sensitivity Analysis of Entrained Flow Coal Gasification Process Through Fourier Amplitude Sensitivity Test (FAST) and Sobol Techniques (IEEE, 2018), 79-84.

[49] M. Clerc, “The Swarm and the Queen: Towards a Deterministic and Adaptive Particle Swarm Optimization,” in Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406) 3 (IEEE, 1999), 1951-1957, https://doi.org/10.1109/cec.1999.785513.

[50] D. Wang, D. Tan, and L. Liu, “Particle Swarm Optimization Algorithm: An Overview,” Soft Computing 22, no. 2 (2018): 387-408, https://doi.org/10.1007/s00500-016-2474-6.

[51] K. Khan and A. Sahai, “A Comparison of BA, GA, PSO, BP and LM for Training Feed Forward Neural Networks in e-Learning Context,” International Journal of Intelligent Systems and Applications 4, no. 7 (2012): 23-29, https://doi.org/10.5815/ijisa.2012.07.03.

[52] M. Shariati, M. S. Mafipour, P. Mehrabi, et al., Application of a Hybrid Artificial Neural Network-Particle Swarm Optimization (ANN-PSO) Model in Behavior Prediction of Channel Shear Connectors Embedded in Normal and High-Strength Concrete,” Applied Sciences 9, no. 24 (2019): 5534, https://doi.org/10.3390/app9245534.

[53] J. H. Holland , Adaptation in Natural and Artificial Systems (University of Michigan Press, 1975).

[54] J. S. Khan, I. Ahmad, U. K. Jadoon, et al., Artificial Intelligence Based Prediction of Optimum Operating Conditions of a Plate and Fin Heat Exchanger Under Uncertainty: A Gray-Box Approach,” International Journal of Heat and Mass Transfer 217 (2023): 124653, https://doi.org/10.1016/j.ijheatmasstransfer.2023.124653.

[55] S. N. Sivanandam, S. Sumathi, and S. Deepa , Introduction to Genetic Algorithms (Springer Science & Business Media, 2007).

[56] A. A. Kiss, J. J. Pragt, H. J. Vos, G. Bargeman, and M. T. De Groot, “Novel Efficient Process for Methanol Synthesis by CO2 Hydrogenation,” Chemical Engineering Journal 284 (2016): 260-269, https://doi.org/10.1016/j.cej.2015.08.101.

[57] J. Nyári, M. Magdeldin, M. Larmi, M. Järvinen, and A. Santasalo-Aarnio, “Techno-Economic Barriers of an Industrial-Scale Methanol CCU-Plant,” Journal of CO2 Utilization 39 (2020): 101166, https://doi.org/10.1016/j.jcou.2020.101166.

[58] M. Pérez-Fortes, J. C. Schöneberger, A. K. Boulamanti, and E. J. A. E. Tzimas, “Methanol Synthesis Using Captured CO2 as Raw Material: Techno-Economic and Environmental Assessment,” Applied Energy 161 (2016): 718-732, https://doi.org/10.1016/j.apenergy.2015.07.067.

[59] O. Y. Abdelaziz, W. M. Hosny, M. A. Gadalla, F. H. Ashour, I. A. Ashour, and C. P. Hulteberg, “Novel Process Technologies for Conversion of Carbon Dioxide From Industrial Flue Gas Streams Into Methanol,” Journal of CO2 Utilization 21 (2017): 52-63, https://doi.org/10.1016/j.jcou.2017.06.018.

[60] S. Szima and C. C. Cormos, “Improving Methanol Synthesis From Carbon-Free H2 and Captured CO2: A Techno-Economic and Environmental Evaluation,” Journal of CO2 Utilization 24 (2018): 555-563, https://doi.org/10.1016/j.jcou.2018.02.007.