Parametric analysis of CO2 hydrogenation via Fischer-Tropsch synthesis - A review based on machine learning for quantitative assessment

Aug 6, 2026

Upload by Finn

This review examines how parametric factors influence conversion and selectivity during CO2 hydrogenation via Fischer-Tropsch (FT) synthesis using iron-based catalysts, enabling quantitative evaluation. Collected literature data are compiled as a training dataset for artificial neural networks (ANNs) implemented in TensorFlow, and three parameter categories—operational, catalyst informatics, and mass transfer—are used to estimate impacts on CO2 conversions and selectivity. Literature kinetic power expressions are compared, and the best-fitting model avoids arbitrary assumptions of partial-pressure power values. Binary-parameter sets are analyzed to reveal evolving conversion/selectivity patterns, and ANN predictions enable practical tailoring of product distributions for optimization based on target selectivity or conversion.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages21

Reading Time53 min

AccessFree to download

Introduction

Energy transition context and motivation

Review scope and approach

Data collection and ANN-based quantitative assessment

Parameter categorization and evaluation targets (conversion, selectivity)

Model comparison and parameter-pattern analysis

Kinetic power expression comparison

Binary-parameter set investigation

Optimization and practical implications

Product distribution tailoring using predictions

Edith Cowan University Research Online Research outputs 2022 to 2026 3-15-2024 Parametric analysis of CO2 hydrogenation via fischer-tropsch synthesis: A review based on machine learning for quantitative assessment Jing Hu Yixao Wang Xiyue Zhang Yunshan Wang Gang Yang See next page for additional authors Follow this and additional works at: [https://ro.ecu.edu.au/ecuworks2022-2026](https://ro.ecu.edu.au/ecuworks2022-2026) Part of the Civil and Environmental Engineering Commons 10.1016/j.ijhydene.2024.02.055 Hu, J., Wang, Y., Zhang, X., Wang, Y., Yang, G., Shi, L., & Sun, Y. (2024) . Parametric analysis of CO2 hydrogenation via fischer-tropsch synthesis: A review based on machine learning for quantitative assessment. International Journal of Hydrogen Energy, 59, article 1023-1041 . [https://doi.org/10.1016/j.ijhydene.2024.02.055](https://doi.org/10.1016/j.ijhydene.2024.02.055) [This Journal Article is posted at Research Online.](This Journal Article is posted at Research Online.)[ ](This Journal Article is posted at Research Online.)[https://ro.ecu.edu.au/ecuworks2022-2026/3854](https://ro.ecu.edu.au/ecuworks2022-2026/3854) Authors Jing Hu, Yixao Wang, Xiyue Zhang, Yunshan Wang, Gang Yang, Lufang Shi, and Yong Sun This journal article is available at Research Online: [https://ro.ecu.edu.au/ecuworks2022-2026/3854](https://ro.ecu.edu.au/ecuworks2022-2026/3854) International Journal of Hydrogen Energy 59 (2024) 1023–1041 Contents lists available at ScienceDirect International Journal of Hydrogen Energy journal [homepage:](homepage: www.elsevier.com/locate/he)[ www.elsevier.com/locate/he](homepage: www.elsevier.com/locate/he) | Parametric analysis of CO2 hydrogenation via Fischer-Tropsch synthesis: A review based on machine learning for quantitative assessment
Jing Hua, 1, Yixao Wang b, 1, Xiyue Zhang c, Yunshan Wang d, Gang Yang d, **, Lufang Shie, Yong Sun f, g, *
a Stanford School of Engineering & Doerr School of Sustainability, Stanford University, California, 94305, USA b UCL Institute for Materials Discovery, University College London (UCL), London, WC1H 0AJ, UK c Department of Civil and Environmental Engineering, Imperial College London, London, SW7 3LE, UK
d National Engineering Laboratory of Cleaner Hydrometallurgical Production Technology, Institute of Process Engineering, Chinese Academy of Sciences, Beijing, 100190, China
e Each Energy Australia, James Ruse Drive, NSW, 2116, Australia
f School of Engineering, Edith Cowan University, 270 Joondalup Drive, Joondalup, WA, 6027, Australia
g Key Laboratory of Carbonaceous Wastes Processing and Process Intensification of Zhejiang Province, University of Nottingham Ningbo, 315100, China | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Handling Editor: Ramazan Solmaz | | This review focuses on the parametric impacts upon conversion and selectivity during CO2 hydrogenation via Fischer-Tropsch (FT) synthesis using iron-based catalyst to provide quantitative evaluation. Using all collected data from reported literatures as training dataset via artificial neural networks (ANNs) in TensorFlow, three categorized parameters (namely: operational, catalyst informatic and mass transfer) were deployed to assess their impacts upon conversions (CO2) and selectivity. The lump kinetic power expressions among literature reports were compared, and the best fit model is the one that was proposed by this work without arbitrarily assuming power values of individual partial pressure (CO and H2). More than five sets of binary parameters were systematically investigated to find out corresponding evolving patterns in conversion and selectivity. Aided by machine learning, tailoring product distributions based on specific selectivity or conversion for optimization purpose is practically achievable by deploying the predictions generated from ANNs in this work. | | Keywords:
Artificial neural networks
CO2 hydrogen

FAQs

What is the main focus of the review on CO2 hydrogenation via Fischer-Tropsch synthesis?

It focuses on how operational, catalyst-related, and mass-transfer parameters affect conversion and selectivity in CO2 hydrogenation using iron-based FT catalysts, providing quantitative evaluation.

How are machine learning models used for the quantitative assessment?

The review compiles all collected literature data as a training dataset and trains artificial neural networks (ANNs) in TensorFlow to assess the impacts of categorized parameters on conversion and selectivity.

What modeling comparison is performed regarding kinetic power expressions?

The review compares lump kinetic power expressions reported across literature and selects the best fit model without arbitrarily assuming power values for individual partial pressures (CO and H2).

How does the review support optimization of product distributions?

By using ANN-generated predictions, it shows that tailoring product distributions toward specific selectivity or conversion targets for optimization is practically achievable.

Aug 6, 2026

Upload by Finn