The Rise of the Machines - A State-of-the-Art Technical Review on Process Modelling and Machine Learning within Hydrogen Production with Carbon Capture

Aug 3, 2026

Upload by Anda

This technical review compiles current trends in process modelling and the adoption of machine learning in combined hydrogen production and carbon capture, focused on blue hydrogen research and development. It outlines the landscape of blue hydrogen production and introduces relevant machine-learning and process-modelling concepts, then examines how these techniques are implemented across material and process development. The study highlights key tools, and evaluates strengths and limitations. It concludes by positioning machine learning as a major accelerator for future blue-hydrogen R&D and future research directions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Introduction to hydrogen production & machine learning

Hydrogen production: types, current and future trends

118 (2023) 205104 Contents lists available at ScienceDirect Gas Science and Engineering journal [homepage: www.journals.elsevier.com/gas-science-and-engineering](homepage: www.journals.elsevier.com/gas-science-and-engineering) | The rise of the machines: A state-of-the-art technical review on process modelling and machine learning within hydrogen production with
carbon capture
William George Davies, Shervan Babamohammadi, Yang Yang, Salman Masoudi Soltani * Department of Chemical Engineering, Brunel University London, Uxbridge, UB8 3PH, United Kingdom | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Keywords: Machine learning Hydrogen Carbon capture Process modelling | | This study aims to present a compendious yet technical scrutiny of the current trends in process modelling as well as the implementation of machine learning within combined hydrogen production and carbon capture ([i.e. blue](i.e. blue)[ ](i.e. blue)[hydrogen](hydrogen)). The paper is intended to accurately portray the role that machine learning is anticipated to play within research and development in blue hydrogen production in the forthcoming years. This covers the implementation of machine learning at both material and process development levels. The paper provides a concise overview of the current trends in blue hydrogen production, as well as an intro to machine learning and process modelling within the same context. We have reinforced our paper by first summarising a brief description of the key “tools” used in machine learning and process modelling, before painstakingly examining the implementation of these techniques in blue hydrogen production and the less-discovered merits and de-merits.
Ultimately, the paper depicts a clear picture of the advancements in machine learning and the major role it is expected to play in accelerating research and development in blue hydrogen production on both material and process development fronts. The paper strives to shed some light on the key advantages that machine learning has to offer in blue hydrogen for future research work. | 1. Introduction to hydrogen production & machine learning 1.1. Hydrogen production: types, current and future trends Climate change is our most pressing issue of the 21st century as outlined in the latest Intergovernmental Panel on Climate Change (IPCC) report (IPCC et al., 2023). CO2 concentrations have now exceeded 420 ppm globally, there is a need to decarbonise globally at a rapid rate (IPCC et al., 2023). Since 2015 and the signing of the Paris agreement (UNFCCC, 2015), countries have, at least “on paper”, committed to ensuring that global warming does not exceed 2 ◦ C (with an ambition to limit this to just 1.5 ◦ C). Within the UK since 2019 and the declaration of a climate emergency. A policy framework has been developed known as“build back greener”(DESNZ & BEIS, 2021). This framework outlines away to ensure the meeting of Net Zero by 2050 in comparison to 1990 levels of CO2 emissions. Part of this strategy to ensure we reach Net Zero is the development of carbon capture and storage (CCS) technologies, transitioning from oil and gas to renewable resources and an increase in hydrogen production (BEIS, 2021). Deployment of CCS technologies is critical to ensure the continued supply of low-carbon energy within developing countries (Masoudi Soltani et al., 2021). In the UK, a key part of the Net Zero strategy is to develop CCS technologies, especially within industries such as cement and steel (DESNZ & BEIS, 2021). Hydrogen has been identified as a low-carbon energy storage molecule (van Renssen, 2020), and has been identified as a potentially viable alternative to fossil fuels as a clean fuel for transport in the aviation and shipping industry (Ishaq et al., 2022). As of 2021, 94 million tonnes of hydrogen are produced globally, and by 2030, this is expected to rise to a minimum of 105 million tonnes by 2030 (well below the 200 mil

FAQs

What is the document’s main goal regarding process modelling and machine learning in hydrogen production?

It presents a technical review of current process-modelling trends and how machine learning is being implemented in combined hydrogen production with carbon capture, specifically for blue hydrogen R&D.

Which areas of development does it discuss for applying machine learning?

It covers machine-learning implementation at both material development and process development levels within blue hydrogen production.

What key aspects does the review evaluate about machine-learning techniques?

It summarizes key machine-learning and process-modelling tools, then examines the merits and de-merits of these techniques as applied to blue hydrogen production.

Aug 3, 2026

Upload by Anda