A machine learning approach for country-level deployment of greenhouse gas removal technologies

Date published

2023-10-19

Free to read from

Supervisor/s

Journal Title

Journal ISSN

Volume Title

Publisher

Elsevier

Department

Type

Article

ISSN

1750-5836

Format

Citation

Asibor JO, Clough PT, Nabavi SA, Manovic V. (2023) A machine learning approach for country-level deployment of greenhouse gas removal technologies, International Journal of Greenhouse Gas Control, Volume 130, December 2023, Article Number 103995

Abstract

The suitability of countries to deploy five greenhouse gas removal technologies was investigated using hierarchical clustering machine learning. These technologies include forestation, enhanced weathering, direct air carbon capture and storage, bioenergy with carbon capture and storage and biochar. The use of this unsupervised machine learning model greatly minimises the likelihood of human bias in the assessment of GGR technology deployment potentials and instead takes a more holistic view based on the applied data. The modelling utilised inputs of bio-geophysical and techno-economic factors of 182 countries, with the model outputs highlighting the potential performance of these GGR methods. Countries such as USA, Canada, Brazil, China, Russia, Australia as well as those within the EU and Sub-Saharan Africa were identified as key areas suitable to deploy these GGR technologies. The level of certainty of the obtained deployment suitability categorisation ranged from 65 to 98 %. While the results show the need for regional collaboration between nations, they also highlight the necessity for nations to prioritise and integrate GGR technologies in their revised nationally determined contributions.

Description

Software Description

Software Language

Github

Keywords

Greenhouse gas removal, BECCS, DACCS, Machine learning, Climate change mitigation

DOI

Rights

Attribution 4.0 International

Relationships

Relationships

Supplements

Funder/s