Energy scenarios project future possibilities based on a variety of assumptions, yet do not fully account for inherent friction in the energy transition, particularly over the near term. A new study shows how machine learning can complement existing scenario tools by incorporating lessons from the past into projections for the future.
This is a preview of subscription content, access via your institution
Access options
Subscribe to Journal
Get full journal access for 1 year
$119.00
only $9.92 per issue
All prices are NET prices.
VAT will be added later in the checkout.
Tax calculation will be finalised during checkout.
Buy article
Get time limited or full article access on ReadCube.
$32.00
All prices are NET prices.
References
Craig, P. P., Gadgil, A. & Koomey, J. G. Annu. Rev. Environ. Resour. 27, 83–118 (2002).
Africa Energy Outlook 2019 (International Energy Agency, 2019).
Africa Power Sector: Planning and Prospects for Renewable Energy (International Renewable Energy Agency 2015).
Lucas, P. L. et al. Energy Policy 86, 705–717 (2015).
Alova, G., Trotter, P. A. & Money, A. Nat. Energy https://doi.org/10.1038/s41560-020-00755-9 (2020).
Krey, V. Wiley Interdiscip. Rev. Energy Environ. 3, 363–383 (2014).
Ou, S. et al. Nat. Energy 5, 666–673 (2020).
de Coninck, H. et al. in IPCC Special Report on Global Warming of 1.5°C (eds Masson-Delmotte, V. et al.) Ch. 4 (WMO, 2018).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
McCollum, D.L. Machine learning for energy projections. Nat Energy 6, 121–122 (2021). https://doi.org/10.1038/s41560-021-00779-9
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41560-021-00779-9