Using deep learning to generate key variables in global mitigation scenarios

Li, P., Zhu, R., McJeon, H., Byers, E. ORCID: https://orcid.org/0000-0003-0349-5742, Zhou, P., & Ou, Y. (2025). Using deep learning to generate key variables in global mitigation scenarios. Nature Climate Change 10.1038/s41558-025-02352-8.

Full text not available from this repository.

Abstract

Integrated assessment models (IAMs) are the dominant tools for projecting mitigation scenarios. However, IAM-based scenarios often face challenges such as modelling biases and large computational burden. Here we develop a deep learning framework to generate key variables through synthetic mitigation scenarios aligned with the Sixth Assessment Report (AR6) Scenarios Database. By analysing 1,202 scenarios from a diverse set of IAMs, we select key drivers that enable a more detailed sectoral representation. Next, we trained three generative deep learning models to produce 30,000 synthetic scenarios at low computational cost across various IPCC AR6 climate categories, replicating variable distributions and correlations while also demonstrating physical consistency in power sector variables through internal validation checks. We found that the variational autoencoder achieved the highest label transferring accuracy among three frameworks. This study illustrates the potential of deep learning to complement IAM approaches and provides a basis for handling complex mitigation scenario generation tasks.

Item Type:	Article
Research Programs:	Energy, Climate, and Environment (ECE) Energy, Climate, and Environment (ECE) > Integrated Assessment and Climate Change (IACC) Energy, Climate, and Environment (ECE) > Sustainable Service Systems (S3)
Depositing User:	Luke Kirwan
Date Deposited:	23 Jun 2025 11:43
Last Modified:	23 Jun 2025 11:43
URI:	https://pure.iiasa.ac.at/20694

Actions (login required)

View Item