Policy-making optimization based on generative adversarial networks: A case study of mapping energy transition pathways to China's carbon neutrality.

• Existing model outputs of energy transitions to carbon neutrality are integrated by DCGAN. • Uncertainties from different model outputs are assimilated by DCGAN. • The application of DCGAN is extended into policy-making optimization. • DCGAN reveals the underestimation of hydrogen and nuclear energies in the pathway to carbon neutrality. • DCGAN underscores the importance of accelerating CCUS development in the early stage. Mapping energy transition pathways is pivotal for achieving carbon neutrality. However, potential pathways delineated by rule-based models differ significantly due to model characteristics, posing a grand challenge in subsequent policy-making. Inspired by the ability of deep convolutional generative adversarial networks (DCGAN) to extract features and generate images, we integrate model outputs concerning 16 energies' transition pathways to carbon neutrality through DCGAN, assimilating the uncertainties among these outputs. Since DCGAN absorbs the patterns of published data, it offers new insights into policy-making of energy transitions. DCGAN indicates that natural gas and its application with carbon capture and storage play more crucial roles than these currently suggested levels. Additionally, hydrogen and nuclear energies require further development over 2020−2060, serving as a cushion during the substantial energy restructuring. Our study not only provides novel insights into methods mapping the trajectories of critical variables to carbon neutrality but extends DCGAN's application into policy-making optimization. [Display omitted] [ABSTRACT FROM AUTHOR]