EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Interactive Climate Projection via Conditional Generative AI

Chengjie Sun, Zijie Guo, Pumeng Lyu, Fenghua Ling, Jing‐Jia Luo

Geophysical Research Letters · 28.06.2026 · 53 (12)

DOI: 10.1029/2026gl123578 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 16.06.2026. Verfasst von Chengjie Sun und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamical Earth System Models are extremely expensive, requiring ∼10 6 core‐hours for century‐scale simulations. This limits climate projections to only a few Shared Socioeconomic Pathways (SSPs) and leaves numerous policy trajectories unexplored. Here, we develop an external forcing boundary‐constrained generative emulator trained on CMIP6 model outputs, enabling rapid projection of temperature, precipitation and sea‐surface height under arbitrary CO 2 forcing pathways. The model learns the continuous manifold of future climate states by conditioning on the physical boundary defined by two extreme scenarios (SSP1‐1.9 and SSP5‐8.5). It can reconstruct climate responses under pathways held out during training (e.g., SSP2‐4.5). We further apply it to four newly constructed CO 2 pathways (higher‐emission, lower‐emission, overshoot, and step‐change) to demonstrate its generalization capability across distinct forcings. This allows us to capture regional shifts in extreme events and threshold timings. The emulator substantially reduces computational demand and provides a high‐throughput, user‐driven platform for evaluating flexible mitigation strategies.

Zitieren

APA

Sun, C., Guo, Z., Lyu, P., Ling, F., & Luo, J. (2026). Interactive Climate Projection via Conditional Generative AI. Geophysical Research Letters, 53(12). https://doi.org/10.1029/2026gl123578

Vancouver

Sun C, Guo Z, Lyu P, Ling F, Luo J. Interactive Climate Projection via Conditional Generative AI. Geophysical Research Letters. 2026;53(12). doi:10.1029/2026gl123578

BibTeX
@article{Sun2026,
  author = {Sun, Chengjie and Guo, Zijie and Lyu, Pumeng and Ling, Fenghua and Luo, Jing‐Jia},
  title = {Interactive Climate Projection via Conditional Generative AI},
  journal = {Geophysical Research Letters},
  year = {2026},
  volume = {53},
  number = {12},
  doi = {10.1029/2026gl123578}
}
Kostenlos starten →