PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
September 29, 20250 citationsOpen Access

Advanced long-term earth system forecasting by learning the small-scale nature

View Full Paper
HWHao WuAir Force Engineering UniversityYGYuan GaoNanjing University of Science and TechnologyRSRong ShuUniversity of Science and Technology of China

Key Points

  • Triton achieves stable year-long global temperature forecasts while significantly improving upon baseline AI models.
  • The framework demonstrates superior performance in Kuroshio eddy predictions, maintaining skill until 120 days.
  • Using a hierarchical architecture, Triton mitigates spectral bias and accurately models small-scale processes across resolutions.
  • Effective suppression of high-frequency error accumulation enhances the reliability of AI-driven climate simulations.

Abstract

Reliable long-term forecast of Earth system dynamics is heavily hampered by instabilities in current AI models during extended autoregressive simulations. These failures often originate from inherent spectral bias, leading to inadequate representation of critical high-frequency, small-scale processes and subsequent uncontrolled error amplification. We present Triton, an AI framework designed to address this fundamental challenge. Inspired by increasing grids to explicitly resolve small scales in numerical models, Triton employs a hierarchical architecture processing information across multiple resolutions to mitigate spectral bias and explicitly model cross-scale dynamics. We demonstrate Triton's superior performance on challenging forecast tasks, achieving stable year-long global temperature forecasts, skillful Kuroshio eddy predictions till 120 days, and high-fidelity turbulence simulations preserving fine-scale structures all without external forcing, with significantly surpassing baseline AI models in long-term stability and accuracy. By effectively suppressing high-frequency error accumulation, Triton offers a promising pathway towards trustworthy AI-driven simulation for climate and earth system science.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Wu et al. (2025) studied this question.

synapsesocial.com/papers/68da5a3ec1728099cfd11968https://doi.org/10.48550/arxiv.2505.19432
Ask AI
Helpful
Bookmark
Share
View Full Paper