Advanced Long-term Earth System Forecasting

TL;DR

TritonCast is a novel AI architecture that significantly improves long-term Earth system forecasting stability and accuracy by mitigating spectral bias through a nested, multi-scale design, enabling multi-year climate simulations and cross-resolution generalization.

Contribution

The paper introduces TritonCast, a new AI model with a latent dynamical core and nested structure that enhances long-term stability and accuracy in Earth system forecasting, addressing spectral bias issues.

Findings

Achieves state-of-the-art accuracy on WeatherBench 2.

Performs year-long autoregressive global forecasts without drift.

Extends eddy forecast skill to 120 days and generalizes across resolutions.

Abstract

Reliable long-term forecasting of Earth system dynamics is fundamentally limited by instabilities in current artificial intelligence (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. Inspired by the nested grids in numerical models used to resolve small scales, we present TritonCast. At the core of its design is a dedicated latent dynamical core, which ensures the long-term stability of the macro-evolution at a coarse scale. An outer structure then fuses this stable trend with fine-grained local details. This design effectively mitigates the spectral bias caused by cross-scale interactions. In atmospheric science, it achieves state-of-the-art accuracy on the WeatherBench 2 benchmark while demonstrating exceptional long-term stability: executing year-long autoregressive global forecasts and completing multi-year climate simulations that span the entire available $2500$-day test period without drift. In oceanography, it extends skillful eddy forecast to $120$ days and exhibits unprecedented zero-shot cross-resolution generalization. Ablation studies reveal that this performance stems from the synergistic interplay of the architecture's core components. TritonCast thus offers a promising pathway towards a new generation of trustworthy, AI-driven simulations. This significant advance has the potential to accelerate discovery in climate and Earth system science, enabling more reliable long-term forecasting and deeper insights into complex geophysical dynamics.