This repo is the official PyTorch implementation of Triton_Earth: TritonCast: Advanced Long-term Earth System Forecasting.

📘Documentation | 🛠️Installation | 🚀Model Zoo | 🤗Huggingface | 👀Visualization | 🆕News

📑Open-source Plan

• [✅] Project Page
• [✅] Paper

🛠️Repository Structure

TritonCast-main/
├── exp1_medium_range_weather_forecasting/   # Corresponds to the medium-range weather forecasting experiments in the paper
├── exp2_long_term_stability_test/           # Corresponds to the long-term atmospheric stability experiments in the paper
├── exp3_multi_year_climate_simulation/      # Corresponds to the multi-year climate simulation experiments in the paper
├── exp4_global_ocean_simulation_and_forecasting/ # Corresponds to the global ocean simulation and forecasting experiments in the paper
├── exp6_high_fidelity_eddy_forecast/        # Corresponds to the high-fidelity ocean eddy forecasting experiments in the paper, including zero-shot
├── exp7_isotropic_turbulence/               # Corresponds to the turbulence benchmark tests in the paper
└── Readme.md                                # This document

Below is a guide to the experiments presented in our paper and their corresponding code directories.

Experiment Description	Directory	Quick Start
Medium-Range Weather Forecasting (on WeatherBench 2)	./exp1_...	Instructions
Long-Term Atmospheric Stability Test (Year-long forecast)	./exp2_...	Instructions
Multi-Year Climate Simulation	./exp3_...	Instructions
Global Ocean Simulation & Forecasting	./exp4_...	Instructions
High-Fidelity Ocean Eddy Forecast	./exp6_...	Instructions
Isotropic Turbulence Benchmark	./exp7_...	Instructions

🚀Architecture

Figure: The V-cycle architecture of TritonCast. It integrates a Multi-Grid Hierarchy for multi-scale processing, a stable Latent Dynamical Core (LDC) for long-term evolution, and Skip-Connections to retain high-fidelity details. This design effectively mitigates error accumulation in long-term forecasts.

🌟 Highlights

TritonCast establishes a new state-of-the-art in long-term Earth system forecasting. Our key contributions include:

• 🌀 Unprecedented Long-term Stability: Achieves stable, year-long, purely autoregressive global atmospheric forecasts without any drift or model collapse, accurately capturing seasonal cycles.
• 🌊 High-Fidelity Ocean Forecasting: Extends the skillful forecast of ocean eddies to an unprecedented 120 days, preserving fine-scale structures that other models lose.
• 🏆 State-of-the-Art Performance: Matches or exceeds leading AI models (like Pangu-Weather, GraphCast) and operational systems on the WeatherBench 2 benchmark for medium-range forecasting.
• 🌐 Zero-Shot Generalization: Demonstrates a remarkable ability to generalize across resolutions—a model trained on 0.25° data can produce physically realistic forecasts on unseen 0.125° grids, proving it has learned the underlying physical laws.