EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matching
cs.LG, physics.ao-ph
Submitted: 2026-10-07
Updated: 2026-10-07
Code: https://github.com/nmucke/scientificstochastic-interpolants
Terminology
Sources
- Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere
- CAMulator: Fast Emulation of the Community Atmosphere Model
- Probabilistic Forecasting with Stochastic Interpolants and F\"ollmer Processes
- Physics-Constrained Adaptive Flow Matching for Climate Downscaling
- PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations
- AIFS -- ECMWF's data-driven forecasting system
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- SGDR: Stochastic Gradient Descent with Warm Restarts
- ACE: A fast, skillful learned global atmospheric model for climate prediction
- A comparison of stretched-grid and limited-area modelling for data-driven regional weather forecasting
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks