Resolving sources of uncertainty in AI weather forecasting
cs.LG, cs.AI
Submitted: 2025-11-18
Updated: 2026-09-06
Comments: Substantially revised and extended version with an updated title and author list. Wenbo Hu and Xinlei Xiong contributed equally to this version
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Foundation Model for the Earth System
- Uncertainty quantification for data-driven weather models
- FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
- Forecasting Global Weather with Graph Neural Networks
- BayesDLL: Bayesian Deep Learning Library
- AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score
- Decoupled Weight Decay Regularization
- Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
- FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
- ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
- FuXi-ENS: A machine learning model for medium-range ensemble 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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks