arXiv Machine Learning
Stochastically Perturbed Weights: Ensembles from Deterministic Machine-Learning Weather Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 1
Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions
arXiv:2608.30795v1 Announce Type: cross Abstract: End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth observations, replacing the nume...
arXiv AI
Jun 2
U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
arXiv:2604. 09041v2 Announce Type: replace-cross Abstract: AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and massive computational budgets, creating a high barrier to entry.
arXiv Machine Learning
Jun 26
Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting
arXiv:2606. 26421v1 Announce Type: new Abstract: State-of-the-art medium-range AI weather models can outperform traditional Numerical Weather Prediction (NWP) but require massive training budgets.
arXiv Computer Vision
Oct 16
DIAL: Dynamic and Informed Adjustment of the Native Stochastic Law for Reliable Weather Ensembles
The paper introduces DIAL, a method that dynamically adjusts the native stochasticity of a frozen weather forecasting model to improve ensemble reliability across variables, scales, and lead times. DIAL learns from past forecasts to predict necessary spread adjustments and applies small noise updates during each forecast step, avoiding retraining or full backpropagation. Experiments on FourCastNet 3 show that DIAL outperforms post‑processing and reward‑based baselines, achieving an 8.27% improvement in multiscale CRPS over the unmodified model.
arXiv AI
Oct 19
Rescene: stable century-long climate emulation from a frozen weather model
Rescene is a 0.4 M‑parameter wrapper that transforms a frozen 1.5° weather model into a stochastic climate emulator. By anchoring the model to a calendar climatology with a deterministic slow clock and adding a band‑limited AR(1) perturbation tuned to the observed anomaly spectrum, Rescene produces century‑long runs with no detectable drift and realistic variability. A 100‑year, 8‑member experiment shows stable temperature trends, calibrated ensemble spread/skill, and accurate reproduction of day‑to‑day variability and blocking frequency.
arXiv Machine Learning
Aug 27
Forecasting Multiple Observables with SCROLL: Score-Trained Uncertainty for Stochastic Dynamics
The paper introduces SCROLL, a method for forecasting multiple observables in stochastic dynamical systems by composing each observable’s likelihood into per‑task free‑routed last‑layer beliefs on a shared backbone. This approach learns unit‑dependent loss scaling directly from data, enabling accurate predictive variance estimation without separate tuning. Experiments on the Ornstein–Uhlenbeck process, stochastic Lorenz‑63, and real air‑quality data show that SCROLL recovers analytic kernels, achieves superior negative log‑likelihood on state and regime tasks, and maintains calibration while reducing hyper‑parameter search costs.