Skillful joint probabilistic weather forecasting from marginals
pith:GCY2WGTRopen to challenge →
read the original abstract
Machine learning (ML)-based weather models have rapidly risen to prominence due to their greater accuracy and speed than traditional forecasts based on numerical weather prediction (NWP), recently outperforming traditional ensembles in global probabilistic weather forecasting. This paper presents FGN, a simple, scalable and flexible modeling approach which significantly outperforms the current state-of-the-art models. FGN generates ensembles via learned model-perturbations with an ensemble of appropriately constrained models. It is trained directly to minimize the continuous rank probability score (CRPS) of per-location forecasts. It produces state-of-the-art ensemble forecasts as measured by a range of deterministic and probabilistic metrics, makes skillful ensemble tropical cyclone track predictions, and captures joint spatial structure despite being trained only on marginals.
This paper has not been read by Pith yet.
Forward citations
Cited by 18 Pith papers
-
The physics of AI weather models
AI weather models may simulate the atmosphere via particle positions in latent space whose updates follow gradient flow on a learned free energy functional rather than conventional physical equations.
-
Uncertainty-aware Machine Learning Interatomic Potentials via Learned Functional Perturbations
Learned functional perturbations plus CRPS training convert deterministic ML interatomic potentials into probabilistic ones, improving CRPS by 19-32% on N-body benchmarks and uncertainty-error correlation from 0.75 to...
-
Cast3: Translating numerical weather prediction principles into data-driven forecasting
Cast3 translates NWP principles into a data-driven model using cubed-sphere grids, super-ensembles, and generative nudging to achieve state-of-the-art ensemble predictions that outperform baselines.
-
Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction
Online conformal prediction post-processing guarantees calibrated uncertainty coverage for GenCast, NeuralGCM, and AIFS-ENS forecasts of temperature and precipitation including extremes.
-
Uncertainty-aware Machine Learning Interatomic Potentials via Learned Functional Perturbations
Learned functional perturbations convert deterministic ML interatomic potentials to probabilistic models trained with CRPS, improving uncertainty calibration over Bayesian baselines on N-body and silica benchmarks.
-
Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting
Njord introduces a probabilistic GNN model using latent variables and adaptive K-means meshes for ensemble ocean forecasting with uncertainty estimates on global and regional domains.
-
Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting
Njord is a probabilistic GNN model using latent variables and adaptive K-means meshes that produces ensemble forecasts and outperforms deterministic ML baselines on global OceanBench and Baltic Sea domains.
-
Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
Tyche achieves competitive probabilistic weather forecasting skill and calibration using a single-step flow model with JVP-regularized training and rollout finetuning.
-
Extreme Weather Bench: A framework and benchmark for evaluation of high-impact weather
Extreme Weather Bench supplies standardized case studies, observational data, impact metrics, and code to evaluate weather models on high-impact hazards.
-
Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting
WassersteinGrad aggregates perturbed gradient attribution maps via their entropic Wasserstein barycenter to avoid blurring from geometric shifts in explanations of autoregressive weather forecasts.
-
Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting
ESFM is a single open foundation model that unifies heterogeneous Earth data sources and forecasts missing regions while preserving inter-variable physical relationships.
-
U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
A standard U-Net with MAE pre-training followed by short CRPS fine-tuning via Monte Carlo Dropout matches or exceeds GenCast and IFS ENS probabilistic skill at 1.5° resolution while cutting training compute and infere...
-
EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
EnScale emulates high-resolution regional climate model outputs from global circulation models for multiple variables using a two-step generative process with sparse local stochastic layers and energy score optimizati...
-
Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting
Otter Weather is a spatiotemporal model that outperforms NWP baselines by 9.6% at 24h lead with under 3.5 A100-days training and extends efficiency gains to probabilistic forecasting via CRPS.
-
Towards Fair Comparisons of AI- and Physics-Based Weather Models for Extreme Events via the Weighted Potential CRPS
Extends Potential CRPS with weights and IDR post-processing to enable fair comparisons of AIWP and NWP models on extreme weather, finding AI models more informative across most variables and thresholds.
-
Reliability of Probabilistic Emulation of Physical Systems
CRPS-trained ensembles achieve better uncertainty reliability and speed than latent generative models for probabilistic emulation of 2D physical systems.
-
Evaluation of medium range machine learning models for sub-seasonal prediction
GraphCast and FourCastNetV2 show skill for sub-seasonal prediction comparable to physics-based models like ACCESS-S2 over 38-year and 2.5-year hindcast periods.
-
Towards a Foundation Model for the Martian Atmosphere
The paper reviews data sources, physical models, downstream applications, and AI techniques to outline considerations for building a foundation model for the Martian atmosphere.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.