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.
hub
arXiv, ://arxiv.org/abs/2412.15832
15 Pith papers cite this work, alongside 8 external citations. Polarity classification is still indexing.
15
Pith papers citing it
8
external citations · external index
hub tools
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
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 0.84 on silica.
Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.
Augments the energy score objective for sample-based generative models with a differentiable decision loss that is itself a proper scoring rule, yielding targeted improvements on cost-sensitive regions in synthetic and real tasks.
Training climate emulators on random-CO2 runs that break SST–CO2 correlation, plus an energy constraint, yields a data-efficient model that works on AMIP+4K and abrupt 4xCO2 cases prior ACE models mishandled.
Distributional autoencoders trained on climate model simulations model full conditional distributions of European temperature fields to enable probabilistic storyline attribution, illustrated by higher intensities and probability ratios for a 2003-like heatwave in 2028 and 2053.
AdaWeather adaptively mixes probabilistic weather forecasts and achieves logarithmic regret relative to the best static mixture of experts in hindsight.
RealBench is a benchmark for data-driven weather forecasting that enforces operational conditions via a 2025 OOD test set, operational analysis, in-situ observations, and event-specific extreme metrics to expose gaps versus reanalysis-based evaluation.
A generative 3D Gaussian splatting model with scale-aware attention enables unified arbitrary-resolution forecasting and downscaling of 87 atmospheric variables.
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 optimization, including a temporally consistent variant.
CRPS-trained ensembles achieve better uncertainty reliability and speed than latent generative models for probabilistic emulation of 2D physical systems.
Probabilistic bias correction doubles ECMWF AI subseasonal skill and improves debiased dynamical forecasts for most pressure, temperature, and precipitation targets, winning ECMWF’s 2025 real-time competition.
A standard U-Net with MAE pre-training plus short CRPS fine-tuning and MC Dropout matches GenCast and IFS ENS probabilistic skill at 1.5° while cutting training and inference cost by over 10×.
A multimodal GNN ablation for Nordic precipitation nowcasting shows sparse point observations improve station and onset scores while NWP and CRPS losses improve radar-grid performance, indicating local and field skills are distinct targets.
GraphCast shows regime-dependent skill versus ECMWF HRES in Brazil, underperforming on winter baroclinic systems in medium range but gaining in extended range and summer moisture transport.
citing papers explorer
-
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 0.84 on silica.
-
Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulators
Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.
-
Decision-Aware Training for Sample-Based Generative Models
Augments the energy score objective for sample-based generative models with a differentiable decision loss that is itself a proper scoring rule, yielding targeted improvements on cost-sensitive regions in synthetic and real tasks.
-
Disentangling the effects of sea surface temperature and CO$_2$ in global machine learned weather-climate emulators
Training climate emulators on random-CO2 runs that break SST–CO2 correlation, plus an energy constraint, yields a data-efficient model that works on AMIP+4K and abrupt 4xCO2 cases prior ACE models mishandled.
-
Probabilistic storyline attribution using machine learning
Distributional autoencoders trained on climate model simulations model full conditional distributions of European temperature fields to enable probabilistic storyline attribution, illustrated by higher intensities and probability ratios for a 2003-like heatwave in 2028 and 2053.
-
AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret
AdaWeather adaptively mixes probabilistic weather forecasts and achieves logarithmic regret relative to the best static mixture of experts in hindsight.
-
RealBench: Benchmarking Data-Driven Numerical Weather Forecasting Under Operational Conditions and Extreme Event Challenges
RealBench is a benchmark for data-driven weather forecasting that enforces operational conditions via a 2025 OOD test set, operational analysis, in-situ observations, and event-specific extreme metrics to expose gaps versus reanalysis-based evaluation.
-
Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting
A generative 3D Gaussian splatting model with scale-aware attention enables unified arbitrary-resolution forecasting and downscaling of 87 atmospheric variables.
-
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 optimization, including a temporally consistent variant.
-
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.
-
Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction
Probabilistic bias correction doubles ECMWF AI subseasonal skill and improves debiased dynamical forecasts for most pressure, temperature, and precipitation targets, winning ECMWF’s 2025 real-time competition.
-
U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
A standard U-Net with MAE pre-training plus short CRPS fine-tuning and MC Dropout matches GenCast and IFS ENS probabilistic skill at 1.5° while cutting training and inference cost by over 10×.
-
Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks
A multimodal GNN ablation for Nordic precipitation nowcasting shows sparse point observations improve station and onset scores while NWP and CRPS losses improve radar-grid performance, indicating local and field skills are distinct targets.
-
Performance Evaluation of GraphCast for Medium-Range Weather Forecasting over Brazil
GraphCast shows regime-dependent skill versus ECMWF HRES in Brazil, underperforming on winter baroclinic systems in medium range but gaining in extended range and summer moisture transport.