An ML model trained only on harmonized gridded observations achieves competitive medium-range weather forecast skill with the IFS for several upper-air and surface headline scores when verified against observations.
hub
Forecasting global weather with graph neural networks
19 Pith papers cite this work, alongside 127 external citations. Polarity classification is still indexing.
19
Pith papers citing it
127
external citations · Pith
abstract
We present a data-driven approach for forecasting global weather using graph neural networks. The system learns to step forward the current 3D atmospheric state by six hours, and multiple steps are chained together to produce skillful forecasts going out several days into the future. The underlying model is trained on reanalysis data from ERA5 or forecast data from GFS. Test performance on metrics such as Z500 (geopotential height) and T850 (temperature) improves upon previous data-driven approaches and is comparable to operational, full-resolution, physical models from GFS and ECMWF, at least when evaluated on 1-degree scales and when using reanalysis initial conditions. We also show results from connecting this data-driven model to live, operational forecasts from GFS.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Observation-only machine learning can generate multi-decade global atmospheric reanalyses with large-scale skill near ERA5 and surface errors between ERA-Interim and ERA5, in a single day of compute.
Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.
SIES learns generalizable local coupling operators via signed source-target attention for controllable synchronization in graph dynamical systems and applies the principle to heterophilous graph representation learning.
Samudra 2 scales autoregressive neural ocean emulators to finer resolutions with architectural tweaks and dynamic loss, raising upper-ocean temperature R² from 0.56 to 0.87 at 1° and recovering mesoscale features.
WeatherSyn is the first instruction-tuned MLLM for weather forecasting report generation, outperforming closed-source models on a new dataset of 31 US cities across 8 weather aspects.
Diffusion model climate emulators provide probability density estimates that allow likelihood calculations and odds-ratio-based importance sampling for extreme events such as tropical cyclones.
A GraphCast-based ocean emulator achieves skillful 10-15 day forecasts, with a Mahalanobis loss that accounts for variable correlations improving performance over MSE and acting as a statistical-dynamical regularizer.
Image-to-image networks estimate parameters of non-stationary SAR models faster and more accurately than traditional methods by framing fields and parameters as images.
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.
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 conditional diffusion model downscales global atmospheric forecasts from 100 km to 30 km resolution while improving probabilistic skill, matching power spectra, and preserving physical relationships.
STCast introduces Spatial-Aligned Attention and Temporal Mixture-of-Experts modules to adaptively refine regional boundaries in data-driven weather forecasting and reports better performance than prior methods on global, regional, extreme-event, and ensemble tasks.
COGENT is a continuous graph emulator using Neural ODEs for stable long-term forecasting on irregular geospatial meshes, evaluated on ice-sheet simulations with improved stability over autoregressive baselines.
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.
The work introduces WaLeF/FIDLAr for flood forecasting, CoDiCast for probabilistic weather, and Hypercube-RAG for explainable environmental QA, claiming superior accuracy, efficiency, and interpretability over baselines.
DroughtFormer predicts soil moisture, vegetation health, and related variables in Africa with skill out to 90 days that matches or exceeds climatology for most targets, but shows lower accuracy for precipitation and flash drought indices.
The paper reviews data sources, physical models, downstream applications, and AI techniques to outline considerations for building a foundation model for the Martian atmosphere.
A review of Earth science foundation models covering capability evolution from perception to discovery, applications across atmosphere/hydrosphere/lithosphere/biosphere/anthroposphere/cryosphere, over 200 datasets, and key challenges.
citing papers explorer
-
AIFS-DOP: End-to-End Medium-Range Weather Prediction from Observations Alone with Machine Learning
An ML model trained only on harmonized gridded observations achieves competitive medium-range weather forecast skill with the IFS for several upper-air and surface headline scores when verified against observations.
-
Global reanalysis from observations alone with machine learning
Observation-only machine learning can generate multi-decade global atmospheric reanalyses with large-scale skill near ERA5 and surface errors between ERA-Interim and ERA5, in a single day of compute.
-
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.
-
Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems
SIES learns generalizable local coupling operators via signed source-target attention for controllable synchronization in graph dynamical systems and applies the principle to heterophilous graph representation learning.
-
Samudra 2: Scaling Ocean Emulators across Resolutions
Samudra 2 scales autoregressive neural ocean emulators to finer resolutions with architectural tweaks and dynamic loss, raising upper-ocean temperature R² from 0.56 to 0.87 at 1° and recovering mesoscale features.
-
WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation
WeatherSyn is the first instruction-tuned MLLM for weather forecasting report generation, outperforming closed-source models on a new dataset of 31 US cities across 8 weather aspects.
-
Towards accurate extreme event likelihoods from diffusion model climate emulators
Diffusion model climate emulators provide probability density estimates that allow likelihood calculations and odds-ratio-based importance sampling for extreme events such as tropical cyclones.
-
Skillful Global Ocean Emulation and the Role of Correlation-Aware Loss
A GraphCast-based ocean emulator achieves skillful 10-15 day forecasts, with a Mahalanobis loss that accounts for variable correlations improving performance over MSE and acting as a statistical-dynamical regularizer.
-
LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Data
Image-to-image networks estimate parameters of non-stationary SAR models faster and more accurately than traditional methods by framing fields and parameters as images.
-
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.
-
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×.
-
Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models
A conditional diffusion model downscales global atmospheric forecasts from 100 km to 30 km resolution while improving probabilistic skill, matching power spectra, and preserving physical relationships.
-
STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting
STCast introduces Spatial-Aligned Attention and Temporal Mixture-of-Experts modules to adaptively refine regional boundaries in data-driven weather forecasting and reports better performance than prior methods on global, regional, extreme-event, and ensemble tasks.
-
COGENT: Continuous Graph Emulators with Neural Ordinary Differential Equations for Long-Term Physical Forecasting
COGENT is a continuous graph emulator using Neural ODEs for stable long-term forecasting on irregular geospatial meshes, evaluated on ice-sheet simulations with improved stability over autoregressive baselines.
-
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.
-
Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems
The work introduces WaLeF/FIDLAr for flood forecasting, CoDiCast for probabilistic weather, and Hypercube-RAG for explainable environmental QA, claiming superior accuracy, efficiency, and interpretability over baselines.
-
Prediction of Drought and Flash Drought in Africa at the Seasonal-to-Subseasonal Scale using the Community Research Earth Digital Intelligence Twin Framework
DroughtFormer predicts soil moisture, vegetation health, and related variables in Africa with skill out to 90 days that matches or exceeds climatology for most targets, but shows lower accuracy for precipitation and flash drought indices.
-
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.
-
Earth Science Foundation Models: From Perception to Reasoning and Discovery
A review of Earth science foundation models covering capability evolution from perception to discovery, applications across atmosphere/hydrosphere/lithosphere/biosphere/anthroposphere/cryosphere, over 200 datasets, and key challenges.