Learning skillful medium-range global weather forecasting
2023/11/14 by Rémi Lam, Álvaro Sánchez‐González, Matthew Willson +15 · 245 citations
Earth and Planetary Sciences · Environmental Science · #Climate variability and models #Meteorological Phenomena and Simulations #Tropical and Extratropical Cyclones Research
paper · doi:10.1126/science.adi2336
openalex publication_date 2023/11/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30
Abstract
Global medium-range weather forecasting is critical to decision-making across many social and economic domains. Traditional numerical weather prediction uses increased compute resources to improve forecast accuracy but does not directly use historical weather data to improve the underlying model. Here, we introduce GraphCast, a machine learning-based method trained directly from reanalysis data. It predicts hundreds of weather variables for the next 10 days at 0.25° resolution globally in under 1 minute. GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets, and its forecasts support better severe event prediction, including tropical cyclone tracking, atmospheric rivers, and extreme temperatures. GraphCast is a key advance in accurate and efficient weather forecasting and helps realize the promise of machine learning for modeling complex dynamical systems.
Citations
Cited by
- Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models
- Applications of Machine Learning and Artificial Intelligence in Tropospheric Ozone Research
- A robust and stable hybrid neural network/finite element method for 2D flows that generalizes to different geometries
- Generative AI as a tool to accelerate the field of ecology
- Improving the generalization of protein expression models with mechanistic sequence information
- Snow Height Sensors Reveal Phenological Advance in Alpine Grasslands
- Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
- Hierarchical Testing of a Hybrid Machine Learning‐Physics Global Atmosphere Model
- Land surface information from satellites boost near-surface temperature forecast skill
- Multi-scale Autoregressive Models are Laplacian, Discrete, and Latent Diffusion Models in Disguise
- Practical Quantum Advantage before Fault Tolerance via Quantum-Informed Machine Learning
- Extreme Weather Bench: A framework and benchmark for evaluation of high-impact weather
- Modeling the Asymptotic Behavior of Higher Order Aftershocks with Deep Learning
- The Rise of AI in Weather and Climate Information and its Impact on Global Inequality
- ViT-Transformer: Self-attention mechanism based constitutive modeling for nonlinear heterogeneous materials
- Evaluating Extreme Precipitation Forecasts: A Threshold-Weighted, Spatial Verification Approach for Comparing an AI Weather Prediction Model Against a High-Resolution NWP Model
- Learning from History: A Retrieval-Augmented Framework for Spatiotemporal Prediction
- Synergistic Neural Forecasting of Air Pollution with Stochastic Sampling
- Parameter Estimation in Land Surface Models: Challenges and Opportunities With Data Assimilation and Machine Learning
- A PDE-Informed Latent Diffusion Model for 2-m Temperature Downscaling
- A foundation model for microbial growth dynamics
- Revealing the Potential of Learnable Perturbation Ensemble Forecast Model for Tropical Cyclone Prediction
- Enhanced forecasting of bird nocturnal migration intensity in relation to previous days and synoptic weather patterns
- The Benchmarking Epistemology: Construct Validity for Evaluating Machine Learning Models
- A Review of End-to-End Precipitation Prediction Using Remote Sensing Data: from Divination to Machine Learning
- A Framework for Hybrid Physics-AI Coupled Ocean Models
- HPC-Driven Modeling with ML-Based Surrogates for Magnon-Photon Dynamics in Hybrid Quantum Systems
- Hierarchical Graph Networks for Accurate Weather Forecasting via Lightweight Training
- LLMComp: A Language Modeling Paradigm for Error-Bounded Scientific Data Compression (Technical Report)
- Navigating Through Turbulence: Blueprint for the Next Generation of Weather-Climate Scientists
- CSU-PCAST: A Dual-Branch Transformer Framework for medium-range ensemble Precipitation Forecasting
- Signature Kernel Scoring Rule: A Spatio-Temporal Diagnostic for Probabilistic Weather Forecasting
- Sensing Without Colocation: Operator-Based Virtual Instrumentation for Domains Beyond Physical Reach
- Assessing Monotone Dependence: Area Under the Curve Meets Rank Correlation
- OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
- Improving the generalization of protein expression models with mechanistic sequence information
- Prediction-Augmented Trees for Reliable Statistical Inference
- An Operational Deep Learning System for Satellite-Based High-Resolution Global Nowcasting
- Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling
- Leveraging Teleconnections with Physics-Informed Graph Attention Networks for Long-Range Extreme Rainfall Forecasting in Thailand
- Deploying Atmospheric and Oceanic AI Models on Chinese Hardware and Framework: Migration Strategies, Performance Optimization and Analysis
- AgentCaster: Reasoning-Guided Tornado Forecasting
- DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space
- Interactive Atmospheric Composition Emulation for Next-Generation Earth System Models
- Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
- A Spatio-temporal CP decomposition analysis of New England region in the US
- Evaluating the Shanghai Typhoon Model against State-of-the-Art Machine-Learning Weather Prediction Models: A Case Study for Typhoon Danas (2025)
- ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting
- Quantifying Very Extreme Precipitation and Temperature Using Huge Ensembles Generated by Machine Learning-based Climate Model Emulators
- GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations
- Zeeman: A Deep Learning Regional Atmospheric Chemistry Transport Model
- Deep Learning Reconstruction of Tropical Cyclogenesis in the Western North Pacific from Climate Reanalysis Dataset
- Climate Model Tuning with Online Synchronization-Based Parameter Estimation
- Hybrid Sequential Quantum Computing
- DANRA: The Kilometer-Scale Danish Regional Atmospheric Reanalysis
- Benchmarking atmospheric circulation variability in an AI emulator, ACE2, and a hybrid model, NeuralGCM
- Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models
- Zephyrus: An Agentic Framework for Weather Science
- Learning more physically realistic dynamics in machine-learning based weather forecasting with latent-space constraints
- EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
- Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting
- A Synergistic Approach: Dynamics–AI Ensemble in Tropical Cyclone Forecasting
- Predictability Study of Weather and Climate Events Related to Artificial Intelligence Models
- From Edge to HPC: Investigating Cross-Facility Data Streaming Architectures
- A Weather Foundation Model for the Power Grid
- Rotational equivariant graph neural networks via local eigenbasis transformations
- Learning Regional Monsoon Patterns with a Multimodal Attention U-Net
- Using deep learning to generate key variables in global mitigation scenarios
- Flexible multi-fidelity framework for load estimation of wind farms through graph neural networks and transfer learning
- Model Training, Data Assimilation, and Forecast Experiments with a Hybrid Atmospheric Model that Incorporates Machine Learning
- Forecasting the Future with Yesterday's Climate: Temperature Bias in AI Weather and Climate Models
- Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
- Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
- Graph-based Neural Space Weather Forecasting
- Routes towards an effective AI in CFD: an epistemological and technical perspective
- Can AI Follow In Einstein's Footsteps?
- From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery
- Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts
- A Big Chill: Examining an Extremely Sharp Cold Front from Three Perspectives
- Simultaneous Emulation and Downscaling With Physically Consistent Deep Learning‐Based Regional Ocean Emulators
- Lessons from complex systems science for AI governance
- Harnessing artificial intelligence to fill global shortfalls in biodiversity knowledge
- The Impact of Tropical Convective Heating on the Amundsen Sea Low in a Deep-Learning Weather Forecasting Model
- Study Design and Demystification of Physics Informed Neural Networks for Power Flow Simulation
- Training-Free Data Assimilation with GenCast
- Discovering strategies for coastal resilience with AI-based prediction and optimization
- Technical overview and architecture of the FastNet Machine Learning weather prediction model, version 1.0
- Breaking the Discretization Barrier of Continuous Physics Simulation Learning
- An AutoML Framework using AutoGluonTS for Forecasting Seasonal Extreme Temperatures
- STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting
- From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?
- A data-driven global ocean forecasting model with sub-daily and eddy-resolving resolution
- FlowCast-ODE: Continuous Hourly Weather Forecasting with Dynamic Flow Matching and ODE Solver
- AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions
- SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators
- GraphCSVAE: Graph Categorical Structured Variational Autoencoder for Spatiotemporal Auditing of Physical Vulnerability Towards Sustainable Post-Disaster Risk Reduction
- Spatial Modeling and Risk Zoning of Global Extreme Precipitation via Graph Neural Networks and r-Pareto Processes
- Technical Aspects of Plasma Operational Simulation (POPSIM): A Framework for Data-Driven Simulation and Control
- A neural drift-plus-penalty algorithm for network power allocation and routing
- Breaking the Statistical Similarity Trap in Extreme Convection Detection
- MoWE : A Mixture of Weather Experts
- Intelligent Shanghai Typhoon Model (ISTM): A generative probabilistic emulator for typhoon hybrid modeling
- Stop using root-mean-square error as a precipitation target!
- S2Transformer: Scalable Structured Transformers for Global Station Weather Forecasting
- Seasonal forecasting using the GenCast probabilistic machine learning model
- Learning from one graph: transductive learning guarantees via the geometry of small random worlds
- Data-driven solar forecasting enables near-optimal economic decisions
- Temporal social network modeling of mobile connectivity data with graph neural networks
- Scale-Adaptive Generative Flows for Multiscale Scientific Data
- LUCIE-3D: A three-dimensional climate emulator for forced responses
- DeepSeasons: a Deep Learning scale-selecting approach to Seasonal Forecasts
- IndiaWeatherBench: A Dataset and Benchmark for Data-Driven Regional Weather Forecasting over India
- Post-processing of ensemble photovoltaic power forecasts with distributional and quantile regression methods
- Efficiently Generating Multidimensional Calorimeter Data with Tensor Decomposition Parameterization
- Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Events
- Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction
- Training Transformers for Mesh-Based Simulations
- Learning from nature: insights into GraphDOP's representations of the Earth System
- GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes
- Surya: Foundation Model for Heliophysics
- MedFormer: a data-driven model for forecasting the Mediterranean Sea
- CERA: A Framework for Improved Generalization of Machine Learning Models to Changed Climates
- Open science falling behind in the era of artificial intelligence
- DeepFleet: Multi-Agent Foundation Models for Mobile Robots
- Discovering Spatial Correlations of Earth Observations for weather forecasting by using Graph Structure Learning
- Lightning Prediction under Uncertainty: DeepLight with Hazy Loss
- Nonparametric Reaction Coordinate Optimization with Histories: A Framework for Rare Event Dynamics
- Large Model Driven Solar Activity AI Forecaster: A Scalable Dual Data-Model Framework
- MeteorPred: A Meteorological Multimodal Large Model and Dataset for Severe Weather Event Prediction
- Discovery Learning accelerates battery design evaluation
- Diffeomorphic Neural Operator Learning
- Prediction-Oriented Subsampling from Data Streams
- SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA
- Signals, Concepts, and Laws: Toward Universal, Explainable Time-Series Forecasting
- Point-wise Diffusion Models for Physical Systems with Shape Variations: Application to Spatio-temporal and Large-scale system
- Flow Matching for Probabilistic Learning of Dynamical Systems from Missing or Noisy Data
- KFS: KAN based adaptive Frequency Selection learning architecture for long term time series forecasting
- Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
- A Deep Learning Earth System Model for Efficient Simulation of the Observed Climate
- Data-driven global ocean model resolving ocean-atmosphere coupling dynamics
- Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperature
- Stability Analysis and Local Influence Diagnostics for an Extreme-Value Regression Model of Anomalous Wind Gusts
- Extreme Solar Storm Reveals Causal Interactions in Space Weather
- Quantum-Informed Machine Learning for Predicting Spatiotemporal Chaos
- A comparison of stretched-grid and limited-area modelling for data-driven regional weather forecasting
- GraphVSSM: Graph Variational State-Space Model for Probabilistic Spatiotemporal Inference of Dynamic Exposure and Vulnerability for Regional Disaster Resilience Assessment
- Learning Deformable Body Interactions With Adaptive Spatial Tokenization
- Wasserstein GAN-Based Precipitation Downscaling with Optimal Transport for Enhancing Perceptual Realism
- MVAR: MultiVariate AutoRegressive Air Pollutants Forecasting Model
- TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval
- EPT-2 Technical Report
- XiChen: A global weather observation-to-forecast machine learning system via four-dimensional variational gradient-guided flexible assimilation
- Intraseasonal Equatorial Kelvin and Rossby Waves in Modern AI-ML Models
- Learnable quantum spectral filters for hybrid graph neural networks
- TerraNova: A Foundation Model for the Anthropocene
- SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications
- CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning
- RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections
- Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation
- Deep Learning Atmospheric Models Reliably Simulate Out-of-Sample Land Heat and Cold Wave Frequencies
- Data and Code for Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion
- Understanding Generalization in Node and Link Prediction
- Accurate Mediterranean Sea forecasting via graph-based deep learning
- Imposing the Fundamental Dynamical Constraint of Hydrostatic Balance to Improve Global ML Weather Prediction
- RTide: Automating the Tidal Response Method
- Graph Neural Networks in Wind Power Forecasting
- Learning Stochastic Multiscale Models
- Probing forced responses and causality in data-driven climate emulators: conceptual limitations and the role of reduced-order models
- FuXi-Air: Urban Air Quality Forecasting Based on Emission-Meteorology-Pollutant multimodal Machine Learning
- Residual Reweighted Conformal Prediction for Graph Neural Networks
- Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics
- Projecting U.S. coastal storm surge risks and impacts with deep learning
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- PeakWeather: MeteoSwiss Weather Station Measurements for Spatiotemporal Deep Learning
- GITO: Graph-Informed Transformer Operator for Learning Complex Partial Differential Equations
- Physics-Informed Teleconnection-Aware Transformer for Global Subseasonal-to-Seasonal Forecasting
- Forecast error diagnostics in neural weather models
- Arnoldi Singular Vector perturbations for machine learning weather prediction
- FIGNN: Feature-Specific Interpretability for Graph Neural Network Surrogate Models
- Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
- Constructing Extreme Heatwave Storylines with Differentiable Climate Models
- Hierarchical Implicit Neural Emulators
- Probabilistic measures afford fair comparisons of AIWP and NWP model output
- Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony
- FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution
- A machine learning model for skillful climate system prediction
- Using Diffusion Models to do Data Assimilation
- Localized Forest Fire Risk Prediction: A Department-Aware Approach for Operational Decision Support
- Deep Learning Weather Models for Subregional Ocean Forecasting: A Case Study on the Canary Current Upwelling System
- Exploring Design Choices for Autoregressive Deep Learning Climate Models
- BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
- Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
- NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation
- FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation
- Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias
- Hierarchical-embedding autoencoder with a predictor (HEAP) as efficient architecture for learning long-term evolution of complex multi-scale physical systems
- Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems
- PEAR: Equal Area Weather Forecasting on the Sphere
- Anytime-valid, Bayes-assisted, Prediction-Powered Inference
- On the use of Graphs for Satellite Image Time Series
- Physics-based machine learning for mantle convection simulations
- Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
- Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model
- Terrain-aware Deep Learning for Wind Energy Applications: From Kilometer-scale Forecasts to Fine Wind Fields
- PhyDA: Physics-Guided Diffusion Models for Data Assimilation in Atmospheric Systems
- FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models
- Improving regional weather forecasts with neural interpolation
- Weather Research and Forecasting (WRF) Model and Machine Learning Algorithms to Improve Marine Fog Predictions at Two Coastal Locations in Atlantic Canada
- LanTu: Dynamics-Enhanced Deep Learning for Eddy-Resolving Ocean Forecasting
- LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Data
- Predicting Beyond Training Data via Extrapolation versus Translocation: AI Weather Models and Dubai's Unprecedented 2024 Rainfall
- RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours
- Towards scalable surrogate models based on Neural Fields for large scale aerodynamic simulations
- ExEBench: Benchmarking Foundation Models on Extreme Earth Events
- Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams
- Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere
- From AI Weather Prediction to Infrastructure Resilience: A Real-Time Correction-Downscaling Framework for Tropical Cyclone Impact Forecasting
- Latent Attention on Masked Patches for Flow Reconstruction
- SPIN-ODE: Stiff Physics-Informed Neural ODE for Chemical Reaction Rate Estimation
- Physics-Assisted and Topology-Informed Deep Learning for Weather Prediction
- Machine Learning for Physical Simulation Challenge Results and Retrospective Analysis: Power Grid Use Case
- AIFS-DOP: End-to-End Medium-Range Weather Prediction from Observations Alone with Machine Learning
- U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
- Towards Fair Comparisons of AI- and Physics-Based Weather Models for Extreme Events via the Weighted Potential CRPS
- Exascale Hybrid Numerical-AI Ensembles for Operational Flood-Season Forecasting in East Asia: 15-km Decadal Hindcasts and 1-km High-Resolution Capability
- Advancing Seasonal Prediction of Tropical Cyclone Activity with a Hybrid AI-Physics Climate Model
- Machine Learning (ML)-Physics Fusion Model Outperforms Both Physics-Only and ML-Only Models in Typhoon Predictions
- Quantifying the Influence of Climate on Storm Activity Using Machine Learning
- Atmospheric Predictability Beyond 30 Days with Machine Learning
- How Hyper-Datafication Impacts the Sustainability Costs in Frontier AI
- Error in ERA5 2m Temperature identified using GraphCast
- OpenFOAMGPT 2.0: end-to-end, trustworthy automation for computational fluid dynamics
- Towards Solving the Gilbert-Pollak Conjecture via Large Language Models
- Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation
- Transferable Dual-Stream Representations for Mesoscale-Preserving Sea Surface Temperature Downscaling
- EnsAI: An Emulator for Atmospheric Chemical Ensembles
- EIoT: Embodied Intelligence of Things
- A Physics-guided Multimodal Transformer Path to Weather and Climate Sciences
- Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations
- Temporal Bridges for Spatial Resolution: Enhancing Climate Data Super-Resolution with Bidirectional Alignment
- Dynamical errors in machine learning forecasts
- Air Quality Prediction with A Meteorology-Guided Modality-Decoupled Spatio-Temporal Network
- TianQuan-S2S: A Subseasonal-to-Seasonal Global Weather Model via Incorporate Climatology State
- Graph Neural Networks for Enhancing Ensemble Forecasts of Extreme Rainfall
- KunPeng: A Global Ocean Environmental Model
Related