WeatherBench 2: A benchmark for the next generation of data-driven global weather models
Not on the map. Why?
Cited by 22 in Diffusion models, but placed by its own abstract, which didn’t fit.
Abstract (arXiv)
WeatherBench 2 is an update to the global, medium-range (1-14 day) weather forecasting benchmark proposed by Rasp et al. (2020), designed with the aim to accelerate progress in data-driven weather modeling. WeatherBench 2 consists of an open-source evaluation framework, publicly available training, ground truth and baseline data as well as a continuously updated website with the latest metrics and state-of-the-art models: https://sites.research.google/weatherbench. This paper describes the design principles of the evaluation framework and presents results for current state-of-the-art physical and data-driven weather models. The metrics are based on established practices for evaluating weather forecasts at leading operational weather centers. We define a set of headline scores to provide an overview of model performance. In addition, we also discuss caveats in the current evaluation setup and challenges for the future of data-driven weather forecasting.
Key facts. Cited by 236 papers in the map (data through 14 Oct 2026). Builds on 21 of its 65 references that are in the map. First posted on arXiv 29 Aug 2023.
Builds on
21 of 65 references.
References · 21
- 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
- 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
- 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
- 2023ClimaX: A foundation model for weather and climatecited by 337
- 2020WeatherBench: A benchmark dataset for data-driven weather forecastingcited by 275
- 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 267
- 2021Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformerscited by 248
- 2023FuXi: A cascade machine learning forecasting system for 15-day global weather forecastcited by 241
- 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 233
- 2023FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Leadcited by 175
- 2022Forecasting Global Weather with Graph Neural Networkscited by 168
- 2020Improving data-driven global weather prediction using deep convolutional neural networks on a cubed spherecited by 96
9 more
- 2018Neural networks for post-processing ensemble weather forecastscited by 95
- 2023Deep Learning for Day Forecasts from Sparse Observationscited by 72
- 2020Deep Learning for Post-Processing Ensemble Weather Forecastscited by 52
- 2023SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecastingcited by 32
- 2023Scaling Spherical CNNscited by 21
- 2021Combining distribution-based neural networks to predict weather forecast probabilitiescited by 18
- 2022WeatherBench Probability: A benchmark dataset for probabilistic medium-range weather forecasting along with deep learning baseline modelscited by 17
- 2022ENS-10: A Dataset For Post-Processing Ensemble Weather Forecastscited by 13
- 2021Self-Attentive Ensemble Transformer: Representing Ensemble Interactions in Neural Networks for Earth System Modelscited by 7
Built on by
Citing papers per year: 2023: 10; 2024: 47; 2025: 82; 2026: 97.
236 papers.
Sort:
By area:
- 2023Neural General Circulation Models for Weather and Climatecited by 239
- 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 177
- 2023Scaling transformer neural networks for skillful and reliable medium-range weather forecastingcited by 110
- 2024ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEscited by 82
- 2025FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scalecited by 62
- 2024DiffDA: a Diffusion Model for Weather-scale Data Assimilationcited by 61
- 2025MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answeringcited by 55
- 2024ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responsescited by 54
- 2024ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Predictioncited by 43
- 2023Foundation Models for Weather and Climate Data Understanding: A Comprehensive Surveycited by 34
- 2025OneForecast: A Universal Framework for Global and Regional Weather Forecastingcited by 34
- 2024On the Foundations of Earth and Climate Foundation Modelscited by 33
38 more
- 2024Prithvi WxC: Foundation Model for Weather and Climatecited by 31
- 2024FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecastingcited by 30
- 2024Probabilistic Weather Forecasting with Hierarchical Graph Neural Networkscited by 30
- 2023Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Meshcited by 28
- 2025Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Functioncited by 28
- 2024Uncertainty quantification for data-driven weather modelscited by 26
- 2024Can AI weather models predict out-of-distribution gray swan tropical cyclones?cited by 26
- 2023ClimateSet: A Large-Scale Climate Model Dataset for Machine Learningcited by 25
- 2024A Practical Probabilistic Benchmark for AI Weather Modelscited by 25
- 2023Graph-based Neural Weather Prediction for Limited Area Modelingcited by 22
- 2023FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion modelcited by 22
- 2023Towards an end-to-end artificial intelligence driven global weather forecasting systemcited by 21
- 2024Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Modelcited by 21
- 2024Probabilistic Emulation of a Global Climate Model with Spherical DYffusioncited by 21
- 2025Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilationcited by 20
- 2024Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operatorscited by 18
- 2025Probabilistic neural operators for functional uncertainty quantificationcited by 18
- 2024ORBIT: Oak Ridge Base Foundation Model for Earth System Predictabilitycited by 17
- 2025Deep Learning and Foundation Models for Weather Prediction: A Surveycited by 16
- 2024Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Predictioncited by 15
- 2023WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correctioncited by 14
- 2024Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Eventscited by 14
- 2025CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformercited by 14
- 2025Numerical models outperform AI weather forecasts of record-breaking extremescited by 14
- 2024FuXi-ENS: A machine learning model for medium-range ensemble weather forecastingcited by 13
- 2025Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamicscited by 13
- 2025Swift: An Autoregressive Consistency Model for Efficient Weather Forecastingcited by 13
- 2025OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scalescited by 12
- 2026U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecastercited by 12
- 2024Uncertainty Quantification of Surrogate Models using Conformal Predictioncited by 11
- 2024FuXi-2.0: Advancing machine learning weather forecasting model for practical applicationscited by 11
- 2026Recursive self-improvement of AI research agentscited by 11
- 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
- 2025ZAPBench: A Benchmark for Whole-Brain Activity Prediction in Zebrafishcited by 10
- 2025Zephyrus: An Agentic Framework for Weather Sciencecited by 10
- 2025ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Modelscited by 9
- 2026Scaling Laws of Global Weather Modelscited by 9
- 2024EWMoE: An effective model for global weather forecasting with mixture-of-expertscited by 8
50 most cited of 236 All 236 (JSON)
- 2026Mesh-Free Convolution: Learned Spectral Attenuation and Transport11 Oct 2026
- 2026EarthAlign: Learning Language-Aligned Representations of Earth System Data10 Oct 2026
- 2026Cross-Domain Pretraining for Steady-State Neural CFD Surrogates7 Oct 2026
- 2026Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior5 Oct 2026
- 2026SO(3)-RoPE for Spherical Transformers5 Oct 2026
- 2026FlexCast: Adaptive Weather Forecasting from Arbitrary Field Sets4 Oct 2026
- 2026S3N: A Spherical Spiral Scanning Network for Weather Forecasting3 Oct 2026
- 2026SDECast: Probabilistic Weather Forecasting in Continuous Time with Neural SDEs2 Oct 2026
- 2026Post-Training Quantization of Autoregressive Weather Models1 Oct 2026
- 2026Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography1 Oct 2026
- 2026Proper Scoring Rule-based Diffusion for Probabilistic Weather Forecasting29 Sep 2026
- 2026Evaluating Dynamical Fidelity through Predictive Structure in Physical Representations28 Sep 2026
38 more
- 2026ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations26 Sep 2026
- 2026Suitable Measures for the Potential Operational Utility of AI NWP Rainfall Forecasts Over Africa24 Sep 2026
- 2026Recursive self-improvement of AI research agents22 Sep 2026
- 2026JEPA-Anything: Learning Predictive Models across Different Worlds17 Sep 2026
- 2026Butterfly Effect and the Kinetic Energy Cascade in Probabilistic Machine Learning Weather Prediction Models16 Sep 2026
- 2026Every Fixed Metric Has a Blind Spot: A Learned Atmospheric Critic for Scoring Forecast Realism16 Sep 2026
- 2026Physically Typed and Geometry-Aware Representations for Earth Foundation Models12 Sep 2026
- 2026Large Distant Gradients Need Not Be Reliable: reliability-weighted credit assignment for long-horizon autoregressive forecasting11 Sep 2026
- 20264D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling11 Sep 2026
- 2026Stochastically Perturbed Weights: Ensembles from Deterministic Machine-Learning Weather Models8 Sep 2026
- 2026Too Rare to Learn: Prescribed Cyclone Tracks Degrade a Bay of Bengal Ocean Emulator4 Sep 2026
- 2026WeatherNext 3: Increasing resolution and performance of global weather models with raw observations3 Sep 2026
- 2026Improving global precipitation forecasts with an AI weather model trained on satellite observations2 Sep 2026
- 2026TC-Next: Zero-Shot Multimodal Cyclone Forecasting2 Sep 2026
- 2026Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions31 Aug 2026
- 2026Diffusion Distillation for Efficient Weather Ensembles27 Aug 2026
- 2026Dandelion: A Spherical Flower for Neural Simulation of Planetary Dynamics27 Aug 2026
- 2026Missing the Butterfly and Predicting the Past: Features or Bugs of Accurate AI Weather Models?26 Aug 2026
- 2026A Station-Based Evaluation of Machine Learning-based Weather Forecasting Models in Northern Norway25 Aug 2026
- 2026Earth observation embeddings are effective sub-grid descriptors for probabilistic weather downscaling12 Aug 2026
- 2026VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting10 Aug 2026
- 2026Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling31 Jul 2026
- 2026Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulator30 Jul 2026
- 2026A foundation model of numerical intelligence with cross-disciplinary generalization30 Jul 2026
- 2026Can Deep Generative Models Reproduce Non-Stationary Gaussian Random Fields?28 Jul 2026
- 2026SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents27 Jul 2026
- 2026An adaptive and evolvable deep reinforcement learning framework for weather prediction7 Jul 2026
- 2026Integrating GNSS-Derived Zenith Wet Delay into a Weather Foundation Model Improves Precipitation Forecasting6 Jul 2026
- 2026Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction2 Jul 2026
- 2026Conditional Tropical Cyclogenesis Rates via Rare-Event Sampling in a Neural Weather Emulator29 Jun 2026
- 2026Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting24 Jun 2026
- 2026A Hybrid LSTM--Vision Transformer Architecture for Predicting HRRR Forecast Errors17 Jun 2026
- 2026ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets16 Jun 2026
- 2026DYNA-PRUNER: Input-Adaptive Data-Model Co-Pruning for Efficient and Scalable Spatio-Temporal Media Prediction13 Jun 2026
- 2026PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models9 Jun 2026
- 2026Physics-Guided Dual Decoding and Spectral Supervision for Global 3D Hydrometeor Prediction7 Jun 2026
- 2026Performance Evaluation of GraphCast for Medium-Range Weather Forecasting over Brazil4 Jun 2026
- 2026Scalable Uncertainty Quantification for Extreme Weather Forecasting via Empirical Neural Tangent Kernels1 Jun 2026
50 newest of 236 All 236 (JSON)
- 2024DiffDA: a Diffusion Model for Weather-scale Data Assimilationcited by 61
- 2023FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion modelcited by 22
- 2025Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilationcited by 20
- 2025Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamicscited by 13
- 2025Swift: An Autoregressive Consistency Model for Efficient Weather Forecastingcited by 13
- 2025OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scalescited by 12
- 2025AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictionscited by 8
- 2025LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecastingcited by 6
- 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferencescited by 5
- 2025Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priorscited by 5
- 2025DiffScale: Continuous Downscaling and Bias Correction of Subseasonal Wind Speed Forecasts using Diffusion Modelscited by 3
- 2025ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matchingcited by 3
12 most cited of 22 All 22 (JSON)
- 2026Diffusion Distillation for Efficient Weather Ensembles27 Aug 2026
- 2026Can Deep Generative Models Reproduce Non-Stationary Gaussian Random Fields?28 Jul 2026
- 2026Guided Diffusion Sampling for Precipitation Forecast Interventions14 May 2026
- 2026Super-Resolving Coarse-Resolution Weather Forecasts With Flow Matching1 Apr 2026
- 2026Climate Prompting: Generating the Madden-Julian Oscillation using Video Diffusion and Low-Dimensional Conditioning23 Mar 2026
- 2026PuYun-LDM: A Latent Diffusion Model for High-Resolution Ensemble Weather Forecasts12 Feb 2026
- 2026FlowDA: Accurate, Low-Latency Weather Data Assimilation via Flow Matching6 Feb 2026
- 2026Accelerated Sequential Flow Matching: A Bayesian Filtering Perspective5 Feb 2026
- 2025OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales20 Oct 2025
- 2025Quantile Regression, Variational Autoencoders, and Diffusion Models for Uncertainty Quantification: A Spatial Analysis of Sub-seasonal Wind Speed Prediction19 Oct 2025
- 2025Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priors13 Oct 2025
- 2025Improved probabilistic regression using diffusion models6 Oct 2025
12 newest of 22 All 22 (JSON)
- 2026Recursive self-improvement of AI research agentscited by 11
- 2025Zephyrus: An Agentic Framework for Weather Sciencecited by 10
- 2025Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reportingcited by 2
- 2026HVR-Met: A Hypothesis-Verification-Replanning Agentic System for Extreme Weather Diagnosiscited by 2
- 2026SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agentscited by 2
- 2026ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstationscited by 0
- 2026ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations26 Sep 2026
- 2026Recursive self-improvement of AI research agents22 Sep 2026
- 2026SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents27 Jul 2026
- 2026HVR-Met: A Hypothesis-Verification-Replanning Agentic System for Extreme Weather Diagnosis1 Mar 2026
- 2025Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reporting28 Nov 2025
- 2025Zephyrus: An Agentic Framework for Weather Science5 Oct 2025
- 2026Mechanistic Interpretability Tool for AI Weather Modelscited by 2
- 2026Mechanistic Interpretability Tool for AI Weather Models22 Apr 2026
- 2023Neural General Circulation Models for Weather and Climatecited by 239
- 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 177
- 2023Scaling transformer neural networks for skillful and reliable medium-range weather forecastingcited by 110
- 2024ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEscited by 82
- 2025FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scalecited by 62
- 2024ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responsescited by 54
- 2024ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Predictioncited by 43
- 2023Foundation Models for Weather and Climate Data Understanding: A Comprehensive Surveycited by 34
- 2025OneForecast: A Universal Framework for Global and Regional Weather Forecastingcited by 34
- 2024On the Foundations of Earth and Climate Foundation Modelscited by 33
- 2024Prithvi WxC: Foundation Model for Weather and Climatecited by 31
- 2024FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecastingcited by 30
12 most cited of 200 All 200 (JSON)
- 2026Mesh-Free Convolution: Learned Spectral Attenuation and Transport11 Oct 2026
- 2026EarthAlign: Learning Language-Aligned Representations of Earth System Data10 Oct 2026
- 2026Cross-Domain Pretraining for Steady-State Neural CFD Surrogates7 Oct 2026
- 2026Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior5 Oct 2026
- 2026SO(3)-RoPE for Spherical Transformers5 Oct 2026
- 2026FlexCast: Adaptive Weather Forecasting from Arbitrary Field Sets4 Oct 2026
- 2026S3N: A Spherical Spiral Scanning Network for Weather Forecasting3 Oct 2026
- 2026SDECast: Probabilistic Weather Forecasting in Continuous Time with Neural SDEs2 Oct 2026
- 2026Post-Training Quantization of Autoregressive Weather Models1 Oct 2026
- 2026Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography1 Oct 2026
- 2026Proper Scoring Rule-based Diffusion for Probabilistic Weather Forecasting29 Sep 2026
- 2026Evaluating Dynamical Fidelity through Predictive Structure in Physical Representations28 Sep 2026
12 newest of 200 All 200 (JSON)