Pith. sign in

REVIEW 33 cited by

FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2507.12144 v2 pith:7UQORXY5 submitted 2025-07-16 cs.LG physics.ao-ph

FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale

classification cs.LG physics.ao-ph
keywords fourcastnetprobabilisticforecastingapproachensembleadvancesapproachesgeometric
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting. The approach is designed to respect spherical geometry and to accurately model the spatially correlated probabilistic nature of the problem, resulting in stable spectra and realistic dynamics across multiple scales. FourCastNet 3 delivers forecasting accuracy that surpasses leading conventional ensemble models and rivals the best diffusion-based methods, while producing forecasts 8 to 60 times faster than these approaches. In contrast to other ML approaches, FourCastNet 3 demonstrates excellent probabilistic calibration and retains realistic spectra, even at extended lead times of up to 60 days. All of these advances are realized using a purely convolutional neural network architecture tailored for spherical geometry. Scalable and efficient large-scale training on 1024 GPUs and more is enabled by a novel training paradigm for combined model- and data-parallelism, inspired by domain decomposition methods in classical numerical models. Additionally, FourCastNet 3 enables rapid inference on a single GPU, producing a 60-day global forecast at 0.25{\deg}, 6-hourly resolution in under 4 minutes. Its computational efficiency, medium-range probabilistic skill, spectral fidelity, and rollout stability at subseasonal timescales make it a strong candidate for improving meteorological forecasting and early warning systems through large ensemble predictions.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 33 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Disentangling the effects of sea surface temperature and CO$_2$ in global machine learned weather-climate emulators

    physics.ao-ph 2026-06 unverdicted novelty 7.0

    Trains ACE emulator on independent SST-CO2 variations plus energy constraint to improve accuracy in decoupled climate forcing scenarios.

  2. The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench

    cs.LG 2026-05 unverdicted novelty 7.0

    Introduces the Perception-Physics Paradox and TC-Bench benchmark demonstrating that vision foundation models rely on visual shortcuts that fail in intense regimes rather than achieving scientific alignment via structu...

  3. The physics of AI weather models

    physics.ao-ph 2026-05 unverdicted novelty 7.0

    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.

  4. One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators

    stat.ML 2026-05 unverdicted novelty 7.0

    A single neural operator can approximate the map from arbitrary joint densities to their conditionals, backed by new continuity results and illustrated on Gaussian mixtures.

  5. Cast3: Translating numerical weather prediction principles into data-driven forecasting

    physics.ao-ph 2026-05 unverdicted novelty 7.0

    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.

  6. Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulators

    physics.ao-ph 2026-02 unverdicted novelty 7.0

    Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.

  7. SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints

    cs.LG 2026-02 unverdicted novelty 7.0

    SnareNet introduces a repair layer that navigates the range space of constraints plus adaptive relaxation training to enforce hard non-convex constraints on neural network outputs more reliably than prior methods.

  8. Weather Emulators at the Frontier of Heat Extremes Predictability

    physics.ao-ph 2026-07 accept novelty 6.0

    At 10–15 day leads, AI weather emulators can match or beat dynamical models on global temperature skill but under-represent heat-extreme intensity and lose to IFS on recall.

  9. Orca: Neural Operators for Causal Reasoning in Continuous Time

    cs.AI 2026-07 conditional novelty 6.0

    Orca extends structural causal models to continuous time with neural operators, enabling resolution-invariant dose-response and counterfactual trajectories on irregularly sampled cyclic systems.

  10. Decision-Aware Training for Sample-Based Generative Models

    cs.LG 2026-07 unverdicted novelty 6.0

    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 an...

  11. Fourier Neural Operators with rank-1 lattice points and hyperbolic cross

    math.NA 2026-06 unverdicted novelty 6.0

    Rank-1 lattice points and hyperbolic crosses are shown to improve the generalization error and efficiency of Fourier neural operators for PDE approximation on the torus.

  12. Physics-Guided Dual Decoding and Spectral Supervision for Global 3D Hydrometeor Prediction

    cs.LG 2026-06 unverdicted novelty 6.0

    PredHydro-Net is a new dual-decoding architecture with wavelet spectral matching and adversarial training that outperforms Earthformer, PredRNNv2, and GFS on extreme-event detection and spectral fidelity in 72-hour gl...

  13. Disentangling the effects of sea surface temperature and CO$_2$ in global machine learned weather-climate emulators

    physics.ao-ph 2026-06 conditional novelty 6.0

    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.

  14. Samudra 2: Scaling Ocean Emulators across Resolutions

    cs.CE 2026-05 unverdicted novelty 6.0

    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.

  15. Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting

    cs.LG 2026-05 unverdicted novelty 6.0

    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.

  16. Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting

    cs.LG 2026-05 unverdicted novelty 6.0

    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.

  17. ShardTensor: Domain Parallelism for Scientific Machine Learning

    cs.DC 2026-05 unverdicted novelty 6.0

    ShardTensor is a domain-parallelism system for SciML that enables flexible scaling of extreme-resolution spatial datasets by removing the constraint of batch size one per device.

  18. One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators

    stat.ML 2026-05 unverdicted novelty 6.0

    A single neural operator can approximate the map from joint densities to conditional densities to arbitrary accuracy, with a proof based on continuity of the conditioning operator and a demonstration on Gaussian mixtures.

  19. Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting

    physics.ao-ph 2026-04 unverdicted novelty 6.0

    ESFM is a single open foundation model that unifies heterogeneous Earth data sources and forecasts missing regions while preserving inter-variable physical relationships.

  20. U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

    cs.LG 2026-04 conditional novelty 6.0

    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...

  21. Physics constraints and response validation in discrete-time reduced-order modeling: from idealized turbulent systems to climate dynamics

    nlin.CD 2026-02 conditional novelty 6.0

    A discrete-time energy-conserving neural map with FDT-derived causal regularization reproduces stationary statistics and forced responses of CdV and Lorenz-96 turbulence from unperturbed data alone.

  22. Physics constraints and response validation in discrete-time reduced-order modeling: from idealized turbulent systems to climate dynamics

    nlin.CD 2026-02 unverdicted novelty 6.0

    A framework builds stable neural models of turbulent dynamics by enforcing energy-preserving nonlinearities and causal constraints in discrete-time flow maps, demonstrated on Charney-DeVore and Lorenz-96 systems.

  23. Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems

    cs.LG 2026-02 unverdicted novelty 6.0

    Multi-scale wavelet transformers learn operator dynamics of chaotic systems in the wavelet domain, yielding lower errors and higher spectral fidelity on benchmarks and ERA5 climate data.

  24. HealDA: Highlighting the importance of initial errors in end-to-end AI weather forecasts

    physics.ao-ph 2026-01 conditional novelty 6.0

    HealDA supplies ML-based initial conditions for AI weather models that produce forecasts trailing ERA5-initialized runs by less than one day of effective lead time, with the skill gap arising mainly from initial error size.

  25. From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

    cs.AI 2026-07 accept novelty 5.0

    The paper proposes Mechanistic World Models — models organized as typed latent variables, a reusable mechanism library, and binding structures — as the route from AI forecasting to autonomous discovery.

  26. From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

    cs.AI 2026-07 unverdicted novelty 5.0

    Mechanistic World Models reframe AI scientific discovery as knowledge organisation around reusable explanatory mechanisms rather than predictive input–output mappings.

  27. Deep learning model emulators for marine biogeochemistry forecasting from days to decades

    q-bio.QM 2026-06 unverdicted novelty 5.0

    LSTM and 1D CNN emulators replicate a 1D marine biogeochemistry model at daily resolution, remain stable over decades, reproduce spring bloom timing years ahead, and outperform the parent model on reanalysis-driven fo...

  28. Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting

    cs.LG 2026-06 unverdicted novelty 5.0

    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.

  29. Reliability of Probabilistic Emulation of Physical Systems

    cs.LG 2026-06 unverdicted novelty 5.0

    CRPS-trained ensembles achieve better uncertainty reliability and speed than latent generative models for probabilistic emulation of 2D physical systems.

  30. U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

    cs.LG 2026-04 conditional novelty 5.0

    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×.

  31. Towards Scaling Law Analysis For Spatiotemporal Weather Data

    cs.LG 2026-04 unverdicted novelty 5.0

    Scaling laws for weather models exhibit strong cross-channel and cross-horizon heterogeneity, where globally pooled metrics appear favorable while many individual channels degrade at longer leads.

  32. CRPS-LAM: Probabilistic Regional Weather Forecasting with Continuous Ranked Probability Score

    cs.LG 2025-10 conditional novelty 5.0

    CRPS-LAM produces 57-hour probabilistic limited-area forecasts on MEPS at diffusion-comparable accuracy with single-forward-pass sampling, roughly 39x faster than Diffusion-LAM.

  33. The Rise of AI in Weather and Climate Information and its Impact on Global Inequality

    physics.ao-ph 2026-03 conditional novelty 4.0

    AI weather and climate tools inherit Northern-controlled data and compute, risking worse forecasts and maladaptation for the Global South rather than democratizing climate information.