Pith. sign in

REVIEW 23 cited by

A Foundation Model for the Earth System

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 2405.13063 v3 pith:XIZM7FWR submitted 2024-05-20 physics.ao-ph cs.LG

classification physics.ao-phcs.LG
keywords auroraearthsystemcomputationaldiversedomainsforecastsfoundation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reliable forecasts of the Earth system are crucial for human progress and safety from natural disasters. Artificial intelligence offers substantial potential to improve prediction accuracy and computational efficiency in this field, however this remains underexplored in many domains. Here we introduce Aurora, a large-scale foundation model for the Earth system trained on over a million hours of diverse data. Aurora outperforms operational forecasts for air quality, ocean waves, tropical cyclone tracks, and high-resolution weather forecasting at orders of magnitude smaller computational expense than dedicated existing systems. With the ability to fine-tune Aurora to diverse application domains at only modest computational cost, Aurora represents significant progress in making actionable Earth system predictions accessible to anyone.

Discussion (0). Sign in to comment.

Forward citations

Cited by 23 Pith papers

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

  1. When to Align, When to Predict: A Phase Diagram for Multimodal Learning

    cs.LG 2026-06 accept novelty 7.0 of 10

    A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.

  2. Does Your Wildfire Prediction Model Actually Work, or Just Score Well?

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    WILDFIRE-FM is the first wildfire-specific Earth foundation model, paired with a fixed-contract evaluation framework that demonstrates wildfire model transfer conclusions depend strongly on evaluation design and task ...

  3. Controlling Transient Amplification Improves Long-horizon Rollouts

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Commutativity regularization on Jacobians reduces transient error amplification in neural simulators, enabling stable rollouts over thousands of steps on physical and climate data.

  4. QuadNorm: Resolution-Robust Normalization for Neural Operators

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    QuadNorm uses quadrature-based moments instead of uniform averaging in normalization layers, achieving O(h²) consistency across resolutions and better cross-resolution transfer in neural operators.

  5. GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations

    physics.plasm-ph 2025-10 conditional novelty 7.0 of 10

    GyroSwin predicts 5D gyrokinetic plasma turbulence autoregressively, matching heat-flux and turbulence spectra of GKW simulations at a fraction of the cost.

  6. PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    PhysMetrics.Weather is an evaluation framework that quantifies physical realism of ML weather prediction models using conservation, spectral, and dynamical metrics.

  7. AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    AdaWeather adaptively mixes probabilistic weather forecasts and achieves logarithmic regret relative to the best static mixture of experts in hindsight.

  8. Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    WaveLiT combines wavelet tokenization, linear attention, and multiscale pyramids to produce parameter-efficient neural PDE solvers that match much larger models on TheWell benchmarks.

  9. CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora

    cs.CY 2026-05 unverdicted novelty 6.0 of 10

    CourseBlueprint builds a typed pipeline over a 23-lecture biomedical imaging corpus to generate prerequisite-aware, learner-adaptive videos with auditable engagement contracts and slide grounding.

  10. Does Your Wildfire Prediction Model Actually Work, or Just Score Well?

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Introduces WILDFIRE-FM and a fixed-contract evaluation framework demonstrating that wildfire model transfer conclusions depend strongly on evaluation design and task formulation.

  11. Intervention-Based Time Series Causal Discovery via Simulator-Generated Interventional Distributions

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    SVAR-FM uses simulator clamping to produce interventional distributions and flow matching to identify time series causal structures, with an error bound that predicts sign reversal of causal effects below a simulator ...

  12. Controlling Transient Amplification Improves Long-horizon Rollouts

    cs.LG 2026-05 conditional novelty 6.0 of 10

    Commutativity regularization mitigates transient error amplification in autoregressive neural simulators by penalizing non-normality and non-commutativity of Jacobians, yielding stable long-horizon rollouts.

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

    cs.LG 2026-04 conditional novelty 6.0 of 10

    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...

  14. Scaling Laws of Global Weather Models

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Across five global weather models, validation loss follows power-law scaling, with wider architectures and larger training datasets outperforming deeper or smaller-data configurations.

  15. Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs

    cs.LG 2026-02 conditional novelty 6.0 of 10

    A geometry-conditioned Whitney-form neural network that solves a learned discrete conservation law improves out-of-distribution geometry generalization for steady-state PDEs compared with regression-based neural operators.

  16. Pixel-Resolved Long-Context Learning for Turbulence at Exascale: Resolving Small-scale Eddies Toward the Viscous Limit

    physics.flu-dyn 2025-07 conditional novelty 6.0 of 10

    A multiscale transformer with a new collective-based parallel attention method is claimed to be the first deep-learning model to reproduce small-scale turbulence statistics down to the viscous limit in 3D flow.

  17. How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size

    cs.LG 2026-07 unverdicted novelty 5.0 of 10

    Proposes a three-term scaling law for model size, training steps and batch size that recovers optimal batch size scaling and can be fitted using fewer runs by incorporating suboptimal batch sizes.

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

    cs.LG 2026-04 conditional novelty 5.0 of 10

    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×.

  19. Agentic Physical AI toward a Domain-Specific Foundation Model for Nuclear Reactor Control

    cs.AI 2025-12 unverdicted novelty 5.0 of 10

    A compact language model trained on scaled synthetic nuclear reactor control data exhibits variance collapse and emergent concentration on a single actuation strategy driven by physical execution success.

  20. Does Aurora Encode Atmospheric Structure? Latent Regime Analysis and Attribution

    cs.LG 2026-06 unverdicted novelty 4.0 of 10

    Aurora's latent space is organized by seasonal cycles with evidence of encoding 3D vertical atmospheric structure for storms, confirmed by perturbation experiments.

  21. EPT-2 Technical Report

    cs.LG 2025-07 conditional novelty 4.0 of 10

    EPT-2 is a 9 km global AI weather model reported to beat Aurora, IFS HRES, and the ECMWF ENS mean over 0 to 240 hours on energy-relevant variables.

  22. Foundation Models for Clean Energy Forecasting: A Comprehensive Review

    eess.SY 2025-07 conditional novelty 3.0 of 10

    A survey of foundation model methods, data, and open problems for renewable energy forecasting, built from roughly 218 cited works.

  23. Toward Artificial Intelligence Enabled Earth System Coupling

    physics.ao-ph 2026-03 unverdicted novelty 2.0 of 10

    AI methods can strengthen cross-domain interactions and support more coherent multi-component representations in Earth system models.

Pith tools