mlsanityData to 7 Oct 2026

ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses

arXiv 2411.11268 ↗First posted 18 Nov 2024physics.ao-ph cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

Existing machine learning models of weather variability are not formulated to enable assessment of their response to varying external boundary conditions such as sea surface temperature and greenhouse gases. Here we present ACE2 (Ai2 Climate Emulator version 2) and its application to reproducing atmospheric variability over the past 80 years on timescales from days to decades. ACE2 is a 450M-parameter autoregressive machine learning emulator, operating with 6-hour temporal resolution, 1deg horizontal resolution and eight vertical layers. It exactly conserves global dry air mass and moisture and can be stepped forward stably for arbitrarily many steps with a throughput of about 1500 simulated years per wall clock day. ACE2 generates emergent phenomena such as tropical cyclones, the Madden Julian Oscillation, and sudden stratospheric warmings. Furthermore, it accurately reproduces the atmospheric response to El Ni~no variability and global trends of temperature over the past 80 years. However, its sensitivities to separately changing sea surface temperature and carbon dioxide are not entirely realistic.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 14 of its 71 references that are in the map. First posted on arXiv 18 Nov 2024.

Builds on

14 of 71 references.

References · 14

  1. 2021Machine learning accelerated computational fluid dynamicscited by 461
  2. 2023FuXi: A cascade machine learning forecasting system for 15-day global weather forecastcited by 237
  3. 2023Neural General Circulation Models for Weather and Climatecited by 232
  4. 2023WeatherBench 2: A benchmark for the next generation of data-driven global weather modelscited by 227
  5. 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 225
  6. 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 169
  7. 2020Improving data-driven global weather prediction using deep convolutional neural networks on a cubed spherecited by 95
  8. 2020Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 modelcited by 72
  9. 2023ACE: A fast, skillful learned global atmospheric model for climate predictioncited by 53
  10. 2024LUCIE: A Lightweight Uncoupled ClImate Emulator with long-term stability and physical consistency for O(1000)-member ensemblescited by 30
  11. 2023Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Meshcited by 27
  12. 2021Climate-Invariant Machine Learningcited by 24
2 more
  1. 2024Probabilistic Emulation of a Global Climate Model with Spherical DYffusioncited by 21
  2. 2024Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operatorscited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 27; 2026: 25.

53 papers.

Sort:

By area:

  1. 2025SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulatorscited by 15
  2. 2025Numerical models outperform AI weather forecasts of record-breaking extremescited by 14
  3. 2026Demystifying Data-Driven Probabilistic Medium-Range Weather Forecastingcited by 12
  4. 2025Simultaneous emulation and downscaling with physically-consistent deep learning-based regional ocean emulatorscited by 8
  5. 2025Generative assimilation and prediction for weather and climatecited by 7
  6. 2025Probing forced responses and causality in data-driven climate emulators: conceptual limitations and the role of reduced-order modelscited by 6
  7. 2024What You See is Not What You Get: Neural Partial Differential Equations and The Illusion of Learningcited by 5
  8. 2025CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraintscited by 5
  9. 2025Dynamical errors in machine learning forecastscited by 5
  10. 2025Causal Climate Emulation with Bayesian Filteringcited by 5
  11. 2025PEAR: Equal Area Weather Forecasting on the Spherecited by 4
  12. 2025CERA: A Framework for Improved Generalization of Machine Learning Models to Changed Climatescited by 4
38 more
  1. 2025Spatiotemporal Pyramid Flow Matching for Climate Emulationcited by 4
  2. 2026FloeNet: A mass-conserving global sea ice emulator that generalizes across climatescited by 4
  3. 2025Finetuning a Weather Foundation Model with Lightweight Decoders for Unseen Physical Processescited by 3
  4. 2025Deep Learning Atmospheric Models Reliably Simulate Out-of-Sample Land Heat and Cold Wave Frequenciescited by 3
  5. 2025LUCIE-3D: A three-dimensional climate emulator for forced responsescited by 3
  6. 2025ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matchingcited by 3
  7. 2025Bridging Idealized and Operational Models: An Explainable AI Framework for Earth System Emulatorscited by 3
  8. 2025Forecasting the Future with Yesterday's Climate: Temperature Bias in AI Weather and Climate Modelscited by 2
  9. 2025Reframing Generative Models for Physical Systems using Stochastic Interpolantscited by 2
  10. 2025AI-boosted rare event sampling to characterize extreme weathercited by 2
  11. 2025Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Modelscited by 2
  12. 2026WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modelingcited by 2
  13. 2026Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rolloutscited by 2
  14. 2025Data-driven Seasonal Climate Predictions via Variational Inference and Transformerscited by 1
  15. 2025Advancing Seasonal Prediction of Tropical Cyclone Activity with a Hybrid AI-Physics Climate Modelcited by 1
  16. 2025A machine learning model for skillful climate system predictioncited by 1
  17. 2025The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warmingcited by 1
  18. 2025Benchmarking atmospheric circulation variability in an AI emulator, ACE2, and a hybrid model, NeuralGCMcited by 1
  19. 2026Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulatorscited by 1
  20. 2026Skillful Global Ocean Emulation and the Role of Correlation-Aware Losscited by 1
  21. 2026Towards accurate extreme event likelihoods from diffusion model climate emulatorscited by 1
  22. 2026Evaluating Skill and Stability of ArchesWeather and ArchesWeatherGen under Multi-Decadal Climate Simulationscited by 1
  23. 2026Samudra 2: Scaling Ocean Emulators across Resolutionscited by 1
  24. 2026ADDA: a Modular Framework for Representing, Simulating and Assimilating Dynamics with End-to-end Differentiabilitycited by 1
  25. 2025Capturing Unseen Spatial Heat Extremes Through Dependence-Aware Generative Modelingcited by 0
  26. 2025Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperaturecited by 0
  27. 2026Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learningcited by 0
  28. 2026How Can Machine Learning Emulators Best Support Climate Science?cited by 0
  29. 2026Isotropic Fourier Neural Operatorscited by 0
  30. 2026No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisationcited by 0
  31. 2026Recursive Flow Matchingcited by 0
  32. 2026Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planetcited by 0
  33. 2026Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulatorcited by 0
  34. 2026Stochastic Emulation of a Fully Coupled Preindustrial E3SMv3 Simulationcited by 0
  35. 2026Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamicscited by 0
  36. 2026Missing the Butterfly and Predicting the Past: Features or Bugs of Accurate AI Weather Models?cited by 0
  37. 2026A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modelingcited by 0
  38. 2026Neptune: An AI model for Global Ocean Subseasonal Predictioncited by 0

50 most cited of 53 All 53 (JSON)