mlsanityData to 14 Oct 2026

AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions

arXiv 2509.13523 ↗First posted 16 Sep 2025cs.LG cs.DCcited by 8

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Generative machine learning offers new opportunities to better understand complex Earth system dynamics. Recent diffusion-based methods address spectral biases and improve ensemble calibration in weather forecasting compared to deterministic methods, yet have so far proven difficult to scale stably at high resolutions. We introduce AERIS, a 1.3 to 80B parameter pixel-level Swin diffusion transformer to address this gap, and SWiPe, a generalizable technique that composes window parallelism with sequence and pipeline parallelism to shard window-based transformers without added communication cost or increased global batch size. On Aurora (10,080 nodes), AERIS sustains 10.21 ExaFLOPS (mixed precision) and a peak performance of 11.21 ExaFLOPS with 1 × 1 patch size on the 0.25deg ERA5 dataset, achieving 95.5% weak scaling efficiency, and 81.6% strong scaling efficiency. AERIS outperforms the IFS ENS and remains stable on seasonal scales to 90 days, highlighting the potential of billion-parameter diffusion models for weather and climate prediction.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 55 of its 85 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

55 of 85 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting17 Dec
  2. 2024DiffObs: Generative Diffusion for Global Forecasting of Satellite Observations4 Apr
  3. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling24 Sep
  4. 2023Improving and generalizing flow-based generative models with minibatch optimal transport1 Feb
  5. 2022Flow Matching for Generative Modeling6 Oct
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 49

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2020Scaling Laws for Neural Language Modelscited by 6,586
  8. 2022Scalable Diffusion Models with Transformerscited by 6,054
  9. 2023Qwen Technical Reportcited by 3,344
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  11. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  12. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
37 more
  1. 2020GLU Variants Improve Transformercited by 1,804
  2. 2019Root Mean Square Layer Normalizationcited by 1,480
  3. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  4. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  5. 2021Scaling Vision Transformerscited by 999
  6. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  7. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  8. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  9. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 694
  10. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 660
  11. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
  12. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 457
  13. 2023ClimaX: A foundation model for weather and climatecited by 337
  14. 2022Reducing Activation Recomputation in Large Transformer Modelscited by 302
  15. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 283
  16. 2020WeatherBench: A benchmark dataset for data-driven weather forecastingcited by 275
  17. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 267
  18. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 245
  19. 2023FuXi: A cascade machine learning forecasting system for 15-day global weather forecastcited by 241
  20. 2023WeatherBench 2: A benchmark for the next generation of data-driven global weather modelscited by 236
  21. 2024Rotary Position Embedding for Vision Transformercited by 236
  22. 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 177
  23. 2023FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Leadcited by 175
  24. 2022Forecasting Global Weather with Graph Neural Networkscited by 168
  25. 2022Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecastcited by 166
  26. 2022Earthformer: Exploring Space-Time Transformers for Earth System Forecastingcited by 152
  27. 2023Scaling transformer neural networks for skillful and reliable medium-range weather forecastingcited by 110
  28. 2020Improving data-driven global weather prediction using deep convolutional neural networks on a cubed spherecited by 96
  29. 2021Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction modelscited by 79
  30. 2024Scaling Laws For Diffusion Transformerscited by 44
  31. 2024On the Scalability of Diffusion-based Text-to-Image Generationcited by 36
  32. 2023Challenges of learning multi-scale dynamics with AI weather models: Implications for stability and one solutioncited by 31
  33. 2024FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecastingcited by 30
  34. 2021Combining distribution-based neural networks to predict weather forecast probabilitiescited by 18
  35. 2024ORBIT: Oak Ridge Base Foundation Model for Earth System Predictabilitycited by 17
  36. 2024Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Predictioncited by 15
  37. 2024Exploring the design space of deep-learning-based weather forecasting systemscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2025Swift: An Autoregressive Consistency Model for Efficient Weather Forecastingcited by 13
  2. 2026U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecastercited by 12
  3. 2026Latent Generative Solvers for Generalizable Long-Term Physics Simulationcited by 3
  4. 2026A Multimodal Vision Transformer-based Modeling Framework for Prediction of Fluid Flows in Energy Systemscited by 1
  5. 2026Dual-Scale Temporal Fusion Reveals Structured Predictability in Subseasonal-to-Seasonal Temperature Predictioncited by 0
  6. 2026TERRA: A Hierarchical Parallel Training and Memory Orchestration Framework for High-Resolution AI-based Earth Modelingcited by 0
  7. 20264D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modelingcited by 0
  8. 2026Hapi: A Multivariable Land-Surface Transformer for Medium-Range Hydrological Forecasting at Continental Scalecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion-Based Joint Temperature and Precipitation Emulation of Earth System Models
  2. 2024DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models with 3D Diffusion Models
  3. 2023DiffESM: Conditional Emulation of Earth System Models with Diffusion Models
  4. 2026Monthly Diffusion v0.9: A Latent Diffusion Model for the First AI-MIP
  5. 2025OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
  6. 2026COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data
  7. 2025How to use score-based diffusion in earth system science: A satellite nowcasting example
  8. 2026PuYun-LDM: A Latent Diffusion Model for High-Resolution Ensemble Weather Forecasts