AERIS

Argonne Earth Systems Model for Reliable and Skillful Predictions

Sam Foreman
[email protected]

ALCF

2025-10-08

AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions

arXiv:2509.13523

Figure 1

High-Level Overview of AERIS

Figure 2: Rollout of AERIS model, specific humidity at 700m.
Table 1: Overview of AERIS model and training setup
Property Description
Domain Global
Resolution 0.25° & 1.4°
Training Data ERA5 (1979–2018)
Model Architecture Swin Transformer
Speedup1 O(10k–100k)
  1. Relative to PDE-based models, e.g.: GFS

Model Overview

  • Dataset: ECMWF Reanalysis v5 (ERA5)
  • Variables: Surface and pressure levels
  • Usage: Medium-range weather forecasting
  • Partition:
    • Train: 1979–2018
    • Val: 2019
    • Test: 2020
  • Data Size: 100GB at 5.6° to 31TB at 0.25°
Table 2: Variables used in AERIS training and prediction
Variable Description
t2m 2m Temperature
X u(v) uuu (vvv) wind component @ Xm
q Specific Humidity
z Geopotential
msl Mean Sea Level Pressure
sst Sea Surface Temperature
lsm Land-sea mask

Windowed Self-Attention

  • Benefits for weather modeling:
    • Shifted windows capture both local patterns and long-range context
    • Constant scale, windowed self-attention provides high-resolution forecasts
    • Designed (currently) for fixed, 2D grids
  • Inspiration from SOTA LLMs:
    • RMSNorm, SwiGLU, 2D RoPE
Figure 3: Windowed Self-Attention

Model Architecture: Details

Figure 4: Model Architecture

Sequence-Window-Pipeline Parallelism SWiPe

  • SWiPe is a novel parallelism strategy for Swin-based Transformers
  • Hybrid 3D Parallelism strategy, combining:
    • Sequence parallelism (SP)
    • Window parallelism (WP)
    • Pipeline parallelism (PP)
Figure 5
Figure 6: SWiPe Communication Patterns

🌌 Aurora

Table 3: Aurora Specs
Racks 166
Nodes 10,624
CPUs 21,248
GPUs 63,744
NICs 84,992
HBM 8 PB
DDR5c 10 PB
Figure 7: Aurora1: Fact Sheet.
  1. 🏆 Aurora Supercomputer Ranks Fastest for AI

🌎 AERIS: Scaling Results

Figure 8: AERIS: Scaling Results
  • 10 EFLOPs (sustained) @ 120,960 GPUs
  • See (Hatanpää et al. (2025)) for additional details
  • arXiv:2509.13523

References

Hatanpää, Väinö, Eugene Ku, Jason Stock, Murali Emani, Sam Foreman, Chunyong Jung, Sandeep Madireddy, et al. 2025. “AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions.” https://arxiv.org/abs/2509.13523.

samforeman.me/talks/2025/10/08/slides

1
AERIS Argonne Earth Systems Model for Reliable and Skillful Predictions Sam Foreman [email protected] ALCF 2025-10-08

  1. Slides

  2. Tools

  3. Close
  • AERIS
  • Slide 2
  • AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions
  • High-Level Overview of AERIS
  • Model Overview
  • Windowed Self-Attention
  • Model Architecture: Details
  • Sequence-Window-Pipeline Parallelism SWiPe
  • 🌌 Aurora
  • 🌎 AERIS: Scaling Results
  • References
  • f Fullscreen
  • s Speaker View
  • o Slide Overview
  • e PDF Export Mode
  • r Scroll View Mode
  • b Toggle Chalkboard
  • c Toggle Notes Canvas
  • d Download Drawings
  • ? Keyboard Help