Half-precision inference of AI weather prediction models: negligible loss of skill at a fraction of the cost
physics.ao-ph, cs.LG, cs.PF
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/sieste/ai-nwp-fp16
Project page: https://microsoft.github.io/aurora/models.html
Terminology
Sources
- The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research
- The Compute Divide in Machine Learning: A Threat to Academic Contribution and Scrutiny?
- Post-Training Quantization of Autoregressive Weather Models
- A Foundation Model for the Earth System
- PACT: Parameterized Clipping Activation for Quantized Neural Networks
- Technical overview and architecture of the FastNet Machine Learning weather prediction model, version 1.0
- LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
- FastNet: Improving the physical consistency of machine-learning weather prediction models through loss function design
- How to use and interpret activation patching
- A Study of BFLOAT16 for Deep Learning Training
- AIFS -- ECMWF's data-driven forecasting system
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- Locating and Editing Factual Associations in GPT
- Mixed Precision Training
- FP8 Formats for Deep Learning
- A White Paper on Neural Network Quantization
- FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
- Microscaling Data Formats for Deep Learning
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
Related papers
- Anthropogenic Heat in Urban Climate Systems: Forcing, Sensitivity, and Feedback
- NORi: An ML-Augmented Ocean Boundary Layer Parameterization
- A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling
- Skillful Thunderstorm Forecasts Learned Directly from Observations
- Wind vector retrieval from miniaturized wave-enabled sea-surface drifters
- Stochastic coupling of climate variables and ice volume over the Late Pleistocene glacial cycles