AI Insight
This study examines the application of post-training quantization (PTQ) techniques to artificial intelligence weather forecasting models, specifically testing it on Deep Learning Weather Prediction (DLWP) and FourCastNet (FCN) models. The researchers found that PTQ can reduce computational requirements and power consumption in these autoregressive weather emulators while maintaining qualitatively meaningful short-range forecasts. This represents the first benchmark investigation of quantization techniques applied to AI-based weather prediction systems.
Why it matters
Post-training quantization could enable AI weather models to run on less powerful hardware with reduced energy consumption, potentially making advanced weather forecasting more accessible and deployable on edge devices. This optimization approach may facilitate higher-resolution weather predictions and more widespread implementation of AI-based forecasting systems, particularly in resource-constrained environments.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Advancements in high-resolution numerical weather prediction (NWP) and data assimilation (DA) have shaped the developments in deep learning (DL) architectures emulating atmospheric dynamics. Emulators for weather forecasting exhibit forecast quality comparable to physics based models at forecast horizon scaling from few days to subseasonal time scales. The emulators are driven by hardware-accelerated matrix multiplication in autoregressive inferences, significantly reducing the computation time and resources required for NWP. Optimization of the matrix multiplication processes in GPU architectures provides opportunities to scale towards high-resolution domain, and offers implementation of out of the box solutions. Post-training quantization (PTQ) has been demonstrated across multiple DL architectures to accelerate and increase the number of computations in unit time while consuming less power, enabling applications on edge hardware. In this study, we investigate the effect of PTQ on pre-trained AI emulators for global-scale weather forecasting. We implement PTQ algorithms in Deep Learning Weather Prediction (DLWP) and FourCastNet (FCN) models as a proof of concept for geophysical fluid dynamics applications. We systematically investigate the effect of PTQ on emulator inferences over short-range forecast horizons. Evaluation of PTQ configurations using simulated quantization hints at qualitatively meaningful forecasts over short-time horizons. These results provide a first benchmark of PTQ for autoregressive weather emulators and a basis for quantization-based optimization of DL models for dynamical systems.
Source: Post-Training Quantization of Autoregressive Weather Models