ARCHESWEATHER & ARCHESWEATHERGEN: A DETERMINISTIC AND GENERATIVE MODEL FOR EFFICIENT ML WEATHER FORECASTING

Guillaume Couairon, Renu Singh, Christian Lessig, Claire Monteleoni

Abstract:

Weather forecasting plays a vital role in today’s society, from agriculture and logistics to predicting
the output of renewable energies, and preparing for extreme weather events. Deep learning weather
forecasting models trained with the next state prediction objective on ERA5 have shown great success
compared to numerical global circulation models. However, for a wide range of applications, being
able to provide representative samples from the distribution of possible future weather states is critical.
In this paper, we propose a methodology to leverage deterministic weather models in the design
of probabilistic weather models, leading to improved performance and reduced computing costs.
We first introduce ArchesWeather, a transformer-based deterministic model that improves upon
Pangu-Weather by removing overrestrictive inductive priors. We then design a probabilistic weather
model called ArchesWeatherGen based on flow matching, a modern variant of diffusion models, that
is trained to project ArchesWeather’s predictions to the correct distribution of ERA5 weather states.
ArchesWeatherGen is a true stochastic emulator of ERA5 and surpasses IFS ENS and NeuralGCM on
all WeatherBench headline variables (except for NeuralGCM’s geopotential). Our work also aims to
democratize the use of deterministic and generative machine learning models in weather forecasting
research, with academic computing resources. All models are trained at 1.5º resolution, with a training
budget of ∼9 V100 days for ArchesWeather and ∼45 V100 days for our best ArchesWeatherGen
model. For inference, ArchesWeatherGen generates 15-day weather trajectories (with 24h time
steps) at a rate of 1 minute per ensemble member on a A100 GPU card. To make our work fully
reproducible, our code and models will be open source, including the complete pipeline for data
preparation, training, and evaluation, at https://github.com/INRIA/geoarches.