PDE Foundation Models are Skillful AI Weather Emulators for the Martian Atmosphere

We show that AI foundation models that are pretrained on numerical solutions to a diverse corpus of partial differential equations can be adapted and fine-tuned to obtain skillful predictive weather emulators for the Martian atmosphere. We base our work on the Poseidon PDE foundation model for two-dimensional systems. We develop a method to extend Poseidon from two to three dimensions while keeping the pretraining information. Moreover, we investigate the performance of the model in the presence of missing data. Our results make use of four Martian years (approx. 34 GB) of training data and a median compute budget of 13 GPU hours. This shows that PDEs-FMs can not only be used to solve (other) PDEs but also to anchor models for domains with complex interactions that lack a sufficient amount of training data or a suitable compute budget.