3 papers
cs.LG2026
Field-Space Autoencoder for Scalable Climate Emulators
Johannes Meuer, Maximilian Witte, Ãtiénne Plésiat +2
Kilometer-scale Earth system models are essential for capturing local climate change. However, these models are computationally expensive and produce petabyte-scale outputs, which…
cs.LG2025
Field-Space Attention for Structure-Preserving Earth System Transformers
Maximilian Witte, Johannes Meuer, Ãtienne Plésiat +1
Accurate and physically consistent modeling of Earth system dynamics requires machine-learning architectures that operate directly on continuous geophysical fields and preserve the…
cs.LG2024
Dynamic Deep Learning Based Super-Resolution For The Shallow Water Equations
Maximilian Witte, Fabricio Rodrigues Lapolli, Philip Freese +4
Using the nonlinear shallow water equations as benchmark, we demonstrate that a simulation with the ICON-O ocean model with a 20km resolution that is frequently corrected by a U-ne…