JuliaCon 2026

Niklas Viebig

Master’s student in Physics at ETH Zurich, currently completing my Master’s thesis in the climate modeling group at AOPP, University of Oxford. Im researching differentiable programming and systematic parameter calibration for Earth system models, with interests in exoplanet climates, high-performance computing, and scientific software engineering.


Sessions

08-12
17:20
10min
A learned surface roughness scheme for climate prediction in SpeedyWeather.jl
Greg Munday, Maximilian Gelbrecht, Milan Klöwer, Niklas Viebig

Hybrid climate modelling combines numerical models with machine-learned components. We present the development of multiple machine-learned surface climate processes and their integration into the climate model SpeedyWeather.jl using PyTorch and Lux.jl. Despite the offline training, the hybrid model is designed to generalise in space and to different climates. We address speed vs. accuracy tradeoffs using SymbolicRegression.jl and discuss online learning with Enzyme.jl.

Earth system science in Julia
Room 3
08-13
16:30
15min
The GPU acceleration of SpeedyWeather.jl, the friendly and flexible climate model
Milan Klöwer, Niklas Viebig, Maximilian Gelbrecht

Fortran climate models are being adapted to GPUs by automatically translating loop-by-loop into a kernel. In Julia, we have more flexibility to develop the climate model SpeedyWeather.jl for the GPU. Many parts are easy to accelerate, leverage multiple dispatch on the GPU and a high level of kernel fusion for modularity and performance, while being optionally hardware-specific. The spherical harmonic transforms remain a complex bottleneck but we employ a multi-algorithm approach with custom linear algebra kernels using Reactant, Fourier and Legendre transforms.

Julia, GPUs, and Accelerators
Room 3
08-14
11:15
15min
Differentiable Climate Modeling: Calibrating SpeedyWeather with Enzyme
Niklas Viebig, Milan Klöwer, Maximilian Gelbrecht, Greg Munday, Brian Groenke

Climate models rely on parameterizations that are traditionally tuned manually. We present a differentiable calibration framework using Enzyme.jl to compute exact reverse mode gradients of energy-balance diagnostics in SpeedyWeather.jl. By batching single- timestep gradients across chaotic dynamics, we enable systematic, reproducible optimization of shortwave radiation parameters, establishing an extensible workflow for objective calibration in Earth system models.

Differentiable Computational Models and their Applications
Room 6