Search Results for author: Stephan Rasp

Found 10 papers, 8 papers with code

Climate-Invariant Machine Learning

1 code implementation14 Dec 2021 Tom Beucler, Michael Pritchard, Janni Yuval, Ankitesh Gupta, Liran Peng, Stephan Rasp, Fiaz Ahmed, Paul A. O'Gorman, J. David Neelin, Nicholas J. Lutsko, Pierre Gentine

Data-driven algorithms, in particular neural networks, can emulate the effects of unresolved processes in coarse-resolution climate models when trained on high-resolution simulation data; however, they often make large generalization errors when evaluated in conditions they were not trained on.

Purely data-driven medium-range weather forecasting achieves comparable skill to physical models at similar resolution

3 code implementations19 Aug 2020 Stephan Rasp, Nils Thuerey

Numerical weather prediction has traditionally been based on physical models of the atmosphere.

Atmospheric and Oceanic Physics

Towards Physically-consistent, Data-driven Models of Convection

2 code implementations20 Feb 2020 Tom Beucler, Michael Pritchard, Pierre Gentine, Stephan Rasp

Data-driven algorithms, in particular neural networks, can emulate the effect of sub-grid scale processes in coarse-resolution climate models if trained on high-resolution climate simulations.

WeatherBench: A benchmark dataset for data-driven weather forecasting

3 code implementations2 Feb 2020 Stephan Rasp, Peter D. Dueben, Sebastian Scher, Jonathan A. Weyn, Soukayna Mouatadid, Nils Thuerey

Data-driven approaches, most prominently deep learning, have become powerful tools for prediction in many domains.

Weather Forecasting

Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems

2 code implementations3 Sep 2019 Tom Beucler, Michael Pritchard, Stephan Rasp, Jordan Ott, Pierre Baldi, Pierre Gentine

Neural networks can emulate nonlinear physical systems with high accuracy, yet they may produce physically-inconsistent results when violating fundamental constraints.

Computational Physics Atmospheric and Oceanic Physics

Online learning as a way to tackle instabilities and biases in neural network parameterizations

1 code implementation2 Jul 2019 Stephan Rasp

Here, I propose online learning as a way to combat these issues.

Atmospheric and Oceanic Physics Computational Physics

Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling

no code implementations15 Jun 2019 Tom Beucler, Stephan Rasp, Michael Pritchard, Pierre Gentine

Artificial neural-networks have the potential to emulate cloud processes with higher accuracy than the semi-empirical emulators currently used in climate models.

Combining crowd-sourcing and deep learning to explore the meso-scale organization of shallow convection

no code implementations5 Jun 2019 Stephan Rasp, Hauke Schulz, Sandrine Bony, Bjorn Stevens

In particular, the focus is on the organization of shallow cumulus convection in the trade wind regions.

Deep learning to represent sub-grid processes in climate models

3 code implementations12 Jun 2018 Stephan Rasp, Michael S. Pritchard, Pierre Gentine

We train a deep neural network to represent all atmospheric sub-grid processes in a climate model by learning from a multi-scale model in which convection is treated explicitly.

Neural networks for post-processing ensemble weather forecasts

1 code implementation23 May 2018 Stephan Rasp, Sebastian Lerch

Ensemble weather predictions require statistical post-processing of systematic errors to obtain reliable and accurate probabilistic forecasts.

Cannot find the paper you are looking for? You can Submit a new open access paper.