1.1k citations · 3.5k across the 16 of their papers we have counts for
4 papers · 1 filter
Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
Tom Beucler, Michael Pritchard, Stephan Rasp +3
Neural networks can emulate nonlinear physical systems with high accuracy, yet they may produce physically-inconsistent results when violating fundamental constraints. Here, we int…
Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations
Stephan Rasp
Over the last couple of years, machine learning parameterizations have emerged as a potential way to improve the representation of sub-grid processes in Earth System Models (ESMs).…
Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling
Tom Beucler, Stephan Rasp, Michael Pritchard +1
Artificial neural-networks have the potential to emulate cloud processes with higher accuracy than the semi-empirical emulators currently used in climate models. However, neural-ne…
Combining crowd-sourcing and deep learning to explore the meso-scale organization of shallow convection
Stephan Rasp, Hauke Schulz, Sandrine Bony +1
Humans excel at detecting interesting patterns in images, for example those taken from satellites. This kind of anecdotal evidence can lead to the discovery of new phenomena. Howev…