1 code implementation • 30 Nov 2022 • Daniel Getter, Julie Bessac, Johann Rudi, Yan Feng
For each downscaling factor, we consider three CNN configurations that generate super-resolved predictions of fine-scale wind speed, which take between 1 to 3 input fields: coarse wind speed, fine-scale topography, and diurnal cycle.
no code implementations • 29 Jul 2021 • Amanda Lenzi, Julie Bessac, Johann Rudi, Michael L. Stein
We propose to use deep learning to estimate parameters in statistical models when standard likelihood estimation methods are computationally infeasible.
1 code implementation • 12 Dec 2020 • Johann Rudi, Julie Bessac, Amanda Lenzi
We employ the neural networks to approximate reconstruction maps for model parameter estimation from observational data, where the data comes from the solution of the ODE and takes the form of a time series representing dynamically spiking membrane potential of a biological neuron.