no code implementations • 4 Apr 2024 • Jason Stock, Jaideep Pathak, Yair Cohen, Mike Pritchard, Piyush Garg, Dale Durran, Morteza Mardani, Noah Brenowitz
This work presents an autoregressive generative diffusion model (DiffObs) to predict the global evolution of daily precipitation, trained on a satellite observational product, and assessed with domain-specific diagnostics.
no code implementations • 5 Dec 2022 • Charles Anderson, Jason Stock
To find these optimal patterns, a new way of interpreting what the neural network has learned is explored.
no code implementations • 21 Oct 2022 • Jason Stock, Chuck Anderson
Multi-channel satellite imagery, from stacked spectral bands or spatiotemporal data, have meaningful representations for various atmospheric properties.
no code implementations • 12 May 2022 • Charles Anderson, Jason Stock, David Anderson
Typical deep learning approaches to modeling high-dimensional data often result in complex models that do not easily reveal a new understanding of the data.
no code implementations • 6 May 2022 • Jason Stock, Chuck Anderson
This work introduces a wavelet neural network to learn a filter-bank specialized to fit non-stationary signals and improve interpretability and performance for digital signal processing.
no code implementations • 17 Jun 2021 • Imme Ebert-Uphoff, Ryan Lagerquist, Kyle Hilburn, Yoonjin Lee, Katherine Haynes, Jason Stock, Christina Kumler, Jebb Q. Stewart
Standard loss functions do not cover all the needs of the environmental sciences, which makes it important for scientists to be able to develop their own custom loss functions so that they can implement many of the classic performance measures already developed in environmental science, including measures developed for spatial model verification.
1 code implementation • 7 Jan 2021 • Jason Stock, Tom Cavey
In this paper we outline the development methodology for an automatic dog treat dispenser which combines machine learning and embedded hardware to identify and reward dog behaviors in real-time.
no code implementations • 26 Mar 2020 • Jason Stock, Andy Dolan, Tom Cavey
In this work we evaluate the impact of digitally altered images on the performance of artificial neural networks.