papers
Publications (3)
physics.ao-ph2023
Statistical treatment of convolutional neural network super-resolution of inland surface wind for subgrid-scale variability quantification
Daniel Getter, Julie Bessac, Johann Rudi +1
Machine learning models have been employed to perform either physics-free data-driven or hybrid dynamical downscaling of climate data. Most of these implementations operate over re…
physics.ao-ph2026
Emergent conservation in atmospheric chemical mechanisms
Beatriz Lucia G. Rodriguez, Patrick Obin Sturm, Daniel Getter +1
Conservation laws are time-invariant properties that constrain many physical systems. For systems of chemical reactions, the law of mass conservation constrains how atoms flow betw…
cs.LG2025
Multidimensional Distributional Neural Network Output Demonstrated in Super-Resolution of Surface Wind Speed
Harrison J. Goldwyn, Mitchell Krock, Johann Rudi +2
Accurate quantification of uncertainty in neural network predictions remains a central challenge for scientific applications involving high-dimensional, correlated data. While exis…