Publications by authors named "Luis Zamudio"

In this work, we develop a patch-level training approach and a task-driven intensity-based augmentation method for deep-learning-based segmentation of motion-corrected perfusion cardiac magnetic resonance imaging (MRI) datasets. Further, the proposed method generates an image-based uncertainty map thanks to a novel spatial sliding-window approach used during patch-level training, hence allowing for uncertainty quantification. Using the quantified uncertainty, we detect the out-of-distribution test data instances so that the end-user can be alerted that the test data is not suitable for the trained network.

View Article and Find Full Text PDF

Atmospheric rivers (ARs) cause heavy precipitation and flooding in the coastal areas of many mid-latitude continents, and thus the atmospheric processes associated with the AR have been intensively studied in recent years. However, AR-associated ocean variability and air-sea fluxes have received little attention because of the lack of high-resolution ocean data until recently. Here we demonstrate that typical ARs can generate strong upper ocean response and substantial air-sea fluxes using a high-resolution (1/12°) ocean reanalysis.

View Article and Find Full Text PDF

Atmospheric forcing, which is known to have a strong influence on surface ocean dynamics and production, is typically not considered in studies of the deep sea. Our observations and models demonstrate an unexpected influence of surface-generated mesoscale eddies in the transport of hydrothermal vent efflux and of vent larvae away from the northern East Pacific Rise. Transport by these deep-reaching eddies provides a mechanism for spreading the hydrothermal chemical and heat flux into the deep-ocean interior and for dispersing propagules hundreds of kilometers between isolated and ephemeral communities.

View Article and Find Full Text PDF