Over the past several years, spatially enhanced (3.125 km) AMSR2 36 GHz imagery has become an essential tool for sea ice analysis and forecasting in all conditions, day or night. Forecasters at the Arctic Sea Ice Program (ASIP) also routinely use enhanced (6.25 km) sea ice concentration products derived from these data. Traditionally, improving passive microwave imagery required reconstruction techniques that balance increased resolution against added noise. Today, machine learning is opening new possibilities for pushing these limits. In this seminar, Dr. Greenwald will share recent work using advanced deep learning models to further enhance AMSR2 imagery and discuss the challenges encountered.
Presenter(s):
Dr. Tom Greenwald, Senior Scientist, Cooperative Institute for Meteorological Satellite Studies (CIMSS), University of Wisconsin-Madison
Access
Google Meet joining info
https://meet.google.com/jtm-gghs-yio
Or dial: (US) +1 304-825-5605 PIN: 617 685 319#