Pa. — Song Zhang, a graduate student in the Department of Meteorology and Atmospheric Science at Penn State, will give the talk “Understanding, retrieving and predicting winter precipitation with polarimetric radar and machine learning” at 2 p.m. Friday, Nov. 6, in 117 Earth and Engineering Sciences Building on the University Park campus. The talk also will be available
The event is part of a fall seminar series hosted by TRAnscendIng Natural hazards forecasting (TRAIN). The talk is free and open to the public.
Winter storms can be severe weather events that endanger human lives, cause infrastructure and property damage, and result in major financial losses. Understanding patterns in winter precipitation can help researchers better forecast and prepare for storms.
“Building on our understanding of winter storm microphysics, we explored the potential of assimilating operational radar observations into numerical weather prediction models,” Zhang said.
Zhang found that operational radar could provide information about the vertical temperature structure of winter storms and realized that machine learning techniques could help capture the relationships. She helped train a model on five years of vertical temperature data from winter storms.
“The model demonstrated its ability to learn relationships between vertical variations in polarimetric radar variables and atmospheric temperature,” Zhang said. “Collectively, these observational and machine learning approaches advance our understanding of winter precipitation processes and offer opportunities to improve winter weather forecasting.”
She is in her fourth year working on the NASA IMPACTS project to improve the predictability of winter weather. Before attending Penn State, Zhang received a master of science degree in atmospheric sciences from the University of Illinois Urbana-Champaign.
Zhang’s research focuses on winter storm microphysics, polarimetric weather radar, and machine learning applications in atmospheric science. She is particularly interested in understanding winter precipitation processes, interpreting cloud and precipitation microphysical properties from radar observations, and developing machine learning approaches to improve storm evolution prediction and winter weather forecasting.
About TRAIN
TRAIN is an initiative through the Earth and Environmental Systems Institute that aims to transform complex geophysical and atmospheric data and bridge the gap between raw information and community resilience. TRAIN aims to build the community at Penn State to become nationally recognized for research innovation to respond proactively to funding opportunities and coordinate natural hazard responses.
Contact
-
- plc103@psu.edu
- Cell Phone: 814-863-4663
- http://www.ems.psu.edu
