Zhuo Wang
University of Illinois Urbana-Champaign, IL·Earth & Environmental Science
Farmers can plan around next week's weather, but rarely around next month's. Forecasts made 2 weeks to a few months ahead are called subseasonal to seasonal (S2S) forecasts.
- Fields
Earth & Environmental Science
Plant Science & Agriculture
Computer Science
- Topics
subseasonal to seasonal prediction
S2S forecasting
weather extremes
- Grants
- 1 known grant, through Jul 2027
What they work on
- Investigate how predictable weather extremes and their environmental impacts on Midwest agriculture are at subseasonal to seasonal (2-week to seasonal) forecast lead times.
- Develop prototype machine-learning models that make skillful subseasonal to seasonal predictions of extreme precipitation for the Midwest.
- Build a scalable crop yield forecasting model that integrates phenology, the timing of crop growth stages, to estimate how weather extremes affect harvests.
- Co-develop actionable forecast products with agricultural stakeholders through partnerships, to close information gaps for farmers and policymakers.
More about the research
Their accuracy drops sharply beyond two weeks, especially for extreme events such as heavy rain. Yet those rare extremes do outsized damage to agriculture. In the Midwest, part of the gap is that meteorologists and agricultural stakeholders rarely work together to produce forecasts farmers can actually use. This project aims to build skillful, usable S2S predictions of weather extremes and crop yields for Midwest agriculture.
Why it matters
Better forecasts of extreme weather weeks to months ahead could give Midwest farmers time to take protective action, such as adjusting planting or management. They could help policymakers anticipate crop losses. Linking these forecasts to crop-yield predictions could improve agricultural production, food security and resilience.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Tiantian Yang
University of Michigan, MI·Engineering·Early-career
Correct errors in space and time in subseasonal-to-seasonal precipitation forecasts from the North American Multi-Model Ensemble using deep learning models.
Steven Greybush
Pennsylvania State University, PA·Earth & Environmental Science
Design and optimize a deep learning nowcasting system for convection initiation that combines forecasting, diagnosis and generation of storm scenarios, trained on high-resolution satellite, radar and surface weather data.
Qinghua Ding
University of California-Santa Barbara, CA·Earth & Environmental Science
Develop regional models of summertime Arctic sea ice that combine global observational data through machine learning, to forecast ice from weeks to a season ahead and find how far ahead prediction is possible.
The school
University of Illinois Urbana-Champaign: 41 labs on PI Pages, $907M a year on research, 870 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.