Lizhi Wang
George Mason University, VA·Engineering
Feeding a growing population with less land, water, pesticide and fertilizer is hard, especially as environments change quickly and unpredictably. Developing better crop varieties still depends heavily on slow, expensive, trial-and-error field trials.
- Fields
Engineering
Plant Science & Agriculture
Computer Science
- Topics
plant breeding
genomic selection
crop improvement
- Grants
- 1 known grant, through Apr 2027
What they work on
- Predict crop traits from genetic, management and environmental data by identifying a small subset of variables that interact as well as act additively, using machine learning and statistical selection methods.
- Design algorithms for genomic selection, choosing breeding parents from DNA data, framed as a high-dimensional, dynamic optimization problem constrained by resources and reproductive biology.
- Build multi-objective, multi-level optimization models that design crop management strategies balancing reward, time and risk under genetic, environmental and logistical constraints.
More about the research
This project asks whether engineering tools such as mathematical optimization and machine learning can speed up plant breeding and crop management. These tools have already made communication, manufacturing, transportation and energy systems more efficient and resilient. The work combines agronomy, crop modeling, machine learning, operations research, optimization and plant breeding, together with an industry partner.
Why it matters
Faster, data-driven breeding and management decisions could help farmers and seed developers adapt crops to changing climates while using fewer resources such as land, water and fertilizer. Better trait prediction and genomic selection algorithms may shorten the time and cost of developing improved varieties. Optimization models may help growers choose management strategies that weigh yield against time and risk.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Daniel Robertson
University of Idaho, ID·Plant Science & Agriculture
Automate high-throughput phenotyping of cereal stalks, meaning fast trait measurements across many plants, to overcome the shortage of measured plants compared with millions of genetic markers.
Hau Chan
University of Nebraska-Lincoln, NE·Computer Science
Develop collective decision-making frameworks for the facility accessibility improvement problem that handle multiple facilities and community preferences, using accessibility models and algorithms from operations research and AI.
Viswanath Nagarajan
University of Michigan, MI·Computer Science
Design approximation algorithms with provable performance guarantees for sequential testing of systems made of interconnected components, including series-parallel structures, under complex cost structures.
The school
George Mason University: 15 labs on PI Pages, $282M a year on research, 297 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.