Machine learning helps prepare necessary adaptations to warming conditions for farmers and supply chains
Problem
How can farmers and supply chains be prepared to adapt their practices to a warming climate?
- The average temperature in the United States has increased by approximately 1.5 degrees Fahrenheit in this century compared to the last century.
- Anticipated increases in temperature will likely influence geographical distribution and yield of grain crops.
Findings
Using machine learning—a form of artificial intelligence that enables a computer system to learn from data—a team of plant and meteorology scientists evaluated more than three decades of county-level crop yield data across 18 Midwest and Great Plains states. From this analysis, the team expects that over the next 40 to 50 years, the best conditions for corn and soybean production will shift northward, from Iowa and Illinois to Minnesota and the Dakotas.
Impact
The models can simulate different growing scenarios with variations in, for instance, atmospheric humidity and exposure to extreme temperatures that can impact established practices in planting dates or establishing risk thresholds. The research provides estimates of changes in the best climatic locations for corn and soybean as well as the uncertainty in the modeled estimates. This broad prediction can help all parties along the U.S. grain supply chain be prepared if this shift, which is currently in progress, continues in the coming decades.
Related Research Area: Environmental Resilience
Research Credit
Team
- Armen Kemanian, Alexis Hoffman, Chris Forest
Participating Departments
Partners
- Penn State College of Earth of Mineral Sciences
Competitive Funding
- National Science Foundation/Network for Sustainable Climate Risk Management (SCRiM), USDA NIFA (Agriculture and Food Research Initiative), U.S. Department of Energy
Federal and State Appropriations
- USDA NIFA Hatch Project PEN04710, Accession #1020049
Emerging Discoveries
Published Research
The response of maize, sorghum, and soybean yield to growing-phase climate revealed with machine learning
- Hoffman, A. L., Kemanian, A. R., & Forest, C. E. (2020) The response of maize, sorghum, and soybean yield to growing-phase climate revealed with machine learning. Environmental Research Letters, 15, [094013]. https://doi.org/10.1088/1748-9326/ab7b22
Emerging Discovery
Office for Research and Graduate Education
Address
217 Agricultural Administration BuildingUniversity Park, PA 16802-2600
- Email agresearch@psu.edu
- Office 814-865-3136
Emerging Discovery
Office for Research and Graduate Education
Address
217 Agricultural Administration BuildingUniversity Park, PA 16802-2600
- Email agresearch@psu.edu
- Office 814-865-3136