Developing a Climate-Smart Practice Optimization Tool for Sustainable Agriculture in the US
This VIP aims to develop a climate-smart practices optimization tool for enhancing the climate resilience of agriculture in the US.
What are climate-smart agricultural practices?
Practices that could intensify crop yields by:
- Optimizing nutrient use efficiency (NUE)
- Optimizing water use efficiency (WUE)
- Minimizing greenhouse gasses (GHG) emissions
We will integrate observations with artificial intelligence (AI) and process-based models to investigate the question:
How can we optimize agricultural management practices (e.g., biochar addition, fertilization, irrigation, planting, and harvest) to achieve the “Climate-smart” objective?
This project involves two types of activities for undergraduate students:
- Type 1 (Data-dominated work) focuses on agricultural practice-related data mining, statistical analysis, optimization, and visualization.
- Type 2 (model-dominated work) focuses on model parameters optimization, and AI model training and testing.
As a student, you will be able to choose which path you want to follow based on what you enjoy, and what you're studying. If you're into data, experiments, and creating visuals, Type 1 might be your thing. If you love working with computers, software, and using AI to solve problems, then Type 2 may be where you'd thrive.
With either type of activity, you'll be learning about agricultural practices while making a real impact on future climate-smart agriculture.
Issues Involved or Addressed
- Climate resilience assessment and optimization
- Climate-smart agriculture and ecosystem management
- Water cycle, energy balance, and carbon cycle
- Soil carbon sequestration and nutrient availability
- Water quantity and quality
- Model parameter optimization
- AI model training and testing
Methods and Tech
- Data mining, collection, and organization (Microsoft Excel, etc.)
- Statistical data analysis, interpretation, and visualization (Python/MATLAB/R)
- Spatial data analysis and visualization
- Artificial intelligence and modeling (Python/Fortran)
- Science and interdisciplinary communication
Academic Majors of Interest
Our VIP team is open to all majors, with particular interest in the students with any of the following backgrounds:
- Hydrology and Atmospheric Sciences
- Ecology & Evolutionary Biology
- Environmental Science
- Natural Resources
- Computer Science
- Mathematics and/or Statistics & Data Sciences
- Crop Sciences
Preferred Interests and Preparation
- Basic ability to conduct literature reviews, gather relevant research materials and synthesize information
- Basic ability to use statistical analysis tools, such as Excel, R, MATLAB, or Python
- Preferred: Computer programming (e.g., Python/Fortran) or AI/ML model experience
- Preferred: Spatial data analysis and mapping experiences, such as GIS applications, NETCDF data analysis and visualization
- A genuine interest in addressing climate change and its impact on agriculture
- Enjoys interdisciplinary research and collaborative work environments
- Reliability and accountability in handing research tasks and data
- Commitment to research excellence and the ability to meet project deadlines
- Careful and meticulous approach to data analysis and research tasks
If you are excited about our VIP research in developing a climate-smart agriculture practices tool, we encourage you to apply.Join us in our mission to create a more climate-resilient future for agriculture in the United States. Together, we can make a difference!
If you are interested in joining this VIP team for class credit, contact Dr. Song by completing a VIP Interest Form and selecting the team "Developing a Climate-Smart Practice Optimization Tool for Sustainable Agriculture in the US."
If you are interested in a Federal Work-Study position with this team, please submit 1) your resume/CV, and 2) a one-page cover letter detailing your interest and/or relevant experience to Dr. Yang Song (email@example.com).
Application Deadline: the position will be closed by Dec 31, 2023, or until we find sufficient candidates.