AGRI-FOOD DIGITAL AND DATA SCIENCE TRAINING
GEMS Learning provides modular, non-credit digital and data science training for students and working professionals interested in hands-on food, agriculture, and natural resource applications. Across the curriculum, instructors have built their course content from their own work tackling small- to large-scale, often complex, data science projects to solve real-world agricultural problems. Our non-credit training courses give you the practical knowledge to tackle data-science challenges across the agri-food sciences.
Note:
GEMS is currently reevaluating our course portfolio and will not be offering any instructor-led courses for the remainder of 2025.
Course Fees
Course fees are based on the number of contact hours in each course. Learners are eligible for the following discounts in 2025:
- Current University of Minnesota affiliation, 90% discount
- Acad./non-profit affiliation, 60% discount
- For-profit affiliation, 30% discount
Courses
Instructor led online courses means getting your questions answered in real time. Courses range from a single two-hour course to modules with multiple courses that occur over several weeks. Instructor-led courses have enrollment is capped at 30 learners per course, asynchronous courses have no enrollment cap. Our courses are listed below.
Asynchronous Courses
Computing Basics for the Agri-food Sector
Are you a field or bench scientist and always wanted to feel more comfortable with your computing skills? These courses are designed for those who have never used the command line, but realize that the responsibilities they have or will soon take on require them to automate tasks. It will teach basic UNIX command-line skills, enable participants to work remotely on more powerful machines, create and run scripts to automate complex workflows, and synchronize your scripts with the larger community with Github.
Accounting for Location in Agriculture in Python
Would you like to leverage spatial data to start exploring the relationships of agricultural processes across geographies? This course is designed for those who are interested in explicitly accounting for location in their analyses. Learn how to work with spatial data in Python, starting from importing different spatial datasets and creating simple maps, to conducting basic geocomputation on vector and raster data. Each module includes the opportunity to practice your new skills via hands-on exercises focused on agri-food applications.
HPC for Ag: Upskilling Agri-Food Researchers to Utilize HPC Resources
If you are a researcher that works in the Agri-food domain (e.g., breeder, molecular biologist, food scientist, socioeconomist), you know a little bit of programming (e.g., in R and/or Python), but you feel a little limited (e.g., some of your calculations run for days on your laptop), then you could benefit from this course. We wish to show you how to step up to the next level, improve your coding efficiency, and make use of High Performance Computing (HPC) and Cloud resources readily available to you.
Familiarity at a beginner level with a programming language (e.g. Python, SQL, R, JavaScript, or Scala) is required. Given the nature of course material, some familiarity with the Python language is recommended.
**Course is open to current University of Minnesota faculty, staff and students**
Instructor Led Courses
Accounting for Location in Agriculture
Would you like to leverage spatial data to start exploring the relationships of agricultural processes across geographies? This course is designed for those who are interested in explicitly accounting for location in their analyses. Through this 3-week introductory course, you will learn how to work with spatial data in R, starting from importing different spatial datasets and creating simple maps, to conducting basic geocomputation on vector and raster data. In each 2 hour lecture, you will have the opportunity to immediately practice your new skills via hands-on exercises focused on agri-food applications.
Spatio-Temporal Accounting of Biotic Threats
Have your research, studies or work required you to examine the geographic distribution of various species? This could be for crop protection, forestry, environmental protection, environmental impact assessment, urban and natural landscape design and development, or simply an interest in any given species, whether insects, pathogens or weeds. Then you are at the right place, species distribution models allow us to understand the potential and realized distribution of various species across our landscapes at different scales. Understanding of species distribution at different scales provides different insights, for example global maps support decision makers to make high level biosecurity and conservation related decisions. Meso-scale or regional maps can be used for planning of cross-border projects, informing biosecurity related cross-border operations and various environmental projects. Small scale or local maps allow researchers to design custom pest prevention, monitoring and control strategies. Allow conservationists to use evidence-based information in their plans etc.
Digital Agriculture
Data is everywhere in agriculture, but knowing what to do with it isn't always easy or straightforward. This module will give you the basic tools for analyzing a decision-making context, evaluating the data needs, collecting or integrating data, and then performing basic analysis and visualization in Excel, R, Python, and QGIS. We will also cover some of the common pitfalls of using data to drive decision-making to be sure you and your teams can avoid them.