Agricultural research increasingly relies on the application of techniques from statistics and data science to answer agronomic questions. Data-driven agronomy thus operates at the intersection of three different domains: (i) mathematics & statistics, (ii) computer science and (iii) Agronomy.
In our discussions with agricultural companies, a common theme mentioned as being important was the need for agronomists with skills in data handling and analysis. Like many other fields, agriculture is becoming increasingly data-intensive, with the Netherlands playing a leading role in developing and applying innovative data-driven technologies such as precision agriculture. Therefore, we developed the minor Data-driven Agronomy.
The minor starts with a restricted optional foundational course R for Statistics (MAT50303) that introduces students with limited experience in statistical programming to the basics of R scripting for data processing, analysis, and visualization. The statistical foundations for data science are provided in period 5 via Statistics for Data Scientists (MAT32806) whereas the application of these techniques to agro-ecological data is taught in Data Science for Ecology (REG33806). On period 6 (part 1) the course Advanced Agronomy (CSA34806) provides the disciplinary expertise that agricultural data scientists and agronomists require. The trajectory ends with a new course Data Analysis for Agronomy that integrates, complements, and applies the skills obtained in the other courses. The main objective will be to learn to apply key concepts and methods in probability and statistics to the analysis of large and complex agronomic datasets. This hands-on course will have a strong focus on operationalizing statistical knowledge by working around representative and challenging case studies taken from state-of the art agricultural research.