Inhalte/ Contents

The course presents a novel 3-step approach for improving agricultural crop (e.g. maize, wheat) productivity: 1) deriving Land Water Content (LWC) from sensor time series and estimating Land Food Productivity (LFP) from drone images; 2) exploring the relationship between LWC and LFP with popular methods from machine learning (e.g. Neural Networks) and computer vision (e.g. YOLOv11), that can be used to predict the irrigation demands for farmlands, depending on their crop types and weather conditions; 3) integrating such predictions into natural-language explanations, used by virtual assistants. Bachelor and master students from computer science, data science, and business informatics, will be involved in this approach. Programming skills are a plus. During the course, students will do a small research task, intersecting at least one of the above steps, while participating in consultations and workshops. At the end, they will have to present their projects in a conference-like setting. 

Kontakt/ Contact

aleksandrov.d.martin@gmail.com

Link zum Vorlesungsverzeichnis/ Link to the course catalogue

folgt/ coming