Areas of competencePhoto: Manuel Gutjahr
Data Science in Bioeconomy
Advanced agricultural and bio-economic production processes are generating large and diverse amounts of data - ranging from sensor data from agricultural machinery, satellite and aerial images, weather and climate data to data on soil properties and soil fertility.
The processing and analysis of these large amounts of data using modern methods of machine learning and intelligent data analysis has the potential to record the corresponding production processes in large spatial and temporal order. The aim is to understand underlying mechanisms in detail and, on this basis, to optimise and control processes in a targeted manner.
In order to lay the methodological basis for this potential, the Research Group Data Science in Agriculture is developing methods of machine learning and intelligent data analysis for applications in the field of agricultural engineering and bioeconomy.
Current work focuses, for example, on pattern recognition in image and spectral data for precision crop production as well as in emission and flow modelling in ventilated animal barns. A further methodological focus is the development of machine learning methods that explicitly depict spatial and temporal variation in data.