Use case 1: Using Artificial Intelligence in plant breeding
Plant breeding is an example where the right combinations of process-controlling measures, such as the choice of light spectrum or temperature adjustments at different stages of development, have a decisive influence on breeding success. AI methods are intended to support here by estimating the most relevant parameters and settings, thus providing SU BIOTEC with valuable knowledge for designing the breeding process.
Use case 2: Retaining knowledge from lab reports
GEA, one of the world's largest suppliers of systems for the mechanical clarification and separation of liquids in various industries, faces the challenge of preserving the expert knowledge that laboratory engineers have built up over decades. Due to demographic change, many of these experts will retire in the foreseeable future. Therefore, it is crucial to use AI to compress this expertise into data-based models and make it available to both new employees and the industry as a whole.
"Our results clearly show that we are on the right track," agree Julian Bültemeier, research assistant in the Discrete Systems working group under Prof. Dr Volker Lohweg, and Christoph-Alexander Holst, research group leader in the working group.
Use case 3: Increasing the energy efficiency of household appliances
In Miele's application case, the AI4ScaDa project is about developing intelligent tumble dryers. This involves combining field and laboratory test data and using AI methods to make tumble dryers more efficient. This challenge promises not only the improvement of household appliances, but also a more sustainable use of energy.
More about AI4ScaDa
The it's OWL innovation project AI4ScaDa is dedicated to researching special AI techniques that can be profitably used in the context of Scarce Data. In contrast to Big Data, the term "Scarce Data" refers to a limited amount or incomplete data, but often collected in laboratories. The key challenge is that AI systems depend heavily on the quality and quantity of available data. If only very Scarce Data are available, AI processes can often hardly keep up with human expertise. AI4ScaDa aims to close this gap and help companies to reap the benefits of AI even in data-scarce environments.