naming_logo_cropscienceDr. Philipp Senger and Dr. Daniel Burkow from Bayer Crop Science visited the SDA group on April  17, 2019.

On Wednesday, SDA had visitors from Bayer: Philipp Senger is the Head of CLS (Computational Life Science) Translational R&D at Bayer Crop Science. His main research interests comprise data science, semantic modeling, knowledge graphs (KGs), natural language processing and machine learning. He together with his team apply their research results to develop digital products and services. Philipp earned a Ph.D. in computer science from the Eberhard-Karls-Universität Tübingen in cooperation with the Robert Bosch GmbH where he investigated data-based methods for automatic generation of electrical behavior models in the automotive industry.

Daniel Burkow is a Post-Doctoral researcher at CLS Translational R&D at Bayer Crop Science.
His main research interests comprise applied mathematics for life sciences, machine learning,  data modeling and knowledge graphs. At Translational R&D at Bayer Crop Science, he works on the development of machine learning applications and data modeling approaches.
Daniel earned his Ph.D. from Arizona State University in the field of Applied Mathematics for Life Sciences in which he examined intramyocellular lipids and the progression of muscular insulin resistance.

Dr. Senger and Dr. Burkow were invited at the bi-weekly “SDA colloquium presentations” where they presented Bayer Crop Science and their main research topics. The goal of the visit was to exchange experience and ideas on combining machine learning approaches with knowledge graphs. In particular, they explained how field trials are modeled at Bayer Crop Science and presented a recent use case in which knowledge graph embeddings have been applied to get more insights about their experimental data.

During the meeting, SDA’s core research topics and main research projects have been presented and future collaborations between Bayer Crop Science R&D and SDA has been discussed. Especially, the application of reasoning and inference methods on large scale KGs describing field experiments, the development of KGE embedding models that incorporate literals (e.g., numerical values) and the application of question answering have been discussed.

We are looking forward to future collaborations with Bayer Crop Science.