What cutting-edge project are you working on right now?
We’re building a "kilo-factory“, in which we envision to manufacture batteries on the kWh scale in a year timeframe. This is naturally nothing compared to the Gigawatt hour scale in the industry, but it allows us to be extremely flexible. We also build robots to synthesize kilograms of catalysts and have a digital twin of our entire laboratory. In this lab factory we gather data from all possible sources and integrate them, so that we can understand the structure-processing-function relationships not just in singular materials, but also how these materials act within a system. Further, we also develop brokering approaches to orchestrate material acceleration platforms that interconnect our lab with others. The amount of data analysis, data fusion, and computations nessecary for this is on the entirely new scales for experimental materials science and chemistry.
What was the key experience that made you want to do research in data science and what fascinates you about working with MDSI?
I have been working in high-throughput experimentation throughout all my career and always had the issue of having way too much data to analyze by conventional means. Data science in an experimental setting is super interesting, as there are endless challenges that many people would flag as „simple“, yet they turn out to be rather complicated.
What paradigm shift do you expect within the next ten years, triggered in particular by the Institute's interdisciplinary approach?
I believe that if we put experimental chemistry with all its diverse tools onto a graph and find a way to ingest data from very heterogenous sources, we will be able to achieve a higher level of autonomous research with humans in the loop. If we can guide science and humans by data beyond their „little boxes“ and anthropogenic biases, we will discover and proliferate the materials of tomorrow very soon.
What paradigm shift do you expect within the next ten years, triggered in particular by the Institute's interdisciplinary approach?
I’d love to see less of an activation barrier in being granted more compute power but who doesn’t :-)