I want to end trial and error in coatings R&D

For most of my career I watched the same thing happen over and over. Brilliant people, decades of hands-on knowledge, and a way of running experiments that worked for them and almost nobody else. Not effective in the lab, and not transferable to a new team member, let alone to a computer-aided or data-driven workflow.

Most labs still run experiments the same way. You hold one variable fixed and change another. Then you hold that one fixed and change the first. It is intuitive and it seems efficient, but it costs a lot of time, and you still miss most of what the experiments could have told you, because you never cover the design space in a structured way.

Design of Experiments and Bayesian optimization solve this, and they have existed for decades. But most teams never picked them up. The methods were hard to grasp without statistical training, and the software was complicated, with more features than most users need.

Generative AI changes that. You can describe a problem to your computer in plain English and get an experimental plan back. You don't need to wait for software support, or for the one person in the lab who knows DoE. You just ask the assistant and let it design the next experiments for you.

That's what EDH is for. Modern experimental design methods, available to everyone, not only the labs that can afford a data scientist.

Marcel

Education & experience

Professional

  • Since 2024 HOBUM Oleochemicals · Hamburg, DE. Testing plant-based polymers as coating raw materials, with the same experimental design methods I teach in EDH.
  • Since 2024 Experimental Design Hub · Helping coatings engineers replace trial-and-error with modern experimental design methods (Founder).

Teaching

  • Since 2023 Esslingen University · Teaching Design of Experiments (Lecturer).
  • 2021 to 2022 Esslingen University · Teaching surface characterization methods (Lecturer).

Education

  • 2020 to 2024 DTU · Copenhagen, DK. Researching sustainable antifouling coatings for marine applications (PhD).
  • 2019 to 2020 Esslingen University · Studying applied surface and material science (MSc).
  • 2015 to 2019 Esslingen University · Studying chemical engineering for colors and coatings (BSc), with extended industry practice at FreiLacke.
  • 2013 to 2015 FreiLacke · Bräunlingen, DE. Training as a laboratory technician for coatings (apprenticeship).

Selected work

  • Upcoming workshop What data do we need to become more productive across the coatings value chain? SPFA Workference #3 (online) · June 2026.
  • Guest talk Data-driven coatings development. Esslingen University · May 2026.
  • Webinar How to automate daily tasks with Claude Code. Online · April 2026.

Work with me

Consulting. Hands-on work on your problem. I design the experiments with you, make sense of data you already have, or help you set up a lab that learns.

Trainings. A Lab That Learns, a series of four workshops that takes your lab from repeating experiments to learning from every one, with AI from the first step. Every workshop also runs in-house, for your team.

Speaking. Conferences and guest talks on data-driven coatings R&D, generative AI in the lab, and anything else I write about in the essays. Online or on site.

I work in English or German.

Send me an email