How to Accelerate R&D and Optimize Experiment Planning with Machine Learning and Data Science

Authors

  • Daniel Pacheco Gutierrez Atinary Technologies, Sàrl, Lausanne
  • Linnea M. Folkmann Atinary Technologies, Sàrl, Lausanne
  • Hermann Tribukait Atinary Technologies, Sàrl, Lausanne
  • Loïc M. Roch Atinary Technologies, Sàrl, Lausanne https://orcid.org/0000-0003-1771-2023

DOI:

https://doi.org/10.2533/chimia.2023.7

PMID:

38047848

Keywords:

Artificial intelligence, Autonomous experimentation, Closed-loop optimization, Experiment planning, Machine learning, Materials acceleration platforms, Process optimization, Self-driving labs

Abstract

Accelerating R&D is essential to address some of the challenges humanity is currently facing, such as achieving the global sustainability goals. Today’s Edisonian approach of trial-and-error still prevalent in R&D labs takes up to two decades of fundamental and applied research for new materials to reach the market. Turning around this situation calls for strategies to upgrade R&D and expedite innovation. By conducting smart experiment planning that is data-driven and guided by AI/ML, researchers can more efficiently search through the complex - often constrained - space of possible experiments and find or hit the global optima much faster than with the current approaches. Moreover, with digitized data management, researchers will be able to maximize the utility of their data in the short and long terms with the aid of statistics, ML and visualization tools. In what follows, we describe a framework and lay out the key technologies to accelerate R&D and optimize experiment planning

Downloads

Published

2023-02-22

How to Cite

[1]
D. Pacheco Gutierrez, L. M. Folkmann, H. Tribukait, L. M. Roch, Chimia 2023, 77, 7, DOI: 10.2533/chimia.2023.7.