CEST research acknowledged at Physics Days

Manuel Kuchelmeister received the best poster award at Physics Days 2022
Picture from the poster
Photo of Manuel Kuchelmeister
Masters student Manuel Kuchelmeister

CEST masters student Manuel Kuchelmeister was awarded one of the two best poster prizes for his presentation "Multi-fidelity machine learning to accelerate materials research"  at Physics Days 2022, organized virtually by Aalto University.

Bayesian optimization (BO) is a sample-efficient method for the exploration of large search spaces. In this work, BO is used to find stable configurations on material energy landscapes. Finding such structures is a challenge, due to high-dimensional search spaces and costly quantum mechanical calculations. Kuchelmeister approached this by constructing a multi-fidelity machine learning model. By using a transfer learning approach, it was possible to use less accurate but inexpensive calculations, to accelerate the exploration phases of BO.

The approach reduced the computational cost of a conformer search problem by 70%, serving as a first benchmark for the great potential that multi-fidelity learning can have to accelerate expensive structure-search problems.

  • Published:
  • Updated:
URL copied!

Read more news

A closeup of a woman in green light wearing goggles that reflect colourful pixels
Research & Art Published:

In September, 14 new Academy Researcher Fellows will start at Aalto

The Academy of Finland has granted Aalto University funding for 14 Academy Research Fellowships
On the background, white radiant lines over a black bacground and only hair and shoulder of a person passing by visible
Research & Art Published:

Over 19 million euros for research

A total of 43 researchers received Academy Research Fellow and Academy Project funding from the Academy of Finland
Outi Turpeinen standing on stage talking about Unfolding public art book to a seated audience facing her.
Campus, Research & Art, University Published:

Love and poetry - the artists were inspired by the passion conveyed by the university's research

Engineering Materials, an art collection for K1, K2, and K3 buildings, was published
Graphic illustration of materials science, AI and physics with equations, B&W photos and a photo of prof. Rinke.
Research & Art Published:

Prof. Patrick Rinke: making sustainable materials with AI

Professor Patrick Rinke’s pioneering expertise in finding sustainable and climate-friendly materials with machine learning methodology has arguably never been more in demand