What is it about?
The design of materials often require many aspects of their properties to be optimised at the same time. This paper shows how one could achieve this by combining multi-target regression and Bayesian networks, using a set of simulated nanodiamond data as an exemplar.
Featured Image
Photo by Bas van den Eijkhof on Unsplash
Why is it important?
While purely correlational machine learning studies are able to extract complex structure/property relationships from data, the outcomes are often insufficient to explain how to control or tune the properties of materials, particularly when they are multi-functional. This study proposes a way to achieve greater actionability from the insights that could be obtained from the same data.
Perspectives
It was satisfying to get computers to suggest how the properties of nanodiamonds are related to their structures. I hope the framework presented here becomes useful for someone one day!
Jonathan Ting
Australian National University
Read the Original
This page is a summary of: Causal Paths Allowing Simultaneous Control of Multiple Nanoparticle Properties Using Multi‐Target Bayesian Inference, Advanced Theory and Simulations, July 2022, Wiley,
DOI: 10.1002/adts.202200330.
You can read the full text:
Contributors
The following have contributed to this page
