Surfing Multiple Conformation-Property Landscapes via Machine Learning: Designing Single-Ion Magnetic Anisotropy
![Thumbnail](/themes/edepositireland/images/white_rectangle.jpeg)
File Type:
PDFItem Type:
Journal ArticleDate:
2020Access:
openAccessCitation:
Lunghi, A., Sanvito, S., Surfing Multiple Conformation-Property Landscapes via Machine Learning: Designing Single-Ion Magnetic Anisotropy, Journal of Physical Chemistry C, 124, 10, 2020, 5802-5806Download Item:
Abstract:
Computational statistical disciplines, such as machine learning, are leading to a paradigm shift in the way we conceive the design of new compounds, offering a way to directly design the best compound for specific applications. This approach, known as reverse engineering, requires the construction of models able to efficiently predict continuous structure–property maps. Here, we show that machine learning offers such a possibility by designing a model that predicts both the energy and magnetic properties as a function of the molecular structure of a single-ion magnet. This model is then used to explore the molecular conformational landscapes in search of structures that maximize magnetic anisotropy. We find that a 5% change in one of the coordination angles leads to a ∼50% increase in the anisotropy. This approach can be applied to any structure–property relation and paves the way for a machine-learning-driven optimization of chemical compounds.
Author's Homepage:
http://people.tcd.ie/sanvitoshttp://people.tcd.ie/lunghia
Description:
PUBLISHED
Author: Sanvito, Stefano; Lunghi, Alessandro
Type of material:
Journal ArticleCollections
Series/Report no:
Journal of Physical Chemistry C124
10
Availability:
Full text availableDOI:
http://dx.doi.org/10.1021/acs.jpcc.0c01187Metadata
Show full item recordLicences: