Magnetochemistry, Volume 12, Issue 2
2026 February - 12 articles
Cover Story: The magnetism of lanthanide-based single-molecule magnets is greatly challenging to elucidate, as up to 27 ligand-field parameters need to be inferred from feature-poor experimental data. Machine learning (ML) has shown potential in addressing this challenge. This work first discusses the perspectives of ML approaches to data analysis before presenting a model that combines a variational autoencoder with an invertible neural network to predict ligand field parameters from magnetic susceptibility data. By incorporating common experimental errors through data augmentation, the ML model achieves robust and accurate recovery of the D and E magnetic anisotropy parameters, bringing ML-based analysis closer to routine experimental application. View this paper - Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.