We present a data-driven approach to predict entropy changes (ΔS) in small magnetic fields in single-molecule magnets (SMMs) relevant to their application as magnetocaloric refrigerants. We construct a database of SMMs with a representation scheme incorporating aspects related to dimensionality, structure, local coordination environment, ideal total spin of magnetic ions, ligand type, and linking chemistry. We train machine learning models for predicting the entropy change as a function of structure and chemistry and use the models to arrive at ΔS for hypothetical molecules. We also identify key descriptors that affect the entropy change, thus providing insights into designing tailored SMMs with improved magnetocaloric properties.
This work is highlighted by AIP Scilight:
See paper at:
"Machine learning accelerates design of single-molecule magnets for magnetocaloric applications", Appl. Phys. Lett. 114, 222404 (2019); Ludwig Holleis, B. S. Shivaram, and Prasanna V. Balachandran