Surfing Multiple Conformation-Property Landscapes via Machine Learning: Designing Single-Ion Magnetic Anisotropy

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.