Extracting Design Principles from Physics-Adapted Machine Learning Problems

Rose K. Cersonsky ( École Polytechnique Fédérale de Lausanne)

Click here to joinLink opens in a new window

Due to the subtle balance of intermolecular interactions that govern structure-property relations, predicting the stability of crystal structures formed from molecular building blocks is a highly non-trivial scientific problem. A particularly active and fruitful approach involves classifying the different combinations of interacting chemical moieties, as understanding the relative energetics of different interactions enables the design of molecular crystals and fine-tuning their stabilities.

While this is usually performed based on the empirical observation of the most commonly encountered motifs in known crystal structures, in this talk I will propose to apply a combination of supervised and unsupervised machine-learning techniques to automate the construction of an extensive library of molecular building blocks. I will introduce a structural descriptor tailored to the prediction of the binding energy for a curated dataset of organic crystals and exploit its atom-centered nature to obtain a data-driven assessment of the contribution of different chemical groups to the lattice energy of the crystal. I will then interpret this library using a low-dimensional representation of the structure-energy landscape and discuss selected examples of the insights that can be extracted from this analysis, showcasing a complete database to guide the design of molecular materials.