Building Machine Learning assisted Phase Diagrams: three chemically relevant examples. – (Xabier Telleria Allika / LCPQ / Seminar). – 14/04/2022

Xabier Telleria Allika (hosted by Arjan and Stefano)

Abstract:

In this work we present a systematic procedure to build phase diagrams for chemically relevant properties by the use of a semi-supervised machine learning technique called uncertainty sampling. Concretely, in this work we focus on ground state spin multiplicity and chemical bonding properties. As a first step, we have obtained single-eutectic-point-
containing solid-liquid systems which have been suitable for contrasting the validity of this approach. Once this was settled, on the one hand, we have built magnetic phase diagrams for several Hooke atoms containing few electrons (4 and 6) trapped in spheroidal harmonic potentials. Changing the parameters of the confinement potential such as curvature and anisotropy and interelectronic interaction strength, we have been able to obtain and rationalise magnetic phase transitions flipping the ground state spin multiplicity from singlet (non magnetic) to triplet (magnetic) states. On the other hand, Bader’s analysis is performed upon helium dimers confined by spherical harmonic potentials. Covalency is studied using descriptors as sign for ∆ρ(rC) and H(rC) and the dependency on the degrees of freedom of the system is studied i.e. potential curvature ω2 and inter atomic distance R. As a result, we have observed that there may exist a covalent bond between He atoms for short enough distances and strong enough confinement. This machine learning procedure could, in principle, be applied to the study of other chemically relevant properties involving phase diagrams, saving a lot of computational resources