Workshop Overview

Recently, Machine Learning (ML) methods have penetrated almost all research areas in materials modelling and high-throughput materials screening. And yet the ML triumph has so far mainly focused on developing surrogate models for the potential energy surface (PES) with superior computational efficiency while retaining first principles accuracy. The approach to learn observable properties directly is just emerging and is challenged by several issues, which we intend to address.

The event is meant to support the development of a new collaborative, international network connecting different fields of research and integrating the young researchers community with the help of a scientifically diverse, interactive workshop.

General Information

Abstracts: We invite abstract submissions for contributed talks (20min) and posters. When submitting your participation request, please specify clearly in Your message whether you are applying for a contributed talk (20min) or a poster and include your abstract in Your message. In order to select the contributed talks and posters, we ask that all interested people also include a Motivation for attendance, and upload their academic CV following submission. In order to do this pelase submit your abstract and motivation in the participation page, and then following your submission, you will be able to upload your CV under the tab "My participation" in your CECAM account. If you have any questions please don't hesitate to reach out to harper 'at' fhi.mpg.de

On-site participation: Since the number of on-site participants is limited, the selection of the accepted participants onsite will be based on the motivation included in the registration.

Online participation: will be possible (without a contribution).

Submission deadline: 19 April 2024

We will confirm your participation after the deadline for registration and let you know if your contribution has been chosen as a poster or talk. If for any reasons you should need an earlier confirmation, please do not hesitate to let us know.

Topics:

• ML of electron density and Hamiltonians

• ML of electronic observables

• ML of mechanical & magnetic observables

• ML of spectroscopic observables

• ML of reaction networks

• Theoretical and experimental databases

Objectives

The majority of materials modelling with ML methods represents the (PES) of a material based on the assumption, that the total energy of the system can be decomposed into atomic contributions, which in a first approximation are described as a function of the local atomic environment [1,2]. However, several observables such as charge transfer, dipoles, and the material’s properties in an applied electric field are inherently non-local properties. First approaches [3,4] are able to include long range interactions in models for interatomic potentials. It remains an open question if or how these or other methods can be adapted for ML models of non-local observables.

In contrast to the scalar potential energy of a system, many properties are either vectors, like dipoles, or high rank tensors, like electric field gradients, or more complex properties, like density of states. First implementations encode tensorial properties in either rotationally invariant or equivariant representations [5-7]. Other approaches aim to learn the entire electron density in order to derive the observables [8-10]. However, the practical application to physical observables is still very limited. An open discussion of the concepts is necessary and will provide an essential contribution to the dissemination of the methods within the community.

The majority of materials and their observables are unambiguously described by the atomic structure features. Some properties however also depend on spin states, magnetic arrangement or atomic charges. Including information like atomic magnetic vectors or atomic charges in the feature vector is challenging and not many approaches exist [11,12] to solve the problem, which needs to be addressed to model key properties like charge transfer and spin waves.

The accuracy and performance of any ML model depends critically on the extent and diversity of its training dataset. The different available databases [13-16] of ‘synthetic’ first principle material properties provide a valuable wealth of information, but approaches to combine data have yet to be developed. Other databases [17-19] complement the available information by experimental data. The question remains, whether or how to combine experimental and theoretical data on equal footing in order to pool the available resources.The workshop aims to tackle the challenges in the fledgling field of ML of observables covering spectroscopic, electronic, thermodynamic, magnetic, and mechanical properties as well as ML approaches to predict the electron density.

We gratefully acknowledge the support by CECAM, the Psi-k Charity, Deutsche Forschungsgemeinschaft, and the Max-Planck-Gesellschaft.