What is MARVEL?
The project, Materials' Revolution: Computational Design and Discovery of Novel Materials (MARVEL), is currently in its second phase and part of the SNF National Centres of Competence in Research (NCCR) where EPF Lausanne serves as the leading house. The goal of MARVEL is to both transform and accelerate the design and discovery of novel materials as well as their chemical properties. To achieve this goal, MARVEL consists of nine design and discovery projects, two incubator projects, as well as two supporting platform projects. Each of these is aimed at unifying the strengths of diverse disciplines, such as chemistry and computer science, in an effort to showcase the benefits of quantum mechanical simulations for modelling realistic, complex systems.
Incubator 2: Project Overview
This incubator project consists of three groups with varied research focuses, ranging from quantum chemistry to applied machine learning. Currently, molecule properties are calculated by quantum-mechanic simulations, which require considerable computational costs. Phase 1 of this project demonstrated that machine learning models are able to predict the molecular properties with reasonable accuracy. In Phase 2, these properties will be investigated further.
Project Aim
The aim of this project is to design and discover novel materials as well as their chemical properties based on data obtained from quantum-mechanical simulations. This data is used to develop two types of models: First, we consider deep learning models to predict the properties of individual molecules as surrogates for quantum mechanical simulations. Second, we develop deep latent variable models to generate novel materials on the basis of a set of user-defined properties.
Funding
This project is supported by the Swiss National Science Foundation (SNF) and the National Centres of Competence in Research (NCCR).
