Objectives
Develop a model-based workflow to accelerate advanced materials design
Multiphase and multiscale materials offer improved opportunities to develop high-performance materials with a reduced environmental impact.
To accelerate the design and validation process of advanced materials, MatCHMaker will develop, verify and validate a model-based innovation process.
This workflow will include new characterisation and modelling approaches to better understand and capture material properties and performance at various scales and from multiple dimensions. It also aims to integrate artificial intelligence tools.
To accelerate the design and validation process of advanced materials, MatCHMaker will develop, verify and validate a model-based innovation process.
This workflow will include new characterisation and modelling approaches to better understand and capture material properties and performance at various scales and from multiple dimensions. It also aims to integrate artificial intelligence tools.
Reinforce traceability, integrity and interoperability of characterisation and modelling data and workflows
Retrieving data from multiple databases is difficult since the available application programming interfaces (APIs) differ from one database to another.
MatCHMaker will develop an ontology-based platform to increase the level of interoperability.
This will enable the horizontal link between services across vertical marketplaces and addresses the entire materials development cycle. The creation of a digital twin of materials on which various actions can be performed explores the synergies between physics‐based and data‐driven modelling further.
This will enable the horizontal link between services across vertical marketplaces and addresses the entire materials development cycle. The creation of a digital twin of materials on which various actions can be performed explores the synergies between physics‐based and data‐driven modelling further.
Propose an open data repository
The MatCHMaker Open Repository will enable users to have a large number of models and data documented in an interoperable manner; All data pipelines and structures to be exploited within such machine learning functionalities will be standardised and made available in a Common European Artificial Intelligence marketplace.
The design will follow best practices in terms of explainability and transparency to ensure the efficient and simple use of such tools, providing support to material sciences users.
The design will follow best practices in terms of explainability and transparency to ensure the efficient and simple use of such tools, providing support to material sciences users.