Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

A Synthesis Oracle for Scalable and Sustainable Porous Nanomaterials

Project description

Nanomaterial synthesis for a greener future

Europe’s push towards net zero hinges on low-carbon technologies such as adsorption-based separation and refrigeration. At the heart of this are metal-organic frameworks (MOFs), porous nanomaterials with huge potential. However, selecting and producing the most cost-effective MOF remains a hurdle. Supported by the Marie Skłodowska-Curie Actions programme, the SOSS-PN project tackles this by creating a holistic platform that maps and accelerates MOF synthesis research. Combining text mining, molecular simulations, and machine learning, the project focuses first on the MOF UiO-66, building a ‘synthesis oracle’ to predict optimal production methods. This approach, refined through experiments and active learning, will then extend to related MOFs. By revolutionising how nanomaterials are developed, SOSS-PN paves the way for faster, greener industrial processes essential for Europe’s sustainable future.

Objective

Adoption of new, low-carbon processes like adsorption-based separation and refrigeration is essential to drive Europe’s net zero transition and achieve the targets of the European Green Deal. Advanced porous nanomaterials like metal-organic frameworks (MOFs) are key enabling technologies to achieve this goal, however their adoption is stymied by a chicken-and-egg problem: identifying the most cost-effective MOF for each application, and investing sufficient research time to reduce synthesis costs for the best candidates. In this fellowship I will address this dual challenge by developing a holistic platform to systematise MOF synthesis methodology research, hence both accelerating and generalising the hunt for an optimal synthesis method.

Using a combination of text mining and molecular simulations, I will construct a semantic knowledge graph representation for the synthesis of the common MOF UiO-66, creating a database of synthesis methods connected to to material quality profiles. Once created, I will develop a UiO-66 synthesis “oracle” – a machine learning model which can generate novel synthesis procedures from target material quality profiles. I will then refine the synthesis oracle functions experimentally using Bayesian active learning to identify the global optimum synthesis parameters with respect to several quality metrics. Finally, I will transfer the UiO-66 synthesis oracle to a family of related MOF materials, using further lab synthesis and active learning to fine-tune the quality of these secondary MOFs.

This new paradigm in nanomaterial synthesis optimisation will be transformative in the field of synthesis optimisation and intensification, representing a novel approach that is generalisable to any synthesis target. In turn, completion of this fellowship will perfectly position me to transition into an independent academic career at the interface of digital chemistry and process intensification.

Fields of science (EuroSciVoc)

Programme(s)

Topic(s)

Funding Scheme

HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European Fellowships

See all projects funded under this funding scheme

Call for proposal

(opens in new window) HORIZON-MSCA-2024-PF-01

See all projects funded under this call

Coordinator

UNIVERSITEIT GENT
Net EU contribution
€ 200 400,00
Address
SINT PIETERSNIEUWSTRAAT 25
9000 Gent
Belgium
Region
Vlaams Gewest Prov. Oost-Vlaanderen Arr. Gent
Activity type
Higher or Secondary Education Establishments
Links
Total cost
No data

Partners (1)