ML-NANOCAT - Machine Learning Aided Design of Novel Nano-catalytic Materials
The vision of ML-NANOCAT is to evolve a paradigm shift designing-rule-principle in catalytic materials, potential contributing to the global effort towards the green energy transition and carbon neutrality by 2050. Combustion of fossil fuels for the production of energy is currently producing over 35 gigatons of C02 per year, which cannot be accommodated in the natural carbon cycle. This, in turn, has led to unprecedented increase of the concentration of C02 in the atmosphere over the last two centuries, causing a greenhouse effect that has a major impact on the Earth's climate.
Considering that our modem economies still rely heavily on fossil fuels for energy production, it is extremely urgent to develop technologies that minimize C02 accumulation in the atmospheric environment. The overall goal of ML-NANOCAT is to realize breakthroughs in catalysis enabling a new generation of catalytic materials for C02 reduction, via a synergistic approach that involves multi-scale computational modelling, advanced machine learning (ML) algorithms and tailored design of novel catalysts. In this aspect. computational approaches (simulations and ML algorithms). together with specific "materials properties databases" can be used to provide a first screening of candidate catalytic materials for specific reactions, whereas in the long term, such an "in-silica" design of catalysts could be used to tailor a variety of characteristics, as a trade-off to traditional trial and error approaches.
Following the above paradigm, ML-NANOCAT aims in providing synergetic research that includes advanced computational methods and ML algorithms, formulating a computational predictive tool (suite) for the tailored design and synthesis of novel catalytic materials for C02 reduction. The computational suite will guide state-of-the-art synthesis and characterization methods for creating new nano-catalytic materials that within the framework of ML-NANOCAT will be tested and validated under operating conditions.
CyI Principal Investigator: Prof. Dr. Vangelis Harmandaris
Additional Info
- Acronym: ML-NANOCAT
- Website: Under construction
- Center: CaSToRC
- Funding Source: RIF-CO-DEVELOP (GREEN TRANSITION)/0322
- CyI Funding: €359.600
- Funding Period: 2 years 3 months
- Starting Date: 01/02/2023
- End Date: 30/04/2025
- Coordinator: THE CYPRUS INSTITUTE
- Partners: NOVAMECHANICS LTD
