ML-MULTIMEM · Machine Learning-aided Multiscale Modelling Framework for Polymer Membranes
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2021-11-15 → 2023-11-14
- EU contribution
- €153,085
- Participants
- 1
- Scheme
- MSCA-IF
Lines connect the coordinator with its partners.
Results in brief
Machine Learning-aided Multiscale Modelling Framework for Polymer Membranes
Materials science explores the properties of materials in a variety of ways: from theoretical models, to computational models and real-world experiments. These analyses allow the development of new materials that suit specific needs. The ML-MULTIMEM project focuses on empowering the molecular simulation of polymers - a ubiquitous family of materials in manufacturing, healthcare, energy, and environmental technologies - with artificial intelligence and especially machine learning methods. This synergy allows modelling complex materials at different scales - what is termed "multi-scale modeling" - with an innovative approach. This offers the opportunity to address a critical challenge in materials science: the bottom-up rational design of complex polymers for diverse applications, using molecular simulation methods. Polymers materials require multiscale strategies to be studied, typically including coarse grained representations. To overcome limitations associated with traditional coarse graining strategies, this project integrated Machine Learning (ML) into molecular simulation methods, utilizing Graph Convolutional Neural Networks to obtain coarse grained force fields for molecular simulations. The project achieved three significant goals: 1. We developed a ML-based multiscale simulation strategy, bridging atomic and coarse-grained scales, for the study of macromolecular and organic systems at bulk conditions. 2. We incorporated the developed ML method into open-source packages and widely used simulation tools. 3. We utilized the developed strategy to simulate organic liquids and polymers of industrial interest (polyethylene, PIM-1), to showcase its application to real-world test cases. This work holds societal significance due to the pervasive use of polymers in manufacturing, healthcare, energy, and environmental technologies. Improving our capacity to design polymers efficiently has the potential to catalyse breakthroughs in diverse sectors. The proposed ML-based approach offers a pathway to potentially increase efficiency and versatility of molecular modelling more generally, with broad implications for advancements in a multitude of industries and technologies.
Data: CORDIS, © European Union
Project objective
The goal of this project is to build a systematic modelling framework for advanced polymer materials, that are widely employed in numerous membrane separation applications, especially as gas separation media for carbon capture. Polymers are very challenging to simulate, due to the wide range of timescales that are present in these systems and require elaborate system-specific multiscale strategies. A hierarchical simulation strategy will be developed, encompassing atomistic, mesoscopic and continuum scales, integrating machine learning techniques. The artificial intelligence aided multi-scale approach proposed constitutes a generalized methodology for the efficient computational study of polymers. The synergy of unsupervised machine learning (ML) clustering techniques and neural networks (NN), will enable the extraction of accurate coarse-grained (CG) representations and force fields of the polymer systems, bringing this complex problem within computational reach. Optimized ML models will be integrated into Molecular Dynamics and innovative Monte Carlo simulations at the CG level, with the latter enabling the equilibration up to high molecular weight of polymers of complex chemical constitution, and the prediction of their micro- and macroscopic behaviour. Molecular simulation results will be integrated into macroscopic equation-of-state-based models, resulting in a bottom-up determination of the relevant process parameters for membrane separations (permeability and selectivity) in a wide range of conditions, for pure gases and gas mixtures. Systematic hierarchical modelling provides unique property prediction means, simultaneously shedding light on the mechanisms that are responsible for the materials end-use performance. This is a stepping stone towards the rational design of advanced processes from the molecular level all the way up to industrial applications, which in the present case involve novel separation technologies with great environmental impact.
Original text from CORDIS.
Participants
- NATIONAL CENTER FOR SCIENTIFIC RESEARCH ""DEMOKRITOS"""" · Agia ParaskeviCoordinatorGreece
Links
Data: CORDIS, © European Union