Exploring the polymorphism of dicalcium silicates using transfer learning enhanced machine learning atomic potentials
Preprint
- 10 April 2024
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
Abstract
Belitic cements are a greener alternative to Ordinary Portland Cements due to the lower CO2 associated to their production. However, their low reactivity with water is currently a drawback, resulting in longer setting times. In this study, we utilize a combination of evolutionary algorithms and machine learning atomic potentials (MLPs) to identify previously unreported belite polymorphs that may exhibit higher hydraulic reactivity than the known phases. To address the high computational demand of this methodology, we propose a novel transfer learning approach for generating MLPs. First, the models are pre-trained on a large set of classical data (ReaxFF) and then re-trained with Density Functional Theory (DFT) data. We demonstrate that the transfer learning enhanced potentials exhibit higher accuracy, require less training data, and are more transferable than those trained exclusively on DFT data. The generated machine learning potential enables a fast, exhaustive, and reliable exploration of the dicalcium silicate polymorphs. This includes studying their stability through phonon analysis and calculating their structural and elastic properties. Overall, we identify ten new belite polymorphs within the energy range of the existing ones, including a layered phase with potentially high reactivity.Keywords
All Related Versions
Funding Information
- Eusko Jaurlaritza (IT1458-22)
- Eusko Jaurlaritza (PRE_2019_1_0025)
- Euskal Herriko Unibertsitatea (Colab22/06)
This publication has 33 references indexed in Scilit:
- LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scalesComputer Physics Communications, 2022
- First-Principles Calculations on Polymorphs of Dicalcium Silicate—Belite, a Main Component of Portland CementThe Journal of Physical Chemistry C, 2019
- Eco-efficient cements: Potential economically viable solutions for a low-CO2 cement-based materials industryCement and Concrete Research, 2018
- The PseudoDojo: Training and grading a 85 element optimized norm-conserving pseudopotential tableComputer Physics Communications, 2018
- Hydration, mechanical property and C-S-H structure of early-strength low-heat cement-based materialsMaterials Letters, 2018
- An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2Computational Materials Science, 2016
- New developments in evolutionary structure prediction algorithm USPEXComputer Physics Communications, 2013
- How Evolutionary Crystal Structure Prediction Works—and WhyAccounts of Chemical Research, 2011
- Semiempirical GGA‐type density functional constructed with a long‐range dispersion correctionJournal of Computational Chemistry, 2006
- The chemistry of dicalcium silicate mineralJournal of Materials Science, 1979