Predicting Compound Melting Temperature from Computationally Derived Properties via Machine Learning

Authors

  • Amy Lin Princeton High School
  • Mark Eastburn Princeton High School

DOI:

https://doi.org/10.47611/jsrhs.v13i3.7279

Keywords:

melting temperature, melting point, melting temperature prediction, machine learning, random forest, regression, properties, data augmentation, compound groups, elastic moduli, bulk modulus, shear modulus, electronegativity, energy, atomic row

Abstract

Melting temperature is a fundamental material property used in a wide variety of scientific disciplines. To eliminate the need for experimentally measuring melting temperature, often costly and potentially dangerous, we developed a new computational approach that predicts a compound’s melting temperature from its material properties, computed by Density-functional theory or other computational methods, using machine learning models. The proposed machine learning models achieved promising results, with a Mean Percentage Absolute Error of 15%-20%. We also identified important material properties in predicting melting temperature across various groups of compounds containing metals, transition metals, post transition metals, alkaline earth metals, halogens, and chalcogens.

Downloads

Download data is not yet available.

References or Bibliography

Hong Q.J., Ushakov S.V., van de Walle A., Navrotsky A. Melting temperature prediction using a graph neural network model: From ancient minerals to new materials. Proc Natl Acad Sci U S A. 2022 Sep 6;119(36):e2209630119. Epub 2022 Aug 31. PMID: 36044552; PMCID: PMC9457469. https://doi.org/10.1073/pnas.2209630119

Lee, A., Sarker, S., Saal, J.E. et al. Machine learned synthesizability predictions aided by density functional theory. Commun Mater 3, 73 (2022). https://doi.org/10.1038/s43246-022-00295-7

Guan P.-W., Viswanathan V. MeltNet: Predicting alloy melting temperature by machine learning. (2020). https://doi.org/10.48550/arXiv.2010.14048

Legrain, F., Carrete, J., van Roekeghem, A., Curtarolo, S. & Mingo, N. How chemical composition alone can predict vibrational free energies and entropies of solids. Chem. Mater. 29, 6220–6227 (2017). https://doi.org/10.48550/arXiv.1703.02309

Kirklin, S., Saal, J., Meredig, B. et al. The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies. npj Comput Mater 1, 15010 (2015). https://doi.org/10.1038/npjcompumats.2015.10

de Jong, M., Chen, W., Angsten, T. et al. Charting the complete elastic properties of inorganic crystalline compounds. Sci Data 2, 150009 (2015). https://doi.org/10.1038/sdata.2015.9

The Materials Project. Materials Project. https://legacy.materialsproject.org/

Pymatgen. pymatgen. https://pymatgen.org/

Matminer. matminer (Materials Data Mining) - matminer 0.9.0 documentation. https://hackingmaterials.lbl.gov/matminer/

Meredig B, et al. Combinatorial screening for new materials in unconstrained composition space with machine learning. Physical Review B. 2014;89:094104 (2014). https://doi.org/10.1103/PhysRevB.89.094104.

Jha, D., Ward, L., Paul, A. et al. ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition. Sci Rep 8, 17593 (2018). https://doi.org/10.1038/s41598-018-35934-y

A. M. Krajewski, J. W. Siegel, J. Xu, Z.-K. Liu, Extensible structure-informed prediction of formation energy with improved accuracy and usability employing neural networks. Comput. Mater. Sci. 208, 111254 (2022). https://doi.org/10.1016/j.commatsci.2022.111254

F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, G. Monfardini, The graph neural network model. IEEE Trans. Neural Netw. 20, 61–80 (2009). https://doi.org/10.1109/TNN.2008.2005605

S. V. Krivovichev, Structural complexity and configurational entropy of crystals. Acta Crystallogr. B Struct. Sci. Cryst. Eng. Mater. 72, 274–276 (2016). https://doi.org/10.1107/s205252061501906x

Jain, A. et al. Commentary: The materials project: A materials genome approach to accelerating materials innovation. Apl Materials 1, 011002 (2013). https://doi.org/10.1063/1.4812323

Jain, A. et al. A high-throughput infrastructure for density functional theory calculations. Comput. Mater. Sci. 50, 2295–2310 (2011). https://doi.org/10.1016/j.commatsci.2011.02.023

Hautier, G., Ong, S. P., Jain, A., Moore, C. J. & Ceder, G. Accuracy of density functional theory in predicting formation energies of ternary oxides from binary oxides and its implication on phase stability. Phys. Rev. B 85, 155208 (2012). https://doi.org/10.1103/PhysRevB.85.155208

Hafner, J., Wolverton, C. & Ceder, G. Toward computational materials design: the impact of density functional theory on materials research. MRS bulletin 31, 659–668 (2006). https://doi.org/10.1557/mrs2006.174

Schmidt, J., Marques, M.R.G., Botti, S. et al. Recent advances and applications of machine learning in solid-state materials science. npj Comput Mater 5, 83 (2019). https://doi.org/10.1038/s41524-019-0221-0

Artem R. Oganov, Colin W. Glass; Crystal structure prediction using ab initio evolutionary techniques: Principles and applications. J. Chem. Phys. 28 June 2006; 124 (24): 244704. https://doi.org/10.1063/1.2210932

Published

08-31-2024

How to Cite

Lin, A., & Eastburn, M. (2024). Predicting Compound Melting Temperature from Computationally Derived Properties via Machine Learning. Journal of Student Research, 13(3). https://doi.org/10.47611/jsrhs.v13i3.7279

Issue

Section

HS Research Articles