Abstract
The enthalpy of formation is an important thermodynamic property. Developing fast and accurate methods for its prediction is of practical interest in a variety of applications. Material informatics techniques based on machine learning have recently been introduced in the literature as an inexpensive means of exploiting materials data, and can be used to examine a variety of thermodynamics properties. We investigate the use of such machine learning tools for predicting the formation enthalpies of binary intermetallic compounds that contain at least one transition metal. We consider certain easily available properties of the constituting elements complemented by some basic properties of the compounds, to predict the formation enthalpies. We show how choosing these properties (input features) based on a literature study (using prior physics knowledge) seems to outperform machine learning based feature selection methods such as sensitivity analysis and LASSO (least absolute shrinkage and selection operator) based methods. A nonlinear kernel based support vector regression method is employed to perform the predictions. The predictive ability of our model is illustrated via several experiments on a dataset containing 648 binary alloys. We train and validate the model using the formation enthalpies calculated using a model by Miedema, which is a popular semiempirical model used for the prediction of formation enthalpies of metal alloys.
Highlights
The thermodynamic data of alloys such as the standard enthalpy of formation ∆H plays an important role in several applications, e.g., in the calculation of phase diagrams and materials design, in the exploration of new materials having high melting points that can be used in advanced coal-fired plants, building heat-exchangers, filters, and turbines, and many more
The method we propose differs from previous machine learning (ML) techniques in that it uses readily available properties of the constituting elements, complemented by some basic properties of the compounds that are available in popular databases (e.g., Materials Project25), to predict the formation enthalpies
Our results indicate that features selected based on the prior physics knowledge perform better in predicting enthalpies than those obtained through machine learning techniques
Summary
The thermodynamic data of alloys such as the standard enthalpy of formation ∆H ( known as standard heat of formation) plays an important role in several applications, e.g., in the calculation of phase diagrams and materials design, in the exploration of new materials having high melting points that can be used in advanced coal-fired plants, building heat-exchangers, filters, and turbines, and many more. In a series of papers[3,5,6,7], Miedema and his coauthors developed a semi-empirical method for predicting the heat of formation of binary intermetallic compounds that contain at least one transition metal They showed that the formation enthalpies of such binary alloys can, in general, be described in terms of a simple atomic model, that depends only on two parameters of the constituent atoms. Ideas from machine learning have been coupled with databases of ab initio calculations to estimate molecular electronic properties in chemical compound space, including the enthalpy of formation of compounds[23,24] These methods still have the major disadvantage of requiring results from many DFT calculations, which may not be possible for alloys without given crystal structures, i.e., amorphous or noncrystalline alloys.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.