Abstract
The ability to predict the likelihood of impurity incorporation and their electronic energy levels in semiconductors is crucial for controlling its conductivity, and thus the semiconductor’s performance in solar cells, photodiodes, and optoelectronics. The difficulty and expense of experimental and computational determination of impurity levels makes a data-driven machine learning approach appropriate. In this work, we show that a density functional theory-generated dataset of impurities in Cd-based chalcogenides CdTe, CdSe, and CdS can lead to accurate and generalizable predictive models of defect properties. By converting any semiconductor + impurity system into a set of numerical descriptors, regression models are developed for the impurity formation enthalpy and charge transition levels. These regression models can subsequently predict impurity properties in mixed anion CdX compounds (where X is a combination of Te, Se and S) fairly accurately, proving that although trained only on the end points, they are applicable to intermediate compositions. We make machine-learned predictions of the Fermi-level-dependent formation energies of hundreds of possible impurities in 5 chalcogenide compounds, and we suggest a list of impurities which can shift the equilibrium Fermi level in the semiconductor as determined by the dominant intrinsic defects. Machine learning predictions for the dominating impurities compare well with DFT predictions, revealing the power of machine-learned models in the quick screening of impurities likely to affect the optoelectronic behavior of semiconductors.
Highlights
No crystalline material is devoid of defects and impurities
In this work, we showed that machine learning can be used to train accurate predictive models of the formation enthalpy (ΔH) and defect transition levels (ε(q1/q2)) of impurities in Cd-based chalcogenides using DFT generated data
A comparison of DFT and ML predictions shows that less than 5% of the entire population of impurities in CdTe is classified as false negative or false positive (in terms of its ‘dominating’ nature), giving us confidence that this ML approach can be used for a successful screening of stable and active impurity atoms in preferred defect sites
Summary
The imperfections in a crystal determine its properties as much as the regular arrangement of atoms do. When it comes to crystalline semiconducting materials, it is known that defects such as vacancies, native or impurity interstitials or substitutions, surface states, and grain boundaries can influence their optoelectronic properties. In the absence of external impurities, native defects determine the equilibrium Fermi level in the semiconductor, and the nature of conductivity (p-type, n-type or intrinsic) and charge carriers[1,2,3]. The introduction of impurity atoms can change the conductivity as determined by the dominant native defects, based on their formation enthalpies as a function of the Fermi energy[1,4]. Foresight about the impact of certain impurities on the electronic structure and conductivity of the material is crucial in either trying to curb their presence, or intentionally incorporating them in the semiconductor lattice to induce a desirable optoelectronic change
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
