In this work, we perform screening of functional atomic impurities in Cd-chalcogenide semiconductors using high-throughput computations and machine learning. High-performance computing resources located at Argonne National Lab (Carbon at CNM and LCRC) and Berkeley Lab (NERSC) were utilized to generate large databases of impurity properties from first principles-based density functional theory (DFT) computations. This dataset was combined with material descriptors?ranging from coordination environments to tabulated elemental properties to cheaper DFT data?to train state-of-the-art regression models. LASSO, random forest, and kernel ridge regression techniques were used and the predictive models were optimized with respect to the type and quantity of training data, optimal hyperparameter sets, and cross-validation errors. The best models thus achieved were deployed to make predictions for the combinatorial chemical space of all possible impurity atoms in Cd-chalogenide compounds, following which screening was performed on the basis of their relative energetics, leading to a shortlist of impurities for every compound which can affect a desirable or disastrous change in the optical and electronic properties of the semiconductor. The data and models developed in this work have major consequences for semiconductor applications ranging from solar cells to infrared sensors to quantum information sciences.

The nanoHUB tool "Machine Learning Defect Behavior in Semiconductors" used in this hands-on tutorial.

Arun Mannodi-Kanakkithodi is a computational materials scientist working as a postdoctoral researcher at the Center for Nanoscale Materials at Argonne. His research interests include AI-driven design of novel materials for energy applications, optimizing opto-electronic properties of novel semiconductor compositions, generating and mining computational materials databases, materials informatics, and data-driven materials discovery. Arun will begin a new position as assistant professor in Materials Engineering at Purdue University in December 2020.

Network for Computational Nanotechnology (NCN)

Researchers should cite this work as follows:

• Mannodi-Kanakkithodi, A., Toriyama, M.Y., Sen, F.G. et al., Machine-learned impurity level prediction for semiconductors: the example of Cd-based chalcogenides, npj Comput Mater 6, 39 (2020). https://doi.org/10.1038/s41524-020-0296-7

• Arun Kumar Mannodi Kanakkithodi (2020), "Machine Learning Framework for Impurity Level Prediction in Semiconductors," https://nanohub.org/resources/34601.

  BibTex | EndNote

1. data-driven science
2. density functional theory (DFT)
3. electrical properties
4. hands on
5. machine learning
6. material properties
7. materials science
8. NCN Group - Machine Learning
9. NCN Group - Machine Learning Hands-on
10. optical properties
11. random forrest
12. regression
13. semiconductors
14. sensors/sensing
15. solar cells
16. training data
17. tutorial