TY - JOUR
T1 - Formation energy prediction of neutral single-atom impurities in 2D materials using tree-based machine learning
AU - Kesorn, Aniwat
AU - Hunkao, Rutchapon
AU - Na Talang, Cheewawut
AU - Cholsuk, Chanaprom
AU - Sinsarp, Asawin
AU - Vogl, Tobias
AU - Suwanna, Sujin
AU - Yuma, Suraphong
N1 - Publisher Copyright:
© 2024 The Author(s). Published by IOP Publishing Ltd.
PY - 2024/9/1
Y1 - 2024/9/1
N2 - We applied tree-based machine learning algorithms to predict the formation energy of impurities in 2D materials, where adsorbates and interstitial defects are investigated. Regression models based on random forest, gradient boosting regression, histogram-based gradient-boosting regression, and light gradient-boosting machine algorithms are employed for training, testing, cross validation, and blind testing. We utilized chemical features from fundamental properties of atoms and supplemented them with structural features from the interaction of the added chemical element with its neighboring host atoms via the Jacobi-Legendre (JL) polynomials. Overall, the prediction accuracy yields optimal MAE ≈ 0.518 , RMSE ≈ 1.14 , and R 2 ≈ 0.855 . When trained separately, we obtained lower residual errors RMSE and MAE, and higher R2 value for predicting the formation energy in the adsorbates than in the interstitial defects. In both cases, the inclusion of the structural features via the JL polynomials improves the prediction accuracy of the formation energy in terms of decreasing RMSE and MAE, and increasing R2. This work demonstrates the potential and application of physically meaningful features to obtain physical properties of impurities in 2D materials that otherwise would require higher computational cost.
AB - We applied tree-based machine learning algorithms to predict the formation energy of impurities in 2D materials, where adsorbates and interstitial defects are investigated. Regression models based on random forest, gradient boosting regression, histogram-based gradient-boosting regression, and light gradient-boosting machine algorithms are employed for training, testing, cross validation, and blind testing. We utilized chemical features from fundamental properties of atoms and supplemented them with structural features from the interaction of the added chemical element with its neighboring host atoms via the Jacobi-Legendre (JL) polynomials. Overall, the prediction accuracy yields optimal MAE ≈ 0.518 , RMSE ≈ 1.14 , and R 2 ≈ 0.855 . When trained separately, we obtained lower residual errors RMSE and MAE, and higher R2 value for predicting the formation energy in the adsorbates than in the interstitial defects. In both cases, the inclusion of the structural features via the JL polynomials improves the prediction accuracy of the formation energy in terms of decreasing RMSE and MAE, and increasing R2. This work demonstrates the potential and application of physically meaningful features to obtain physical properties of impurities in 2D materials that otherwise would require higher computational cost.
KW - 2D materials
KW - Jacobi-Legendre polynomials
KW - chemical features
KW - decision tree
KW - formation energy
KW - machine learning
KW - structural features
UR - http://www.scopus.com/inward/record.url?scp=85200839296&partnerID=8YFLogxK
U2 - 10.1088/2632-2153/ad66ae
DO - 10.1088/2632-2153/ad66ae
M3 - Article
AN - SCOPUS:85200839296
SN - 2632-2153
VL - 5
JO - Machine Learning: Science and Technology
JF - Machine Learning: Science and Technology
IS - 3
M1 - 035039
ER -