Nanosafety-data-reusability-34-datasets

Classifying and predicting the electron affinity of diamond nanoparticles using machine learning (2019)

Original Study Abstract

Using a combination of electronic structure simulations and machine learning we have shown that the characteristic negative electron affinity (NEA) of hydrogenated diamond nanoparticles exhibits a class-dependent structure/property relationship. Using a random forest classifier we find that the NEA will either be consistent with bulk diamond surfaces, or much higher than the bulk diamond value; and using class-specific random forest regressors with extra trees we find that these classes are either size-dependent or anisotropy-dependent, respectively. This suggests that the purification or screening of nanodiamond samples to improve homogeneity may be undertaken based on the negative electron affinity.

Data Sample

Nanoparticle NC NH NH/NC D_nm Shape Ani E EA dCC dCCe dCH dCHe tCCC tCCCe tCCH tCCHe
1 5989 904 0.1509 42.218 Cuboctahedron 1.105 -2.926.453.876 -3.391 1.543 0.015 1.116 0.003 109.22 3.04 111.6 1.94
2 5975 976 0.1633 42.187 Truncated octahedron 1.099 -2.928.624.965 -13.483 1.541 0.009 1.118 0.002 109.42 1.77 109.79 1.64
3 4608 780 0.1693 38.853 Cuboctahedron 1.105 -2.259.410.094 -34.553 1.543 0.017 1.116 0.005 109.17 3.31 111.83 2.53
4 4886 844 0.1727 3.958 Truncated octahedron 1.099 -2.399.174.882 -13.515 1.542 0.009 1.118 0.003 109.4 1.96 109.92 1.73
5 3944 688 0.1744 36.991 Cuboctahedron 1.105 -1.936.339.686 -34.713 1.542 0.015 1.117 0.003 109.24 2.96 111.15 2

Data Summary

Variable Count (unique values)
NC 171
NH 113
NH/NC 224
D_nm 171
Shape 13
Ani 47
E 231
EA 230
dCC 22
dCCe 31
dCH 40
dCHe 27
tCCC 48
tCCCe 155
tCCH 125
tCCHe 137
This site is open source. Improve this page.