ML_SION1

ML_SION1 = [real]
Default: ML_SION1 = 0.5 

Description: This tag specifies the width ${\sigma }_{\text{atom}}$ of the Gaussian functions used for broadening the atomic distributions of the radial descriptor ${\rho }_i^{(2)}(r)$ within the machine learning force field method.

---

The radial descriptor is constructed from

${\rho }_i^{(2)}\left(r\right)=\frac{1}{4\pi }\int {\rho }_i\left(r\widehat{\mathbf{𝐫}}\right)d\widehat{\mathbf{𝐫}},\text{where}{\rho }_i\left(\mathbf{𝐫}\right)=\sum _{j=1}^{N_{\mathrm{a}}}{f}_{\mathrm{c}\mathrm{u}\mathrm{t}}\left(r_{ij}\right)g(\mathbf{𝐫}-{\mathbf{𝐫}}_{ij})$

and $g\left(\mathbf{𝐫}\right)$ is the following approximation of the delta function:

$g\left(\mathbf{𝐫}\right)=\frac{1}{\sqrt{2{\sigma }_{\mathrm{a}\mathrm{t}\mathrm{o}\mathrm{m}}\pi }}\mathrm{e}\mathrm{x}\mathrm{p}(-\frac{|\mathbf{𝐫}{|}^2}{2{\sigma }_{\mathrm{a}\mathrm{t}\mathrm{o}\mathrm{m}}^2}).$

The tag ML_SION1 sets the width ${\sigma }_{\text{atom}}$ of the above Gaussian function (see this section for more details).

Tip: Our test calculations indicate that ML_SION1 = ML_SION2 results in an optimal training performance. Furthermore, a value of 0.5 was found to be a good default value for both. However, the best choice is somewhat system-dependent. For instance, a smaller value for ML_SION1 can increase the number of local reference configurations, and hence ultimately the quality of the MLFF. See also here.

The unit of ML_SION1 is $\AA$.

Related tags and articles

ML_LMLFF, ML_SION2, ML_RCUT1, ML_RCUT2, ML_MRB1, ML_MRB2

Examples that use this tag

---