ML RCUT1: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
 
(19 intermediate revisions by 4 users not shown)
Line 1: Line 1:
{{TAGDEF|ML_FF_RCUT1_MB|[real]|{{TAG|ML_FF_RCUT2_MB}}}}
{{DISPLAYTITLE:ML_RCUT1}}
{{TAGDEF|ML_RCUT1|[real]|8.0}}


Description: This flag sets the cutoff radius for the radial descriptor in the machine learning force field method.
Description: Sets the cutoff radius <math>R_\text{cut}</math> for the radial descriptor <math>\rho^{(2)}_i(r)</math> in <math>\AA</math>.
----
----
The unit of the cut-off radius is given in <math>\AA</math>.
The radial descriptor for machine-learned force fields is constructed from


== Related Tags and Sections ==
<math>
{{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_RCUT2_MB}}, {{TAG|ML_FF_W1_MB}}, {{TAG|ML_FF_W2_MB}}
\rho_{i}^{(2)}\left(r\right) = \frac{1}{4\pi} \int \rho_{i}\left(r\hat{\mathbf{r}}\right) d\hat{\mathbf{r}}, \quad \text{where} \quad
\rho_{i}\left(\mathbf{r}\right) = \sum\limits_{j=1}^{N_{\mathrm{a}}} f_{\mathrm{cut}}\left(r_{ij}\right) g\left(\mathbf{r}-\mathbf{r}_{ij}\right)
</math>


{{sc|ML_FF_RCUT1_MB|Examples|Examples that use this tag}}
and <math>g\left(\mathbf{r}\right)</math> is an approximation of the delta function. A basis set expansion of <math>\rho^{(2)}_i(r)</math> yields the expansion coefficients <math>c_{n00}^{i}</math>, which are used in practice to describe the atomic environment; refer to the [[Machine learning force field: Theory#Descriptors|theory of machine-learned force fields]] for details. The tag {{TAG|ML_RCUT1}} sets the cutoff radius <math>R_\text{cut}</math> at which the cutoff function <math>f_{\mathrm{cut}}\left(r_{ij}\right)</math> decays to zero.
{{NB|mind|The cutoff radius determines how many neighbor atoms <math>N_\mathrm{a}</math> are considered to describe each central atom's environment. Hence, important features may be missed if the cutoff radius is too small. On the other hand, a large cutoff radius increases the computational cost of the descriptor as the cutoff sphere contains more neighbor atoms. A good compromise is always system-dependent. Therefore, different values should be tested to achieve satisfying accuracy '''and''' speed.}}
 
The unit of the cut-off radius is <math>\AA</math>.
 
== Related tags and articles ==
{{TAG|ML_LMLFF}}, {{TAG|ML_RCUT2}}, {{TAG|ML_W1}}, {{TAG|ML_SION1}}, {{TAG|ML_SION2}}, {{TAG|ML_MRB1}}, {{TAG|ML_MRB2}}
 
{{sc|ML_RCUT1|Examples|Examples that use this tag}}
----
----


[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]]
[[Category:INCAR tag]][[Category:Machine-learned force fields]]

Latest revision as of 06:34, 11 May 2023

ML_RCUT1 = [real]
Default: ML_RCUT1 = 8.0 

Description: Sets the cutoff radius for the radial descriptor in .


The radial descriptor for machine-learned force fields is constructed from

and is an approximation of the delta function. A basis set expansion of yields the expansion coefficients , which are used in practice to describe the atomic environment; refer to the theory of machine-learned force fields for details. The tag ML_RCUT1 sets the cutoff radius at which the cutoff function decays to zero.

Mind: The cutoff radius determines how many neighbor atoms are considered to describe each central atom's environment. Hence, important features may be missed if the cutoff radius is too small. On the other hand, a large cutoff radius increases the computational cost of the descriptor as the cutoff sphere contains more neighbor atoms. A good compromise is always system-dependent. Therefore, different values should be tested to achieve satisfying accuracy and speed.

The unit of the cut-off radius is .

Related tags and articles

ML_LMLFF, ML_RCUT2, ML_W1, ML_SION1, ML_SION2, ML_MRB1, ML_MRB2

Examples that use this tag