ML SION2
ML_SION2 = [real]
Default: ML_SION2 = 1.5*ML_SION1
Description: This tag specifies the width [math]\displaystyle{ \sigma_\text{atom} }[/math] of the Gaussian functions used for broadening the atomic distributions of the angular descriptor [math]\displaystyle{ \rho^{(3)}_i(r) }[/math] within the machine learning force field method (see this section).
The unit of ML_SION2 is [math]\displaystyle{ \AA }[/math]. Background:{| style="border: 0px solid #3E70EA; padding: 5px; background: #BBCCF5"
| Tip: Our test calculations indicate that a ratio ML_SION2 / ML_SION1 = 1.5 results in an optimal training performance. Furthermore, a value of 0.5 was found to be a good default value for ML_SION2. Both findings together result in the default value for ML_SION1. |}
Related Tags and Sections
ML_LMLFF, ML_SION1, ML_RCUT1, ML_RCUT2, ML_MRB1, ML_MRB2