# Tests of Artificial Neural Network-Based Diabatization Approaches on Simple 1D Models

## TL;DR

This paper tests and improves a machine learning method for chemical simulations using simple models.

## Contribution

The study introduces improvements to a neural network-based diabatization method through activation functions and regularization.

## Key findings

- Nonlinear activation functions in the output layer improved performance.
- Regularization in the loss function enhanced method accuracy.
- Cheap training set extensions significantly improved results.

## Abstract

Recently, a novel diabatization scheme has been proposed
[

ShuY.,
;
TruhlarD. G.,

J. Chem.
Theory Comput.
2020, 16, 6456–6464]32886513
10.1021/acs.jctc.0c00623 using artificial
neural networks. Most importantly, the method almost exclusively requires
the knowledge of adiabatic energies, which are routinely obtained
from ab initio calculations. However, many questions related to the
favorable performance of the method remain unanswered. In the present
paper, some of these questions are considered for selected one-dimensional
models with one configurational variable. In particular, various activation
functions are tested, including nonlinear ones in the output layer,
the effect of the regularization term in the loss function is analyzed,
and computationally cheap extensions of training sets are proposed.
Significant improvements of the performance of the original method
have been achieved.