Neural network potentials facilitating accurate complex scaling for molecular resonances: from a model to high dimensional realistic systems

Abstract

Here we propose a neural network based complex scaling (NN-CS) method for computing the complex eigenvalues (E_r–iΓ/2) of molecular resonances, in which the CS of the potential part in the non-Hermitian Hamiltonian is effectively achieved by NNs. Taking a two-dimensional (2D) diabatic model including two states coupled by the conical intersection for example, the NN-CS method is shown to reproduce the eigenvalues of the resonance states quite well. Subsequently, this NN-CS method with a 2D Hamiltonian model is utilized to compute the vibronic resonances in the ¹nσ*-mediated photodissociation of thioanisole based on a new NN diabatic potential energy matrix. The calculated lifetimes of the vibronic resonances are found to be in good agreement with other theoretical results and available experimental data. Finally, the NN-CS method is applied to treat a much more challenging system, namely, the resonances in the six-dimensional (6D) photodissociation continuum of NH₃, due to its high dimensionalities and all three dissociative coordinates needing to be scaled in the complex scaling of the potential part. Again, the calculated energy positions and widths of the 6D resonances by the NN-CS method agree well with other theoretical results. Our calculations show that the NN-CS method is able to accurately treat the vibronic resonances involving multiple coupled electronic states and resonances in high dimensional realistic systems.