Machine learning the non-radiative decay modes in photochemical processes

TL;DR

This paper introduces an unsupervised information-theoretic framework using Differentiable Information Imbalance to identify nuclear coordinates responsible for non-radiative decay in photoexcited molecules from molecular dynamics simulations.

Contribution

The authors develop a scalable, interpretable method that ranks nuclear degrees of freedom by relevance, revealing mechanistic coordinates and their importance across various molecular systems.

Findings

The method recovers known decay coordinates in tested systems.

It distinguishes between localized and collective structural changes affecting observables.

The framework provides mechanistic insights and reduces high-dimensional data to interpretable modes.

Abstract

Non-radiative decay in photoexcited molecular systems is driven by nuclear motion toward conical intersections (CIs), where electronic states become degenerate and nonadiabatic transitions occur. Identifying the nuclear degrees of freedom responsible for CI access from nonadiabatic molecular dynamics (NAD) simulations remains challenging because the underlying motions are high-dimensional and collective. Here, we introduce an unsupervised, information-theoretic framework based on Differentiable Information Imbalance (DII) to identify the nuclear coordinates governing CI access directly from trajectory surface hopping (TSH) simulations. By quantifying correlations between structural descriptors and electronic observables, including energy gaps and oscillator strengths, the method ranks nuclear degrees of freedom by predictive relevance. A multi-step protocol then extracts low-dimensional, physically interpretable modes associated with non-radiative decay. We apply the framework to the methaniminium cation, furan, L-glutamine, L-pyroglutamine-ammonium, and a photoactive molecular motor. Across all systems, the method recovers known mechanistic coordinates while revealing the relative importance of competing modes when multiple structural distortions contribute to CI access. The analysis also reveals a systematic distinction between observables: energy gaps are typically governed by a small number of localized coordinates, whereas oscillator strengths depend on more collective and distributed structural rearrangements. Overall, the DII-based framework combines predictive power with direct interpretability, providing a general and scalable route for extracting mechanistic insight from high-dimensional NAD data and constructing reduced-dimensional models of excited-state dynamics.