Mimyria: Machine-Learned Vibrational Spectroscopy for Aqueous Systems Made Simple
- 28 April 2026
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (9) , 4626-4640
Abstract
Vibrational spectroscopy provides a powerful connection between molecular dynamics (MD) simulations and experiments, but its routine use in condensed-phase systems remains limited. We introduce mimyria, a modular and automated framework that orchestrates electronic-structure reference calculations, trains atom-resolved machine-learning response models, and generates IR and Raman spectra from MD trajectories within a unified workflow. We introduce the polarizability gradient tensor (PGT) as a novel atom-resolved machine-learning target property for Raman spectroscopy, complementing the established atomic polar tensor (APT) for IR spectroscopy. As a necessary prerequisite, we demonstrate how both PGTs and APTs can accurately be computed from electronic-structure theory, validate them across formally equivalent derivative formulations, and thereby benchmark their numerical consistency. We then employ machine learning as an efficient surrogate to represent the validated APT and PGT response functions on aqueous benchmark systems. We validate the trained models directly at the level of the vibrational spectrum against explicit ab initio reference calculations and find that IR and Raman spectra converge with surprisingly small training sets. Moreover, spectral agreement improves more rapidly than the root-mean-square error (RMSE), the conventional model error metric. While RMSE is straightforward to compute, statistically converged reference spectra are generally impractical to obtain, motivating the need to relate model-level errors to observable-level accuracy. By connecting these complementary error measures, we provide practical guidelines and early stopping criteria for achieving sufficient spectral fidelity. By integrating response-tensor learning, automated training, and spectral-domain validation into a unified workflow, mimyria enables data-efficient and quantitatively reliable vibrational spectroscopy.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (563085417)
- Deutsche Forschungsgemeinschaft (EXC 2033 390677874 RESOLV)
This publication has 71 references indexed in Scilit:
- Vibrational spectroscopy by means of first‐principles molecular dynamics simulationsWIREs Computational Molecular Science, 2022
- Supercritical Water is not Hydrogen BondedAngewandte Chemie International Edition, 2020
- Ion Hydration and Ion Pairing as Probed by THz SpectroscopyAngewandte Chemie International Edition, 2018
- Raman study of cation effect on sulfate vibration modes in solid state and in aqueous solutionsJournal of Raman Spectroscopy, 2013
- A beginner's guide to the modern theory of polarizationJournal of Solid State Chemistry, 2012
- Quickstep: Fast and accurate density functional calculations using a mixed Gaussian and plane waves approachComputer Physics Communications, 2005
- The Raman Effect2002
- The performance of the Becke—Lee—Yang—Parr (B—LYP) density functional theory with various basis setsChemical Physics Letters, 1992
- Statistical Physics II1991
- Correlation Functions for Molecular Motion1968