Coherent Floquet quantum reservoirs for molecular property prediction
Abstract
Quantum reservoir computing (QRC) uses quantum dynamics to represent input histories for prediction through a trained classical readout. Discrete time crystals (DTCs) exhibit robust subharmonic responses under periodic driving, and previous work has used their dynamics to construct DTC-QRC. Here we construct a DTC-based reservoir architecture to predict molecular properties from structural and dynamical observations. Coherent Floquet evolution processes local molecular graph events and surface-hopping frames, while controlled reset regulates the contribution of earlier inputs. Measurements at the end of each input sequence yield a feature vector of fixed dimension. Trained classical decoders use this vector for inhibitor-activity and blood--brain-barrier permeability classification and electronic-gap forecasting, while the reservoir parameters remain fixed during training. With matched input lengths and output widths, DTC-QRC outperforms echo-state networks on long-prefix graph classification and the studied ethene gap forecasting tasks. Dephasing lowers performance in both applications, consistent with a role for coherent propagation. Experiments on the Quafu superconducting quantum cloud platform show that pair observables retain task information under device noise. The architecture provides a common framework for molecular screening and time-resolved property prediction using quantum reservoir computing.
Related
- Towards Multiscale Molecular Representation Learning through Geometry-Based Fragmentation for Polymer Property Prediction
- From Approximate Floquet Engineering to Full Floquet Theory: Coherent Control of Chiral Spin Systems in Spintronics
- Shaping of the finite-size chaos crossover in Floquet circuits by coherent-mismatch architecture
- Polariton-polariton coherent coupling in a molecular spin-superconductor chip
- An open benchmark for machine learning-based polymer property prediction
BibTeX
@misc{wang2026coherent,
title = {{Coherent Floquet quantum reservoirs for molecular property prediction}},
author = {Luofei Wang and Da Zhang and Congren Wang and Yiming Li and Yuxiao Yang and Xuan Zhang and Xuefeng Cui and Zhang-Qi Yin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.11071},
eprint = {2609.11071},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.11071},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Coherent Floquet quantum reservoirs for molecular property prediction
AU - Luofei Wang
AU - Da Zhang
AU - Congren Wang
AU - Yiming Li
AU - Yuxiao Yang
AU - Xuan Zhang
AU - Xuefeng Cui
AU - Zhang-Qi Yin
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2609.11071
UR - https://arxiv.org/abs/2609.11071
AB - Quantum reservoir computing (QRC) uses quantum dynamics to represent input histories for prediction through a trained classical readout. Discrete time crystals (DTCs) exhibit robust subharmonic responses under periodic driving, and previous work has used their dynamics to construct DTC-QRC. Here we construct a DTC-based reservoir architecture to predict molecular properties from structural and dynamical observations. Coherent Floquet evolution processes local molecular graph events and surface-hopping frames, while controlled reset regulates the contribution of earlier inputs. Measurements at the end of each input sequence yield a feature vector of fixed dimension. Trained classical decoders use this vector for inhibitor-activity and blood--brain-barrier permeability classification and electronic-gap forecasting, while the reservoir parameters remain fixed during training. With matched input lengths and output widths, DTC-QRC outperforms echo-state networks on long-prefix graph classification and the studied ethene gap forecasting tasks. Dephasing lowers performance in both applications, consistent with a role for coherent propagation. Experiments on the Quafu superconducting quantum cloud platform show that pair observables retain task information under device noise. The architecture provides a common framework for molecular screening and time-resolved property prediction using quantum reservoir computing.
ER -