Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

The Journal of Physical Chemistry A

Research on Quantum Circuit Learning Models for Molecular Dynamics Simulation

Y. Nishida

Published Sep 26, 2025• 1 citation
Publisher

Abstract

In the past decade, many hybrid quantum-classical algorithms have been applied to various industrial fields, reflecting the growing interest in NISQ devices. For example, in the field of chemistry, many studies were conducted to calculate the energies of eigenstates with high precision. However, there is still little research on molecular dynamics using quantum computers, because traditional approaches based on variational quantum algorithms are not suitable for the long-time steps of molecular dynamics. In this study, we propose a quantum circuit learning model that estimates the eigenvalues of a given molecular Hamiltonian for an arbitrary molecular configuration. Our model must first be costly to train; however, once trained, the resulting trained model can eliminate procedures that required variational optimization each time the molecular coordinates are updated in the previous variational approach. By using the proposed model, we demonstrate that the proposed model can be used to perform simple molecular dynamics simulations, such as Langevin dynamics and NVE simulation. We also show several applications of our model inspired by classical machine learning.

DOI
10.1021/acs.jpca.5c03624

Related papers

Quantum-centric machine learning for molecular dynamics

Yanxian Tao, Lingyun Wan, Xiongzhi Zeng +4 more

Accurate and efficient prediction of electronic wavefunctions is central to ab initio molecular dynamics (AIMD) and electronic structure theory. However, conventional ab initio methods require self-consistent optimization of electronic states at every nuclear configuration, leading to prohibitive computational costs, especially for large or strongly correlated systems. Here, we introduce a quantum-centric machine learning (QCML) model-a hybrid quantum-classical framework that integrates parameterized quantum circuits (PQCs) with Transformer-based machine learning to directly predict molecular wavefunctions and quantum observables. By pretraining the Transformer on a diverse dataset of molecules and ansatz types and subsequently fine-tuning it for specific systems, QCML learns transferable mappings between molecular descriptors and PQC parameters, eliminating the need for iterative variational optimization. The pretrained model achieves chemical accuracy in potential energy surfaces, atomic forces, and dipole moments across multiple molecules and ansatzes, and enables efficient AIMD simulations with infrared spectra prediction. This work establishes a scalable and transferable quantum-centric machine learning paradigm, bridging variational quantum algorithms and modern deep learning for next-generation molecular simulation and quantum chemistry applications.

physics.chem-phCross-listedarXiv:2511.07771•Nov 12, 2025•1 citation

Quantum extreme learning of molecular potential energy surfaces and force fields

Gabriele Lo Monaco, Marco Bertini, Salvatore Lorenzo +1 more

Abstract Quantum machine learning algorithms are expected to play a pivotal role in quantum chemistry simulations in the immediate future. One such key application is the training of a quantum neural network to learn the potential energy surface and force field of molecular systems. We address this task by using the quantum extreme learning machine paradigm. This particular supervised learning routine allows for resource-efficient training, consisting of a simple linear regression performed on a classical computer. We have tested a setup that can be used to study molecules of any dimension and is optimized for immediate use on NISQ devices with a limited number of native gates. We have applied this setup to three case studies: lithium hydride, water, and formamide, carrying out both noiseless simulations and actual implementation on IBM quantum hardware. Compared to other supervised learning routines, the proposed setup requires minimal quantum resources, making it feasible for direct implementation on quantum platforms, while still achieving a high level of predictive accuracy compared to simulations. Our encouraging results pave the way towards the future application to more complex molecules, being the proposed setup scalable.

arXiv:2406.14607•Machine Learning Science and Technology•Jul 9, 2024•10 citations

Quantum Hardware-Enabled Molecular Dynamics via Transfer Learning

Abid Khan, Prateek Vaish, Yaoqi Pang +8 more

The ability to perform ab initio molecular dynamics simulations using potential energies calculated on quantum computers would allow virtually exact dynamics for chemical and biochemical systems, with substantial impacts on the fields of catalysis and biophysics. However, noisy hardware, the costs of computing gradients, and the number of qubits required to simulate large systems present major challenges to realizing the potential of dynamical simulations using quantum hardware. Here, we demonstrate that some of these issues can be mitigated by recent advances in machine learning. By combining transfer learning with techniques for building machine-learned potential energy surfaces, we propose a new path forward for molecular dynamics simulations on quantum hardware. We use transfer learning to reduce the number of energy evaluations that use quantum hardware by first training models on larger, less accurate classical datasets and then refining them on smaller, more accurate quantum datasets. We demonstrate this approach by training machine learning models to predict a molecule's potential energy using Behler-Parrinello neural networks. When successfully trained, the model enables energy gradient predictions necessary for dynamics simulations that cannot be readily obtained directly from quantum hardware. To reduce the quantum resources needed, the model is initially trained with data derived from low-cost techniques, such as Density Functional Theory, and subsequently refined with a smaller dataset obtained from the optimization of the Unitary Coupled Cluster ansatz. We show that this approach significantly reduces the size of the quantum training dataset while capturing the high accuracies needed for quantum chemistry simulations.

arXiv:2406.08554•Jun 12, 2024•0 citations

An Introduction to Variational Quantum Eigensolver Applied to Chemistry

Fonseca, Matheus da S., Caio Moraes Porto, Nicolás A. C. Carpio +4 more

Quantum mechanics has introduced a new theoretical framework for the study of molecules, enabling the prediction of properties and dynamics through the solution of the Schrödinger equation applied to these systems. However, solving this equation is computationally expensive, which has led to the development of various mathematical frameworks and computational methods designed to balance the available resources with the desired level of accuracy. In particular, quantum computers have emerged as a promising technology with the potential to address these problems more efficiently in the coming decades, whether through reductions in memory, time, and energy consumption, $\textit{i. e.}$, reductions in computational complexity or by enhancing precision. This research field is known as Quantum Simulation. Given the current technological limitations of quantum computers, Variational Quantum Algorithms (VQAs), especially the Variational Quantum Eigensolver (VQE), stand out as a feasible approach to demonstrating advantages over classical methods in the near term. This feasibility arises from their lower demand for quantum gates and the reduced depth of the circuits required for their implementation. In this work, we present the application of quantum mechanics to the study of molecules, provide an introduction to the fundamentals of quantum computing, and explore the integration of these fields by employing the VQE in molecular simulations. Finally, we discuss the spatial and temporal complexity associated with the algorithm, highlighting its implications and challenges.

arXiv:2505.04768•May 7, 2025•0 citations

Extending the reach of quantum computing for materials science with machine learning potentials

Julian Schuhmacher, Guglielmo Mazzola, Francesco Tacchino +4 more

Solving electronic structure problems represents a promising field of applications for quantum computers. Currently, much effort is spent in devising and optimizing quantum algorithms for near-term quantum processors, with the aim of outperforming classical counterparts on selected problem instances using limited quantum resources. These methods are still expected to feature a runtime preventing quantum simulations of large scale and bulk systems. In this work, we propose a strategy to extend the scope of quantum computational methods to large scale simulations using a machine learning potential trained on quantum simulation data. The challenge of applying machine learning potentials in today’s quantum setting arises from the several sources of noise affecting the quantum computations of electronic energies and forces. We investigate the trainability of a machine learning potential selecting various sources of noise: statistical, optimization, and hardware noise. Finally, we construct the first machine learning potential from data computed on actual IBM Quantum processors for a hydrogen molecule. This already would allow us to perform arbitrarily long and stable molecular dynamics simulations, outperforming all current quantum approaches to molecular dynamics and structure optimization.

arXiv:2203.07219•AIP Advances•Nov 1, 2022•17 citations

Applications of quantum circuit learning model using particle-number-conserving state on quantum chemical calculations

Y. Nishida, Fumihiko Aiga

Although the variational quantum eigensolver is a typical quantum algorithm utilized in near-term quantum devices, many measurements are required in an iterative closed feedback loop between the classical and quantum computers to obtain sufficient accuracy. In this study, we attempt to construct a quantum circuit learning model to infer potential energy surfaces and atomic forces without using the iterative loop to optimize parameters for every bond length. To realize a high, accurate inference performance, measurement is introduced in the middle of the circuit. When the proposed quantum circuit learning model is applied to the H2 molecule, the energies and atomic forces can be estimated with high accuracy in a single feed-forward calculation with varying bond lengths. A nonlinear relation between outcomes from data-encoding layer and inputs can also be used to eliminate the data-encoding layer, allowing for our quantum circuit model with lower learning costs by reducing the number of parameters to be optimized. Our model can be also extended to six-qubit systems, such as the H3 molecule, and to the water molecule with two internal degrees of freedom. Finally, we use the IBM Quantum backend to perform inference with a real quantum computer and show the effect of noise on the actual quantum device.

APL Quantum•Apr 10, 2024•1 citation
In the past decade, many hybrid quantum-classical algorithms have been applied to various industrial fields, reflecting the growing interest in NISQ devices. For example, in the field of chemistry, many studies were conducted to calculate the energies of eigenstates with high precision. However, there is still little research on molecular dynamics using quantum computers, because traditional approaches based on variational quantum algorithms are not suitable for the long-time steps of molecular dynamics. In this study, we propose a quantum circuit learning model that estimates the eigenvalues of a given molecular Hamiltonian for an arbitrary molecular configuration. Our model must first be costly to train; however, once trained, the resulting trained model can eliminate procedures that required variational optimization each time the molecular coordinates are updated in the previous variational approach. By using the proposed model, we demonstrate that the proposed model can be used to perform simple molecular dynamics simulations, such as Langevin dynamics and NVE simulation. We also show several applications of our model inspired by classical machine learning.
Accurate and efficient prediction of electronic wavefunctions is central to ab initio molecular dynamics (AIMD) and electronic structure theory. However, conventional ab initio methods require self-consistent optimization of electronic states at every nuclear configuration, leading to prohibitive computational costs, especially for large or strongly correlated systems. Here, we introduce a quantum-centric machine learning (QCML) model-a hybrid quantum-classical framework that integrates parameterized quantum circuits (PQCs) with Transformer-based machine learning to directly predict molecular wavefunctions and quantum observables. By pretraining the Transformer on a diverse dataset of molecules and ansatz types and subsequently fine-tuning it for specific systems, QCML learns transferable mappings between molecular descriptors and PQC parameters, eliminating the need for iterative variational optimization. The pretrained model achieves chemical accuracy in potential energy surfaces, atomic forces, and dipole moments across multiple molecules and ansatzes, and enables efficient AIMD simulations with infrared spectra prediction. This work establishes a scalable and transferable quantum-centric machine learning paradigm, bridging variational quantum algorithms and modern deep learning for next-generation molecular simulation and quantum chemistry applications.
Abstract Quantum machine learning algorithms are expected to play a pivotal role in quantum chemistry simulations in the immediate future. One such key application is the training of a quantum neural network to learn the potential energy surface and force field of molecular systems. We address this task by using the quantum extreme learning machine paradigm. This particular supervised learning routine allows for resource-efficient training, consisting of a simple linear regression performed on a classical computer. We have tested a setup that can be used to study molecules of any dimension and is optimized for immediate use on NISQ devices with a limited number of native gates. We have applied this setup to three case studies: lithium hydride, water, and formamide, carrying out both noiseless simulations and actual implementation on IBM quantum hardware. Compared to other supervised learning routines, the proposed setup requires minimal quantum resources, making it feasible for direct implementation on quantum platforms, while still achieving a high level of predictive accuracy compared to simulations. Our encouraging results pave the way towards the future application to more complex molecules, being the proposed setup scalable.
The ability to perform ab initio molecular dynamics simulations using potential energies calculated on quantum computers would allow virtually exact dynamics for chemical and biochemical systems, with substantial impacts on the fields of catalysis and biophysics. However, noisy hardware, the costs of computing gradients, and the number of qubits required to simulate large systems present major challenges to realizing the potential of dynamical simulations using quantum hardware. Here, we demonstrate that some of these issues can be mitigated by recent advances in machine learning. By combining transfer learning with techniques for building machine-learned potential energy surfaces, we propose a new path forward for molecular dynamics simulations on quantum hardware. We use transfer learning to reduce the number of energy evaluations that use quantum hardware by first training models on larger, less accurate classical datasets and then refining them on smaller, more accurate quantum datasets. We demonstrate this approach by training machine learning models to predict a molecule's potential energy using Behler-Parrinello neural networks. When successfully trained, the model enables energy gradient predictions necessary for dynamics simulations that cannot be readily obtained directly from quantum hardware. To reduce the quantum resources needed, the model is initially trained with data derived from low-cost techniques, such as Density Functional Theory, and subsequently refined with a smaller dataset obtained from the optimization of the Unitary Coupled Cluster ansatz. We show that this approach significantly reduces the size of the quantum training dataset while capturing the high accuracies needed for quantum chemistry simulations.
Quantum mechanics has introduced a new theoretical framework for the study of molecules, enabling the prediction of properties and dynamics through the solution of the Schrödinger equation applied to these systems. However, solving this equation is computationally expensive, which has led to the development of various mathematical frameworks and computational methods designed to balance the available resources with the desired level of accuracy. In particular, quantum computers have emerged as a promising technology with the potential to address these problems more efficiently in the coming decades, whether through reductions in memory, time, and energy consumption, i. e.\textit{i. e.}i. e., reductions in computational complexity or by enhancing precision. This research field is known as Quantum Simulation. Given the current technological limitations of quantum computers, Variational Quantum Algorithms (VQAs), especially the Variational Quantum Eigensolver (VQE), stand out as a feasible approach to demonstrating advantages over classical methods in the near term. This feasibility arises from their lower demand for quantum gates and the reduced depth of the circuits required for their implementation. In this work, we present the application of quantum mechanics to the study of molecules, provide an introduction to the fundamentals of quantum computing, and explore the integration of these fields by employing the VQE in molecular simulations. Finally, we discuss the spatial and temporal complexity associated with the algorithm, highlighting its implications and challenges.
Solving electronic structure problems represents a promising field of applications for quantum computers. Currently, much effort is spent in devising and optimizing quantum algorithms for near-term quantum processors, with the aim of outperforming classical counterparts on selected problem instances using limited quantum resources. These methods are still expected to feature a runtime preventing quantum simulations of large scale and bulk systems. In this work, we propose a strategy to extend the scope of quantum computational methods to large scale simulations using a machine learning potential trained on quantum simulation data. The challenge of applying machine learning potentials in today’s quantum setting arises from the several sources of noise affecting the quantum computations of electronic energies and forces. We investigate the trainability of a machine learning potential selecting various sources of noise: statistical, optimization, and hardware noise. Finally, we construct the first machine learning potential from data computed on actual IBM Quantum processors for a hydrogen molecule. This already would allow us to perform arbitrarily long and stable molecular dynamics simulations, outperforming all current quantum approaches to molecular dynamics and structure optimization.
Although the variational quantum eigensolver is a typical quantum algorithm utilized in near-term quantum devices, many measurements are required in an iterative closed feedback loop between the classical and quantum computers to obtain sufficient accuracy. In this study, we attempt to construct a quantum circuit learning model to infer potential energy surfaces and atomic forces without using the iterative loop to optimize parameters for every bond length. To realize a high, accurate inference performance, measurement is introduced in the middle of the circuit. When the proposed quantum circuit learning model is applied to the H2 molecule, the energies and atomic forces can be estimated with high accuracy in a single feed-forward calculation with varying bond lengths. A nonlinear relation between outcomes from data-encoding layer and inputs can also be used to eliminate the data-encoding layer, allowing for our quantum circuit model with lower learning costs by reducing the number of parameters to be optimized. Our model can be also extended to six-qubit systems, such as the H3 molecule, and to the water molecule with two internal degrees of freedom. Finally, we use the IBM Quantum backend to perform inference with a real quantum computer and show the effect of noise on the actual quantum device.