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

PRX Energy

Predicting Complex Materials Energetics with a Scalable Compact Nine-Qubit Quantum Machine-Learning Model

Hsu Kai-Cheng, Po-Yu Yang, Jyh-Pin Chou, Chun‐Wei Pao

Published Dec 22, 2025• 0 citations
Publisher

Abstract

Accurate machine-learning (ML) prediction of material energies typically relies on large models with thousands to hundreds of thousands of parameters and scales poorly with the system size. Here, we present a compact hybrid classical-quantum ML framework that predicts the energies of complex materials using fewer than ten qubits, regardless of system size. By compressing local atomic descriptors into a fixed-size feature spectrum, we enable amplitude encoding of chemically diverse systems into shallow quantum circuits. We implement quantum convolutional neural networks (QCNNs) and quantum deep neural networks (QDNNs) with fewer than 100 trainable parameters and achieve prediction errors below 0.05 eV/atom on chemically complex alloys ( Co 25 Ni 25 ( Hf Ti Zr ) 50 ) and lithium-intercalated metal-organic frameworks. Our results demonstrate the feasibility of scalable quantum assisted materials modeling and introduce a resource-efficient route toward quantum machine learning for atomistic simulations.

DOI
10.1103/j1lk-1cvs

Related papers

Adapting Quantum Machine Learning for Energy Dissociation of Bonds

Swathi Chandrasekhar, Shiva Raj Pokhrel, Navneet Singh

Accurate prediction of bond dissociation energies (BDEs) underpins mechanistic insight and the rational design of molecules and materials. We present a systematic, reproducible benchmark comparing quantum and classical machine learning models for BDE prediction using a chemically curated feature set encompassing atomic properties (atomic numbers, hybridization), bond characteristics (bond order, type), and local environmental descriptors. Our quantum framework, implemented in Qiskit Aer on six qubits, employs ZZFeatureMap encodings with variational ansätz (RealAmplitudes) across multiple architectures Variational Quantum Regressors (VQR), Quantum Support Vector Regressors (QSVR), Quantum Neural Networks (QNN), Quantum Convolutional Neural Networks (QCNN), and Quantum Random Forests (QRF). These are rigorously benchmarked against strong classical baselines, including Support Vector Regression (SVR), Random Forests (RF), and Multi-Layer Perceptrons (MLP). Comprehensive evaluation spanning absolute and relative error metrics, threshold accuracies, and error distributions shows that top-performing quantum models (QCNN, QRF) match the predictive accuracy and robustness of classical ensembles and deep networks, particularly within the chemically prevalent mid-range BDE regime. These findings establish a transparent baseline for quantum-enhanced molecular property prediction and outline a practical foundation for advancing quantum computational chemistry toward near-chemical accuracy.

arXiv:2510.06563•Sep 25, 2025•4 citations

Hybrid Quantum Graph Neural Network for Molecular Property Prediction

Michael Vitz, Hamed Mohammadbagherpoor, Samarth Sandeep +3 more

To accelerate the process of materials design, materials science has increasingly used data driven techniques to extract information from collected data. Specially, machine learning (ML) algorithms, which span the ML discipline, have demonstrated ability to predict various properties of materials with the level of accuracy similar to explicit calculation of quantum mechanical theories, but with significantly reduced run time and computational resources. Within ML, graph neural networks have emerged as an important algorithm within the field of machine learning, since they are capable of predicting accurately a wide range of important physical, chemical and electronic properties due to their higher learning ability based on the graph representation of material and molecular descriptors through the aggregation of information embedded within the graph. In parallel with the development of state of the art classical machine learning applications, the fusion of quantum computing and machine learning have created a new paradigm where classical machine learning model can be augmented with quantum layers which are able to encode high dimensional data more efficiently. Leveraging the structure of existing algorithms, we developed a unique and novel gradient free hybrid quantum classical convoluted graph neural network (HyQCGNN) to predict formation energies of perovskite materials. The performance of our hybrid statistical model is competitive with the results obtained purely from a classical convoluted graph neural network, and other classical machine learning algorithms, such as XGBoost. Consequently, our study suggests a new pathway to explore how quantum feature encoding and parametric quantum circuits can yield drastic improvements of complex ML algorithm like graph neural network.

arXiv:2405.05205•May 8, 2024•10 citations

Leveraging Machine Learning to Overcome Limitations in Quantum Algorithms

Sala, Laia Coronas, Parfait Atchade-Adelomou

Quantum Computing (QC) offers outstanding potential for molecular characterization and drug discovery, particularly in solving complex properties like the Ground State Energy (GSE) of biomolecules. However, QC faces challenges due to computational noise, scalability, and system complexity. This work presents a hybrid framework combining Machine Learning (ML) techniques with quantum algorithms$-$Variational Quantum Eigensolver (VQE), Hartree-Fock (HF), and Quantum Phase Estimation (QPE)$-$to improve GSE predictions for large molecules. Three datasets (chemical descriptors, Coulomb matrices, and a hybrid combination) were prepared using molecular features from PubChem. These datasets trained XGBoost (XGB), Random Forest (RF), and LightGBM (LGBM) models. XGB achieved the lowest Relative Error (RE) of $4.41 \pm 11.18\%$ on chemical descriptors, outperforming RF ($5.56 \pm 11.66\%$) and LGBM ($5.32 \pm 12.87\%$). HF delivered exceptional precision for small molecules ($0.44 \pm 0.66\% RE$), while a near-linear correlation between GSE and molecular electron count provided predictive shortcuts. This study demonstrates that integrating QC and ML enhances scalability for molecular energy predictions and lays the foundation for scaling QC molecular simulations to larger systems.

arXiv:2412.11405•Dec 16, 2024•3 citations

DeepQMLP: A Scalable Quantum-Classical Hybrid Deep Neural Network Architecture for Classification

Mahabubul Alam, Swaroop Ghosh

Quantum machine learning (QML) is promising for potential speedups and improvements in conventional machine learning (ML) tasks (e.g., classification/regression). The search for ideal QML models is an active research field. This includes identification of efficient classical-to-quantum data encoding scheme, construction of parametric quantum circuits (PQC) with optimal expressivity and entanglement capability, and efficient output decoding scheme to minimize the required number of measurements, to name a few. However, most of the empirical/numerical studies lack a clear path towards scalability. Any potential benefit observed in a simulated environment may diminish in practical applications due to the limitations of noisy quantum hardware (e.g., under decoherence, gate-errors, and crosstalk). We present a scalable quantum-classical hybrid deep neural network (DeepQMLP) architecture inspired by classical deep neural network architectures. In DeepQMLP, stacked shallow Quantum Neural Network (QNN) models mimic the hidden layers of a classical feed-forward multi-layer perceptron network. Each QNN layer produces a new and potentially rich representation of the input data for the next layer. This new representation can be tuned by the parameters of the circuit. Shallow QNN models experience less decoherence, gate errors, etc. which make them (and the network) more resilient to quantum noise. We present numerical studies on a variety of classification problems to show the trainability of DeepQMLP. We also show that DeepQMLP performs reasonably well on unseen data and exhibits greater resilience to noise over QNN models that use a deep quantum circuit. DeepQMLP provided up to 25.3% lower loss and 7.92% higher accuracy during inference under noise than QMLP.

arXiv:2202.01899•International Conference on VLSI Design•Feb 1, 2022•9 citations

A hybrid quantum regression model for the prediction of molecular atomization energies

Pranath Reddy, Aranya B. Bhattacherjee

Abstract Quantum machine learning is a relatively new research field that aims to combine the dramatic performance advantage offered by quantum computing and the ability of machine learning algorithms to learn complex distributions of high-dimensional data. The primary focus of this domain is the implementation of classical machine learning algorithms in the quantum mechanical domain and study of the speedup due to quantum parallelism, which could enable the development of novel techniques for solving problems such as quantum phase recognition and quantum error correction optimization. In this paper, we propose a hybrid quantum machine learning pipeline for predicting the atomization energies of various molecules using the nuclear charges and atomic positions of the constituent atoms. Firstly, we will be using a deep convolutional auto-encoder model for the feature extraction of data constructed from the eigenvalues and eigenvector centralities of the pairwise distance matrix calculated from atomic positions and the unrolled upper triangle of each Coulomb matrix calculated from nuclear charges, and we will then be using a quantum regression algorithm such as quantum linear regression, quantum radial basis function neural network and, a quantum neural network for estimating the atomization energy. The hybrid quantum neural network models do not seem to provide any speedup over their classical counterparts. Before implementing a quantum algorithm, we will also be using state-of-the-art classical machine learning and deep learning models such as XGBoost, multilayer perceptron, deep convolutional neural network, and a long short-term memory network to study the correlation between the extracted features and corresponding atomization energies of molecules.

Machine Learning Science and Technology•Dec 17, 2020•21 citations

A Novel Quantum Convolution Neural Network for Image Classification Applications

Venkatachalapathy Madhavanna Venkatappa, Venkateshappa

Image classification plays a vital role in large-scale data analysis, especially in object recognition tasks using advanced Deep Learning (DL) frameworks. However, the growing complexity and computational demands of modern DL models have introduced challenges related to scalability and efficiency. Quantum Computing (QC) has emerged as a promising alternative, capable of addressing these limitations by leveraging the principles of Quantum Machine Learning (QML). However, many existing QML models require a large number of qubits, which poses limitations within the current Noisy Intermediate-Scale Quantum (NISQ) era. This work introduces a novel Adaptive Quantum Convolutional Neural Network (AQCNN) designed for efficient and scalable image classification within the constraints of NISQ devices. Addressing the limitations of existing QML approaches, particularly the high qubit requirements, AQCNN incorporates a resource-efficient quantum convolutional layer that performs localized quantum filtering using parameterized quantum circuits. A classical preprocessing layer encodes input features to reduce qubit load, followed by quantum embedding and hybrid quantum-classical layers that optimize feature extraction and classification performance. The model leverages an adaptive quantum convolution strategy, minimizing quantum gate depth and circuit complexity while preserving critical spatial hierarchies in image data. Evaluated on benchmark datasets, AQCNN achieved 95.88% accuracy on MNIST and 95.68% on FMNIST, outperforming comparable QML architectures. Additionally, the model supports scalable execution through parallel quantum circuit arrays, enabling practical deployment on current quantum hardware. This architecture demonstrates a significant advance in quantum-assisted image classification, balancing performance with qubit and gate efficiency. The integration of adaptive quantum convolution and hybrid processing not only enhances classification accuracy but also provides a viable path forward for deploying QML solutions under realistic hardware constraints.

Engineering Technology & Applied Science Research•Oct 6, 2025•2 citations
Accurate machine-learning (ML) prediction of material energies typically relies on large models with thousands to hundreds of thousands of parameters and scales poorly with the system size. Here, we present a compact hybrid classical-quantum ML framework that predicts the energies of complex materials using fewer than ten qubits, regardless of system size. By compressing local atomic descriptors into a fixed-size feature spectrum, we enable amplitude encoding of chemically diverse systems into shallow quantum circuits. We implement quantum convolutional neural networks (QCNNs) and quantum deep neural networks (QDNNs) with fewer than 100 trainable parameters and achieve prediction errors below 0.05 eV/atom on chemically complex alloys ( Co 25 Ni 25 ( Hf Ti Zr ) 50 ) and lithium-intercalated metal-organic frameworks. Our results demonstrate the feasibility of scalable quantum assisted materials modeling and introduce a resource-efficient route toward quantum machine learning for atomistic simulations.
Accurate prediction of bond dissociation energies (BDEs) underpins mechanistic insight and the rational design of molecules and materials. We present a systematic, reproducible benchmark comparing quantum and classical machine learning models for BDE prediction using a chemically curated feature set encompassing atomic properties (atomic numbers, hybridization), bond characteristics (bond order, type), and local environmental descriptors. Our quantum framework, implemented in Qiskit Aer on six qubits, employs ZZFeatureMap encodings with variational ansätz (RealAmplitudes) across multiple architectures Variational Quantum Regressors (VQR), Quantum Support Vector Regressors (QSVR), Quantum Neural Networks (QNN), Quantum Convolutional Neural Networks (QCNN), and Quantum Random Forests (QRF). These are rigorously benchmarked against strong classical baselines, including Support Vector Regression (SVR), Random Forests (RF), and Multi-Layer Perceptrons (MLP). Comprehensive evaluation spanning absolute and relative error metrics, threshold accuracies, and error distributions shows that top-performing quantum models (QCNN, QRF) match the predictive accuracy and robustness of classical ensembles and deep networks, particularly within the chemically prevalent mid-range BDE regime. These findings establish a transparent baseline for quantum-enhanced molecular property prediction and outline a practical foundation for advancing quantum computational chemistry toward near-chemical accuracy.
To accelerate the process of materials design, materials science has increasingly used data driven techniques to extract information from collected data. Specially, machine learning (ML) algorithms, which span the ML discipline, have demonstrated ability to predict various properties of materials with the level of accuracy similar to explicit calculation of quantum mechanical theories, but with significantly reduced run time and computational resources. Within ML, graph neural networks have emerged as an important algorithm within the field of machine learning, since they are capable of predicting accurately a wide range of important physical, chemical and electronic properties due to their higher learning ability based on the graph representation of material and molecular descriptors through the aggregation of information embedded within the graph. In parallel with the development of state of the art classical machine learning applications, the fusion of quantum computing and machine learning have created a new paradigm where classical machine learning model can be augmented with quantum layers which are able to encode high dimensional data more efficiently. Leveraging the structure of existing algorithms, we developed a unique and novel gradient free hybrid quantum classical convoluted graph neural network (HyQCGNN) to predict formation energies of perovskite materials. The performance of our hybrid statistical model is competitive with the results obtained purely from a classical convoluted graph neural network, and other classical machine learning algorithms, such as XGBoost. Consequently, our study suggests a new pathway to explore how quantum feature encoding and parametric quantum circuits can yield drastic improvements of complex ML algorithm like graph neural network.
Quantum Computing (QC) offers outstanding potential for molecular characterization and drug discovery, particularly in solving complex properties like the Ground State Energy (GSE) of biomolecules. However, QC faces challenges due to computational noise, scalability, and system complexity. This work presents a hybrid framework combining Machine Learning (ML) techniques with quantum algorithms−-−Variational Quantum Eigensolver (VQE), Hartree-Fock (HF), and Quantum Phase Estimation (QPE)−-−to improve GSE predictions for large molecules. Three datasets (chemical descriptors, Coulomb matrices, and a hybrid combination) were prepared using molecular features from PubChem. These datasets trained XGBoost (XGB), Random Forest (RF), and LightGBM (LGBM) models. XGB achieved the lowest Relative Error (RE) of 4.41±11.18%4.41 \pm 11.18\%4.41±11.18% on chemical descriptors, outperforming RF (5.56±11.66%5.56 \pm 11.66\%5.56±11.66%) and LGBM (5.32±12.87%5.32 \pm 12.87\%5.32±12.87%). HF delivered exceptional precision for small molecules (0.44±0.66%RE0.44 \pm 0.66\% RE0.44±0.66%RE), while a near-linear correlation between GSE and molecular electron count provided predictive shortcuts. This study demonstrates that integrating QC and ML enhances scalability for molecular energy predictions and lays the foundation for scaling QC molecular simulations to larger systems.
Quantum machine learning (QML) is promising for potential speedups and improvements in conventional machine learning (ML) tasks (e.g., classification/regression). The search for ideal QML models is an active research field. This includes identification of efficient classical-to-quantum data encoding scheme, construction of parametric quantum circuits (PQC) with optimal expressivity and entanglement capability, and efficient output decoding scheme to minimize the required number of measurements, to name a few. However, most of the empirical/numerical studies lack a clear path towards scalability. Any potential benefit observed in a simulated environment may diminish in practical applications due to the limitations of noisy quantum hardware (e.g., under decoherence, gate-errors, and crosstalk). We present a scalable quantum-classical hybrid deep neural network (DeepQMLP) architecture inspired by classical deep neural network architectures. In DeepQMLP, stacked shallow Quantum Neural Network (QNN) models mimic the hidden layers of a classical feed-forward multi-layer perceptron network. Each QNN layer produces a new and potentially rich representation of the input data for the next layer. This new representation can be tuned by the parameters of the circuit. Shallow QNN models experience less decoherence, gate errors, etc. which make them (and the network) more resilient to quantum noise. We present numerical studies on a variety of classification problems to show the trainability of DeepQMLP. We also show that DeepQMLP performs reasonably well on unseen data and exhibits greater resilience to noise over QNN models that use a deep quantum circuit. DeepQMLP provided up to 25.3% lower loss and 7.92% higher accuracy during inference under noise than QMLP.
Abstract Quantum machine learning is a relatively new research field that aims to combine the dramatic performance advantage offered by quantum computing and the ability of machine learning algorithms to learn complex distributions of high-dimensional data. The primary focus of this domain is the implementation of classical machine learning algorithms in the quantum mechanical domain and study of the speedup due to quantum parallelism, which could enable the development of novel techniques for solving problems such as quantum phase recognition and quantum error correction optimization. In this paper, we propose a hybrid quantum machine learning pipeline for predicting the atomization energies of various molecules using the nuclear charges and atomic positions of the constituent atoms. Firstly, we will be using a deep convolutional auto-encoder model for the feature extraction of data constructed from the eigenvalues and eigenvector centralities of the pairwise distance matrix calculated from atomic positions and the unrolled upper triangle of each Coulomb matrix calculated from nuclear charges, and we will then be using a quantum regression algorithm such as quantum linear regression, quantum radial basis function neural network and, a quantum neural network for estimating the atomization energy. The hybrid quantum neural network models do not seem to provide any speedup over their classical counterparts. Before implementing a quantum algorithm, we will also be using state-of-the-art classical machine learning and deep learning models such as XGBoost, multilayer perceptron, deep convolutional neural network, and a long short-term memory network to study the correlation between the extracted features and corresponding atomization energies of molecules.
Image classification plays a vital role in large-scale data analysis, especially in object recognition tasks using advanced Deep Learning (DL) frameworks. However, the growing complexity and computational demands of modern DL models have introduced challenges related to scalability and efficiency. Quantum Computing (QC) has emerged as a promising alternative, capable of addressing these limitations by leveraging the principles of Quantum Machine Learning (QML). However, many existing QML models require a large number of qubits, which poses limitations within the current Noisy Intermediate-Scale Quantum (NISQ) era. This work introduces a novel Adaptive Quantum Convolutional Neural Network (AQCNN) designed for efficient and scalable image classification within the constraints of NISQ devices. Addressing the limitations of existing QML approaches, particularly the high qubit requirements, AQCNN incorporates a resource-efficient quantum convolutional layer that performs localized quantum filtering using parameterized quantum circuits. A classical preprocessing layer encodes input features to reduce qubit load, followed by quantum embedding and hybrid quantum-classical layers that optimize feature extraction and classification performance. The model leverages an adaptive quantum convolution strategy, minimizing quantum gate depth and circuit complexity while preserving critical spatial hierarchies in image data. Evaluated on benchmark datasets, AQCNN achieved 95.88% accuracy on MNIST and 95.68% on FMNIST, outperforming comparable QML architectures. Additionally, the model supports scalable execution through parallel quantum circuit arrays, enabling practical deployment on current quantum hardware. This architecture demonstrates a significant advance in quantum-assisted image classification, balancing performance with qubit and gate efficiency. The integration of adaptive quantum convolution and hybrid processing not only enhances classification accuracy but also provides a viable path forward for deploying QML solutions under realistic hardware constraints.