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

IEEE International Conference on Quantum Computing and Engineering (QCE)

Advantages of Quantum Circuit Learning for the Development of High Entropy Materials

Sota Osaki, Kazuki Hoshitani, Makoto M. Nakamura, Kôichi Kimura, Tomoyuki Yamamoto

Published Aug 30, 2025• 0 citations
Publisher

Abstract

In this study, we have explored the validity of the quantum circuit learning method by comparing the prediction results of Vickers hardness of the high entropy alloys with those predicted by the conventional linear and nonlinear types of machine learning methods.
DOI
10.1109/qce65121.2025.10375

Related papers

Quantum machine-learning phase prediction of high-entropy alloys

Payden Brown, Houlong L. Zhuang

Materials Today•Mar 1, 2023•44 citations

Efficient quantum algorithm for the design of complex materials: quantum circuit learning

Sota Osaki, Kazuki Hoshitani, Makoto Nakamura +2 more

Validity of the quantum circuit learning (QCL) method for the prediction of physical properties of complex materials has been explored by comparing the prediction results of Vickers hardness of the high entropy alloys with those predicted by the conventional linear and nonlinear types of machine learning methods. The linear models include linear regression (LR), ridge regression (Ridge), Bayesian ridge regression (BR), and linear support vector regression (linear_SVR) for linear models, and the nonlinear models include Gaussian process regression (GBR), support vector regression with an radial basis function kernel (rbf_SVR), random forest (RF), gradient boosting decision trees (GBDT), and multilayer perceptron neural networks (MLP). Our current examinations revealed that the QCL can efficiently predict Vickers hardness of the high entropy alloys for outside applicability domains and extrapolations even with a small number of datasets, which implies that the QCL can be used for the design of new complex materials from an early stage of development with a small dataset.

Scientific Reports•Apr 20, 2026•0 citations

Quantum circuit learning as a potential algorithm to predict experimental chemical properties

Kan Hatakeyama‐Sato, Yasuhiko Igarashi, Takahiro Kashikawa +2 more

Quantum circuit learning is examined to predict standard functions and molecular properties. The algorithm may be used for extrapolating predictions.

Digital Discovery•Dec 2, 2022•8 citations

Quantum Computing for Nanomaterials: Accelerating Material Discovery

Chandra Mouli Penugonda, Vinod Kumar Devalla, Ch. Rami Reddy +1 more

With the increasing demand for high-performance materials in energy, healthcare, and electronics, the discovery of novel nanomaterials has become a critical area of research. Traditional methods for predicting material properties, such as Density Functional Theory (DFT) and classical machine learning (ML), often struggle with scalability and computational efficiency when dealing with complex, high-dimensional quantum systems. This study explores the potential of Quantum Machine Learning (QML) as a transformative tool for accelerating nanomaterial property prediction. By leveraging quantum computing frameworks like IBM Qi skit and PennyLane, quantum algorithms such as Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) were applied to a real-world dataset containing 486 nanomaterial entries. Comparative analysis using performance metrics like MAE, RMSE, and R2 demonstrated that quantum models outperformed classical ones in both accuracy and adaptability to data complexity. Power BI was used for advanced visualization to interpret feature relationships, entropy levels, and prediction patterns across models. Key findings suggest that QML provides a promising alternative to conventional methods by offering faster, more accurate predictions, particularly for datasets with high entropy. While challenges remain—such as limited dataset scope and hardware access—this study lays the groundwork for broader adoption of QML in computational material science and calls for future research involving real quantum hardware and larger, more diverse datasets.

Frontiers in artificial intelligence and applications•Nov 10, 2025•1 citation

Circuit-centric quantum classifiers

Maria Schuld, Alex Bocharov, Krysta M. Svore +1 more

A machine learning design is developed to train a quantum circuit specialized in solving a classification problem. In addition to discussing the training method and effect of noise, it is shown that the circuits perform reasonably well on classical benchmarks.

arXiv:1804.00633•Physical Review A•Mar 6, 2020•1,273 citations

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

Hsu Kai-Cheng, Po-Yu Yang, Jyh-Pin Chou +1 more

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.

PRX Energy•Dec 22, 2025•0 citations
Validity of the quantum circuit learning (QCL) method for the prediction of physical properties of complex materials has been explored by comparing the prediction results of Vickers hardness of the high entropy alloys with those predicted by the conventional linear and nonlinear types of machine learning methods. The linear models include linear regression (LR), ridge regression (Ridge), Bayesian ridge regression (BR), and linear support vector regression (linear_SVR) for linear models, and the nonlinear models include Gaussian process regression (GBR), support vector regression with an radial basis function kernel (rbf_SVR), random forest (RF), gradient boosting decision trees (GBDT), and multilayer perceptron neural networks (MLP). Our current examinations revealed that the QCL can efficiently predict Vickers hardness of the high entropy alloys for outside applicability domains and extrapolations even with a small number of datasets, which implies that the QCL can be used for the design of new complex materials from an early stage of development with a small dataset.
With the increasing demand for high-performance materials in energy, healthcare, and electronics, the discovery of novel nanomaterials has become a critical area of research. Traditional methods for predicting material properties, such as Density Functional Theory (DFT) and classical machine learning (ML), often struggle with scalability and computational efficiency when dealing with complex, high-dimensional quantum systems. This study explores the potential of Quantum Machine Learning (QML) as a transformative tool for accelerating nanomaterial property prediction. By leveraging quantum computing frameworks like IBM Qi skit and PennyLane, quantum algorithms such as Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) were applied to a real-world dataset containing 486 nanomaterial entries. Comparative analysis using performance metrics like MAE, RMSE, and R2 demonstrated that quantum models outperformed classical ones in both accuracy and adaptability to data complexity. Power BI was used for advanced visualization to interpret feature relationships, entropy levels, and prediction patterns across models. Key findings suggest that QML provides a promising alternative to conventional methods by offering faster, more accurate predictions, particularly for datasets with high entropy. While challenges remain—such as limited dataset scope and hardware access—this study lays the groundwork for broader adoption of QML in computational material science and calls for future research involving real quantum hardware and larger, more diverse datasets.
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.