Corrosion inhibition efficiency (IE%) prediction plays a central role in the computational discovery of high-performance organic inhibitors. Classical machine learning has shown promising results; however, its performance often deteriorates when learning non-linear interactions between quantum chemical descriptors. Meanwhile, quantum machine learning (QML) provides enhanced expressivity through quantum feature mapping but remains limited by NISQ-era hardware. In this study, we propose a Hybrid Quantum Neural Network (HQNN) integrating classical dense layers with variational quantum circuits (VQC) to predict the inhibition efficiency of organic corrosion inhibitors. Using a curated dataset of 660 molecules with DFT descriptors, the HQNN achieves an RMSE of 3.41 and R² of 0.958, outperforming classical regressors and pure VQC. The results demonstrate that hybrid quantum models offer a balanced trade-off between quantum advantage and practical feasibility in materials informatics.
Corrosion inhibition efficiency (IE%) prediction plays a central role in the computational discovery of high-performance organic inhibitors. Classical machine learning has shown promising results; however, its performance often deteriorates when learning non-linear interactions between quantum chemical descriptors. Meanwhile, quantum machine learning (QML) provides enhanced expressivity through quantum feature mapping but remains limited by NISQ-era hardware. In this study, we propose a Hybrid Quantum Neural Network (HQNN) integrating classical dense layers with variational quantum circuits (VQC) to predict the inhibition efficiency of organic corrosion inhibitors. Using a curated dataset of 660 molecules with DFT descriptors, the HQNN achieves an RMSE of 3.41 and R² of 0.958, outperforming classical regressors and pure VQC. The results demonstrate that hybrid quantum models offer a balanced trade-off between quantum advantage and practical feasibility in materials informatics.
Corrosion, caused by electrochemical reactions in corrosive environments, can degrade the quality and lifespan of materials, potentially leading to significant losses in various industrial sectors. One common strategy to reduce corrosion rates is by using corrosion inhibitors. A significant challenge in this field is the time-consuming and costly process of testing new corrosion inhibitors in the laboratory. Consequently, there is a need for more efficient and cost-effective methods to predict the effectiveness of potential corrosion inhibitors using machine learning techniques. This research addresses this problem by applying a quantum machine learning (QML) approach with quantum neural network (QNN) algorithms to evaluate the effectiveness of drug compounds as corrosion inhibitors. The study aims to optimize QNN models by investigating three different quantum circuit configurations to identify the most effective design. The results showed that Model-01, consisting of three layers, demonstrated the best performance with an MSE of 38.81, an RMSE of 6.23, and an MAE of 6.19, along with the shortest training time of 32 seconds, indicating an optimal balance between complexity and generalizability. Overall, this QML approach provides new insights into the predictive ability of QNN models in assessing the effectiveness of drug compounds as corrosion inhibitors, demonstrating the potential of quantum computing to enhance predictive accuracy and efficiency in investigating anti-corrosion materials
This study examines the potential of quantum machine learning (QML) to predict the corrosion inhibition capacity of expired pharmaceutical compounds. The investigation employs a QSPR model, using features generated from density functional theory (DFT) calculations as input. At the same time, corrosion inhibition efficiency (CIE) values obtained from experimental data serve as the target output. The VQC model demonstrates varied performance across evaluation metrics, especially with encoding and ansatz design. The model achieves fine scores in evaluation metrics, with root mean square error (RMSE) of 6.15, mean absolute error (MAE) of 5.63, and mean absolute deviation (MAD) of 5.50. The research underscores the significance of larger datasets for enhancing predictive accuracy and points to QML's potential in exploring anti-corrosion materials. Although there are some limitations, this study provides a foundational framework for using QML to predict anti-corrosive properties.
Protein-ligand binding affinity is critical in drug discovery, but experimentally determining it is time-consuming and expensive. Artificial intelligence (AI) has been used to predict binding affinity, significantly accelerating this process. However, the high-performance requirements and vast datasets involved in affinity prediction demand increasingly large AI models, requiring substantial computational resources and training time. Quantum machine learning has emerged as a promising solution to these challenges. In particular, hybrid quantum-classical models can reduce the number of parameters while maintaining or improving performance compared to classical counterparts. Despite these advantages, challenges persist: why hybrid quantum models achieve these benefits, whether quantum neural networks (QNNs) can replace classical neural networks, and whether such models are feasible on noisy intermediate-scale quantum (NISQ) devices. This study addresses these challenges by proposing a hybrid quantum neural network (HQNN) that empirically demonstrates the capability to approximate non-linear functions in the latent feature space derived from classical embedding. The primary goal of this study is to achieve a parameter-efficient model in binding affinity prediction while ensuring feasibility on NISQ devices. Numerical results indicate that HQNN achieves comparable or superior performance and parameter efficiency compared to classical neural networks, underscoring its potential as a viable replacement. This study highlights the potential of hybrid QML in computational drug discovery, offering insights into its applicability and advantages in addressing the computational challenges of protein-ligand binding affinity prediction.
Accurate amine property prediction is essential for optimizing CO2 capture efficiency in post-combustion processes. Quantum machine learning (QML) can enhance predictive modeling by leveraging superposition, entanglement, and interference to capture complex correlations. In this study, we developed hybrid quantum neural networks (HQNN) to improve quantitative structure-property relationship (QSPR) modeling for CO2-capturing amines. By integrating variational quantum regressors with classical multi-layer perceptrons and graph neural networks, quantum-enhanced performance was explored in physicochemical property prediction under noiseless conditions and robustness was evaluated against quantum hardware noise using IBM quantum systems. Our results showed that HQNNs improve predictive accuracy for key solvent properties, including basicity, viscosity, boiling point, melting point, and vapor pressure. The fine-tuned and frozen pre-trained HQNN models with 9 qubits consistently achieved the highest rankings, highlighting the benefits of integrating quantum layers with pre-trained classical models. Furthermore, simulations under hardware noise confirmed the robustness of HQNNs, maintaining predictive performance. Overall, these findings emphasize the potential of hybrid quantum-classical architectures in molecular modeling. As quantum hardware and QML algorithms continue to advance, practical quantum benefits in QSPR modeling and materials discovery are expected to become increasingly attainable, driven by improvements in quantum circuit design, noise mitigation, and scalable architectures.
Hybrid Quantum Neural Networks (HQNNs), under the umbrella of Quantum Machine Learning (QML), have garnered significant attention due to their potential to enhance computational performance by integrating quantum layers within traditional neural network (NN) architectures. Despite numerous state-of-the-art applications, a fundamental question remains: Does the inclusion of quantum layers offer any computational advantage over purely classical models? If yes/no, how and why? In this paper, we analyze how classical and hybrid models adapt their architectural complexity in response to increasing problem complexity. To this end, we select a multiclass classification problem and perform comprehensive benchmarking of classical models for increasing problem complexity, identifying those that optimize both accuracy and computational efficiency to establish a robust baseline for comparison. These baseline models are then systematically compared with HQNNs by evaluating the rate of increase in floating-point operations (FLOPs) and number of parameters, providing insights into how architectural complexity scales with problem complexity in both classical and hybrid networks. We utilize classical machines to simulate the quantum layers in HQNNs, a common practice in Noisy Intermediate-Scale Quantum (NISQ) era. Our analysis reveals that, as problem complexity increases, the architectural complexity of HQNNs, and consequently their FLOPs consumption, despite the simulation overhead associated with quantum layer’s simulation on classical hardware, scales more efficiently (53.1% increase in FLOPs from 10 features (low problem complexity) to 110 features (high problem complexity)), compared to classical networks (88.1%). Moreover, as the problem complexity increases, classical networks consistently exhibit a need for a larger number of parameters to accommodate the increasing problem complexity. Additionally, the rate of increase in number of parameters is also slower in HQNNs (81.4%) than classical NNs (88.5%). These findings suggest that HQNNs provide a more scalable and resource-efficient solution, positioning them as a promising alternative for tackling complex computational problems.
This study explores the development and evaluation of a Variational Quantum Algorithm (VQA) for predicting a drug as a corrosion inhibitor, highlighting its advantages over traditional regression models. The VQA leverages quantum-enhanced feature mapping and optimization techniques to capture complex, non-linear relationships within the data. Comparative analysis with AutoRegressive with exogenous inputs (ARX) and Gradient Boosting (GB) models demonstrate the superior performance of VQA across key metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Deviation (MAD). The VQA achieved the lowest RMSE (4.40), MAE (3.33), and MAD (3.17) values, indicating enhanced predictive accuracy and stability. These results underscore the potential of quantum machine learning techniques in advancing predictive modeling capabilities, offering significant improvements in accuracy and consistency over classical methods. The findings suggest that VQA is a promising approach for applications requiring high precision and reliability, paving the way for broader adoption of quantum-enhanced models in material science and beyond.