As global carbon emissions continue to rise, achieving carbon neutrality has become a primary objective worldwide. Predictive modeling for carbon emissions has emerged as a crucial strategy, with numerous methods developed to forecast and manage emissions effectively. Traditional models, which predominantly employ classical computing-based metaheuristic optimization techniques, often face limitations in reaching global optima, impacting prediction accuracy. This study introduces a hybrid quantum-classical approach to enhance prediction models, particularly through feature dimensionality reduction, which is essential for improving model performance. Quantum algorithms, especially quantum annealing (QA), have shown advantages in addressing complex optimization problems by utilizing principles such as superposition and tunneling, thus offering significant benefits over classical methods. The integration of QA with classical dimensionality reduction techniques, such as principal component analysis (PCA), represents a novel advancement in managing high-dimensional data within predictive models. By optimizing feature selection, our approach aims to increase both the accuracy and computational efficiency of carbon neutrality models. This paper proposes hybrid quantum-classical optimization opportunities that can serve as a foundation for future studies, ultimately leading to more robust and accurate predictive models.
As global carbon emissions continue to rise, achieving carbon neutrality has become a primary objective worldwide. Predictive modeling for carbon emissions has emerged as a crucial strategy, with numerous methods developed to forecast and manage emissions effectively. Traditional models, which predominantly employ classical computing-based metaheuristic optimization techniques, often face limitations in reaching global optima, impacting prediction accuracy. This study introduces a hybrid quantum-classical approach to enhance prediction models, particularly through feature dimensionality reduction, which is essential for improving model performance. Quantum algorithms, especially quantum annealing (QA), have shown advantages in addressing complex optimization problems by utilizing principles such as superposition and tunneling, thus offering significant benefits over classical methods. The integration of QA with classical dimensionality reduction techniques, such as principal component analysis (PCA), represents a novel advancement in managing high-dimensional data within predictive models. By optimizing feature selection, our approach aims to increase both the accuracy and computational efficiency of carbon neutrality models. This paper proposes hybrid quantum-classical optimization opportunities that can serve as a foundation for future studies, ultimately leading to more robust and accurate predictive models.
Accurate carbon-emissions prediction is critical for evidence-based climate policy, where even modest improvements can influence emission–reduction targets. However, high-dimensional datasets often exhibit noise, nonlinear dependencies, and multicollinearity that degrade model stability. We propose QMICO-PCA, a hybrid dimensionality-reduction method that integrates quantum annealing (QA)-based feature selection with principal component analysis (PCA). In the selection stage, mutual information (MI) and Pearson correlation (CO) are combined multiplicatively within a QUBO formulation to jointly reward nonlinear relevance and penalize linear redundancy, enabling balanced subset optimization. The selected features are then transformed via PCA to enhance generalization and mitigate overfitting. We evaluate QMICO-PCA against classical approaches (RFE, LASSO, ELN), with and without PCA, using three regression models on the Our World in Data carbon dataset (13,706 records; 79 features; 1970–2023). Experiments are conducted on heterogeneous QA-based solvers to assess optimization robustness. QMICO-PCA achieves the strongest overall performance (average RMSE = 1134.12, MAE = 237.54, R2 = 0.8020), corresponding to a 4-7% error reduction over classical methods. In multi-year emission prediction, such reductions can lead to lower cumulative projection errors, supporting more reliable quantitative policy design. Statistical analysis confirms significance (Friedman p=0.0018 ) with a strong effect size ( W=0.975 ) and significant Holm-adjusted post-hoc comparisons ( pholm<0.05 ). As additional validation, the proposed method is further evaluated on small-scale carbon-emissions datasets, where it also demonstrates consistent performance. Overall, these findings suggest that the proposed method provides a competitive approach for high-dimensional carbon-emissions modeling.
The forecasting of financial time series has gained more significance in decision making within a dynamic economic setting. Over the last few years, there has been a push in exploring both classical machine learning methods and novel quantum machine learning models with a view to enhance predictive accuracy. This paper suggests a quantum-classical regression framework developed that combines the feature selection in the form of a Random Forest in a hybrid approach, dimensionality reduction in the mode of Principal Component Analysis (PCA), and predicting in the form of a Variational Quantum Circuit (VQC). It is tested in various financial indicators, as BSE ESG, Carbon Exchange, Energy, Green Exchange, Oil and Gas and Power, with the help of RMSE and R 2 as the measure of performance. As experimental findings indicate, the classical algorithms like Random Forest and k-Nearest Neighbors always have the best accuracy and stability compared to quantum and hybrid ones. Quantum models are unstable, in contrast to Quantum kNN which is fairly stable. The hybrid model performs moderately with consistent error values but fairly lower explanatory power with significant results mostly on the BSE ESG data. In general, the paper has pointed out that classical approaches are still best in structured financial prediction tasks and hybrid quantum-classical models are potentially effective, but not yet competent. The results give valuable information on the existing limitation and future of the quantum machine learning to financial forecasting applications.
This paper explores the application of quantum algorithms for feature selection and dimensionality reduction within the field of quantum machine learning. Traditional methods for these tasks often suffer from computational bottlenecks, particularly when dealing with high-dimensional datasets. We propose a framework that leverages the principles of quantum computing to accelerate these processes. Specifically, we investigate the transformation of feature selection and dimensionality reduction problems into quantum optimization problems. We then examine the utilization of quantum annealing and variational quantum sampling algorithms for solving these problems. The core claim is that by employing quantum algorithms, we can significantly improve the efficiency and accuracy of machine learning models. The theoretical framework presented outlines a novel approach to tackling these challenges, offering a potential pathway towards more powerful and scalable quantum machine learning systems. This work provides a foundational exploration into this emerging area, focusing on the algorithmic strategies and potential benefits. ---
Blood glucose is one of the key indicators influencing the body’s metabolic performance. Accurate prediction and proactive management of this parameter are of paramount clinical importance. In this context, the analysis and evaluation of quantum machine learning (QML) algorithms for processing medical data and enhancing the predictive accuracy of health-related models have emerged as cutting-edge research directions in recent studies. Leveraging the principles of quantum physics and computation, QML algorithms serve as a promising alternative to classical methods for predicting chronic diseases. By mapping classical data into a quantum feature space and exploiting intrinsic quantum properties such as superposition and entanglement, these algorithms significantly enhance the ability to detect complex and latent patterns within datasets. In this study, the dataset was first preprocessed using Principal Component Analysis (PCA) for dimensionality reduction and noise suppression. Subsequently, the predictive performance of two quantum machine learning models—the Quantum Support Vector Machine (QSVM) and the Variational Quantum Circuit (VQC)—was evaluated and compared with that of the classical Support Vector Machine (SVM) for blood glucose level prediction. The results indicate that the QSVM model achieves a prediction accuracy of 90%, outperforming the classical SVM, which attained an accuracy of 74.4%. Moreover, the hybrid classical–quantum VQC model demonstrated the highest predictive performance, achieving an accuracy of 94.2%, thereby establishing it as the most effective approach for blood glucose level forecasting in this experimental setting.
Principal component analysis (PCA) is a significant dimensionality reduction technique for information. Unlike classical PCA, which is demanding in computational resources due to the increase in size and complexity of data, Quantum PCA (QPCA) theoretically can not only achieve the same outcome in an exponentially faster time by optimizing linear algebra in a new and efficient way through the use of quantum physics. Despite QPCA possessing theoretical advantages, the application of QPCA for real-world problems is limited due to quantum hardware capabilities, sensitivity of the algorithm to noise, and efficiency of the approach. New quantum circuit designs, better encoding methods of data and strategies to reduce noise, and other errors mentioned previously, Chapter 3 introduces the idea of combining quantum and classical approaches (Hybrid Quantum Classical PCA) to ameliorate these factors; we will refer to this as a “hybrid approach.” We evaluate HQCPCA with respect to QPCA's best performing algorithms with respect to fidelity, accuracy, run time, QPCA's circuit depth, and noise performance. HQCPCA is an efficient and reliable option for general quantum data processing, as these results indicate reduced circuit depth of 24.5%, a 15.8% increase in execution time, and a 2.9% increase in accuracy as compared to the best-performing algorithms mentioned above.