Comparative Analysis of Black Hole Mass Estimation in Type-2 AGNs: Classical vs. Quantum Machine Learning and Deep Learning Approaches

TL;DR

The paper tackles the challenge of estimating black hole masses in Type-2 AGNs, where obscuration of the broad-line region complicates traditional methods. It benchmarks a broad set of approaches—classical ML, classical DL, and quantum ML—on SDSS DR7 Type-2 AGN data, using standard regression metrics. Core findings show that classical methods, especially LSTM, outperform quantum models, though Estimator-QNN is the strongest quantum performer; the results highlight the current maturity gap between classical and quantum approaches in astrophysical data analysis. The study provides a practical benchmark and clarifies the conditions under which quantum machine learning may offer benefits in upcoming astronomical data analyses, while outlining clear avenues for future improvements in quantum hardware and algorithms.

Abstract

In the case of Type-2 AGNs, estimating the mass of the black hole is challenging. Understanding how galaxies form and evolve requires considerable insight into the mass of black holes. This work compared different classical and quantum machine learning (QML) algorithms for black hole mass estimation, wherein the classical algorithms are Linear Regression, XGBoost Regression, Random Forest Regressor, Support Vector Regressor (SVR), Lasso Regression, Ridge Regression, Elastic Net Regression, Bayesian Regression, Decision Tree Regressor, Gradient Booster Regressor, Classical Neural Networks, Gated Recurrent Unit (GRU), LSTM, Deep Residual Networks (ResNets) and Transformer-Based Regression. On the other hand, quantum algorithms including Hybrid Quantum Neural Networks (QNN), Quantum Long Short-Term Memory (Q-LSTM), Sampler-QNN, Estimator-QNN, Variational Quantum Regressor (VQR), Quantum Linear Regression(Q-LR), QML with JAX optimization were also tested. The results revealed that classical algorithms gave better R^2, MAE, MSE, and RMSE results than the quantum models. Among the classical models, LSTM has the best result with an accuracy of 99.77%. Estimator-QNN has the highest accuracy for quantum algorithms with an MSE of 0.0124 and an accuracy of 99.75%. This study ascertains both the strengths and weaknesses of the classical and the quantum approaches. As far as our knowledge goes, this work could pave the way for the future application of quantum algorithms in astrophysical data analysis.

Figures (10)

• Figure 1: Steps for Blackhole Mass Estimation Catalog Creation
• Figure 2: Workflow diagram for Executing Classical DL and ML Algorithms
• Figure 3: Workflow diagram for Executing QML Algorithms
• Figure 4: RMSE, MSE and MAE values for Classical Machine Learning Algorithms
• Figure 5: $R^2$ values for Classical Machine Learning Algorithms