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

In the case of Type-2 AGNs, estimating the mass of the black hole is a chal lenging task. Understanding how galaxies build and evolve requires considerable insight into the mass of black holes. In this work, we compared different classical and quantum machine learning algorithms for Black Hole mass estimation. 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, GRU (Gated Recurrent Unit), LSTM, Deep Residual Networks (ResNets) and Transformer-Based Regression. On the other hand, hybrid quantum algorithms such as the example of Hybrid Quantum Neural Networks, Q-LSTM, Sampler-QNN, Estimator-QNN, Varia- tional Quantum Regressor (VQR), Quantum Linear Regression(Q-LR), QML with JAX optimization were also tested. The results revealed that classical algorithms gave better R², MAE, MSE, and RMSE results than the quantum models. Among the classical models, LSTM has the best result with an accuracy of 99.77%. For quantum algorithms, Estimator-QNN has the highest accuracy with an MSE of 0.0124 and an accuracy of 99.75%. This study proves both the strengths and weaknesses of the classical approach and the quantum approach. This could be used as a reference to determine future application of quantum algorithms in astrophysical data analysis.