arXiv subjects

N. Mankatwit

Publications and source records attributed to N. Mankatwit.

3 recordsLinked to original sources

arXiv2025

Revealing Hidden Repeaters in the CHIME/FRB Catalog: Semi-Supervised Insights into the Fast Radio Burst Population

Fast radio bursts (FRBs) are millisecond-duration extragalactic transients, observationally classified as repeaters or nonrepeaters. This classification may be biased, as some apparently non-repeating sources could simply have undetected subsequent bursts. To address this, we develop a semi-supervised learning framework to identify distinguishing features of repeaters using primary observational parameters from the Blinkverse database, which draws from the CHIME/FRB Catalogs. The framework combines labeled data (known repeaters and confidently classified non-repeaters) with unlabeled sources previously flagged as non-repeaters but exhibiting repeater-like characteristics. We employ uniform manifold approximation and projection with a nearest-neighbor scheme to select potential candidates, followed by semi-supervised classification using five base estimators, including random forest, support vector machine, logistic regression, AdaBoost, and Gradient boost. Each model is fine-tuned through cross-validation, and a voting strategy among the five models is employed to enhance robustness. All models achieve consistently high performance, identifying dispersion measure, peak frequency, and fluence as the most discriminative features. Repeaters tend to show lower dispersion measures, higher peak frequencies, and higher fluences than non-repeaters. We also identify a set of candidate repeaters, several of which are consistent with prior independent studies. Our approach can identify 36 additional repeater candidates that conventional methods may have missed. Finally, the results highlight dispersion measure as a key discriminator between repeaters and non-repeaters, revealing a tension between physical and instrumental origins-either environmental effects, if the two populations arise from distinct progenitors, or detection bias, as nearby sources are more easily observed.

astro-ph.HE↗

arXiv2023

Coronal height constraint in IRAS 13224-3809 and 1H 0707-495 by the random forest regressor

We develop a random forest regressor (RFR) machine learning model to trace the coronal evolution in two highly variable active galactic nuclei (AGNs) IRAS 13224-3809 and 1H 0707-495 observed with XMM-Newton, by probing the X-ray reverberation features imprinted on their power spectral density (PSD) profiles. Simulated PSDs in the form of a power-law, with similar frequency range and bins to the observed data, are produced. Then, they are convolved with relativistic disc-response functions from a lamp-post source before being used to train and test the model to predict the coronal height. We remove some bins that are dominated by Poisson noise and find that the model can tolerate the frequency-bin removal up to $\sim 10$ bins to maintain a prediction accuracy of $R^{2} > 0.9$. The black hole mass and inclination should be fixed so that the accuracy in predicting the source height is still $> 0.9$. The accuracy also increases with the reflection fraction. The corona heights for both AGN are then predicted using the RFR model developed from the simulated PSDs whose frequency range and bins are specifically adjusted to match those from each individual observation. The model suggests that their corona varies between $\sim~5 - 18~r_{\rm g}$, with $R^{2} > 0.9$ for all observations. Such high accuracy can still be obtained if the difference between the true mass and the trained value is $\lesssim 10\%$. Finally, the model supports the height-changing corona under the light-bending scenario where the height is correlated to source luminosity in both IRAS 13224-3809 and 1H 0707-495.

astro-ph.HE↗

arXiv2021

Machine learning application to detect light echoes around black holes

X-ray reverberation has become a powerful tool to probe the disc-corona geometry near black holes. Here, we develop Machine Learning (ML) models to extract the X-ray reverberation features imprinted in the Power Spectral Density (PSD) of AGN. The machine is trained using simulated PSDs in the form of a simple power-law encoded with the relativistic echo features. Dictionary Learning and sparse coding algorithms are used for the PSD reconstruction, by transforming the noisy PSD to a representative sparse version. Then, the Support Vector Machine is employed to extract the interpretable reverberation features from the reconstructed PSD that holds the information of the source height. The results show that the accuracy of predicting the source height, $h$, is genuinely high and the misclassification is only found when $h$ > 15$r_g$. When the test PSD has a bending power-law shape, which is completely new to the machine, the accuracy is still high. Therefore, the ML model does not require the intrinsic shape of the PSD to be determined in advance. By focusing on the PSD parameter space observed in real AGN data, classification for $h \leq$ 10$r_g$ can be determined with 100% accuracy, even using a PSD in an energy band that contains a reflection flux as low as 10% of the total flux. For $h$ > 10$r_g$, the data, if misclassified, will have small uncertainties of $Δh$ ~ 2-4$r_g$. This work shows, as a proof of concept, that the ML technique could shape new methodological directions in the X-ray reverberation analysis.

astro-ph.HE↗