arXiv subjects

Amit Reza

Publications and source records attributed to Amit Reza.

At least 19 recordsLinked to original sources

arXiv2026

Metal Oxide Clusters in Gas Giant Exoplanet Atmospheres

This study investigates the thermal stability and absorption of metal oxide clusters in exoplanetary atmospheres. Utilizing our thermochemical data, we analyze eight distinct cluster families: magnesium oxide (MgO), silicon monoxide (SiO), titanium monoxide (TiO), vanadium monoxide (VO), titanium dioxide (TiO$_2$), vanadium dioxide (VO$_2$), aluminum oxide (Al$_2$O$_3$), and vanadium pentoxide (V$_2$O$_5$). Equilibrium cluster populations as a function of gas temperature and pressure reveal distinct stability regimes. Under solar elemental abundances, (TiO$_2$)$\rm\rm_N$ and (Al$_2$O$_3$)$\rm_N$ are favored at higher temperatures, while (MgO)$\rm_N$ and (SiO)$\rm_N$ dominate at lower temperatures. Computed absorption spectra exhibit strong size- and composition-dependent absorption features in the mid-infrared (8--50~$\mu$m), many of which fall within the wavelength range accessible to \texttt{JWST/MIRI}. We further coupled cluster thermodynamics with 3D general circulation model (GCM) outputs to investigate the cluster stability across the ultra-hot Jupiters (UHJs) WASP-121 b and WASP-18 b, the hot Jupiter (HJ) WASP-39 b, and the warm Jupiter (WJ) WASP-69 b. In WASP-121 b and WASP-18 b, extreme dayside temperatures suppress large-cluster stability, yielding atmospheres dominated by metal ions at low pressures and neutral metals at depth, with limited cluster survival on the nightside and morning terminator. In WASP-39 b, larger clusters are not thermochemically favoured despite the enhanced metallicity; instead, equilibrium chemistry stabilises smaller species, with only TiO showing a tendency toward stable larger cluster forms, likely due to its open d-orbitals. In contrast, WASP-69 b favors the formation of larger metal oxide clusters across an extended pressure range, highlighting WJs as a favorable environment for metal oxide cluster stability.

astro-ph.EP↗

arXiv2025

Accelerating exoplanet climate modelling: A machine learning approach to complement 3D GCM grid simulations

With the development of ever-improving telescopes capable of observing exoplanet atmospheres in greater detail and number, there is a growing demand for enhanced 3D climate models to support and help interpret observational data from space missions like CHEOPS, TESS, JWST, PLATO, and Ariel. However, the computationally intensive and time-consuming nature of general circulation models (GCMs) poses significant challenges in simulating a wide range of exoplanetary atmospheres. This study aims to determine whether machine learning (ML) algorithms can be used to predict the 3D temperature and wind structure of arbitrary tidally-locked gaseous exoplanets in a range of planetary parameters. A new 3D GCM grid with 60 inflated hot Jupiters orbiting A, F, G, K, and M-type host stars modelled with Exorad has been introduced. A dense neural network (DNN) and a decision tree algorithm (XGBoost) are trained on this grid to predict local gas temperatures along with horizontal and vertical winds. To ensure the reliability and quality of the ML model predictions, WASP-121 b, HATS-42 b, NGTS-17 b, WASP-23 b, and NGTS-1 b-like planets, which are all targets for PLATO observation, are selected and modelled with ExoRad and the two ML methods as test cases. The DNN predictions for the gas temperatures are to such a degree that the calculated spectra agree within 32 ppm for all but one planet, for which only one single HCN feature reaches a 100 ppm difference. The developed ML emulators can reliably predict the complete 3D temperature field of an inflated warm to ultra-hot tidally locked Jupiter around A to M-type host stars. It provides a fast tool to complement and extend traditional GCM grids for exoplanet ensemble studies. The quality of the predictions is such that no or minimal effects on the gas phase chemistry, hence on the cloud formation and transmission spectra, are to be expected.

astro-ph.EP↗

arXiv2025

Earthquake Response Analysis with AI

A timely and effective response is crucial to minimize damage and save lives during natural disasters like earthquakes. Microblogging platforms, particularly Twitter, have emerged as valuable real-time information sources for such events. This work explores the potential of leveraging Twitter data for earthquake response analysis. We develop a machine learning (ML) framework by incorporating natural language processing (NLP) techniques to extract and analyze relevant information from tweets posted during earthquake events. The approach primarily focuses on extracting location data from tweets to identify affected areas, generating severity maps, and utilizing WebGIS to display valuable information. The insights gained from this analysis can aid emergency responders, government agencies, humanitarian organizations, and NGOs in enhancing their disaster response strategies and facilitating more efficient resource allocation during earthquake events.

cs.SI↗

arXiv2025

Grid-based exoplanet atmospheric mass loss predictions through neural network

The fast and accurate estimation of planetary mass-loss rates is critical for planet population and evolution modelling. We use machine learning (ML) for fast interpolation across an existing large grid of hydrodynamic upper atmosphere models, providing mass-loss rates for any planet inside the grid boundaries with superior accuracy compared to previously published interpolation schemes. We consider an already available grid comprising about 11000 hydrodynamic upper atmosphere models for training and generate an additional grid of about 250 models for testing purposes. We develop the ML interpolation scheme (dubbed "atmospheric Mass Loss INquiry frameworK"; MLink) using a Dense Neural Network, further comparing the results with what was obtained employing classical approaches (e.g. linear interpolation and radial basis function-based regression). Finally, we study the impact of the different interpolation schemes on the evolution of a small sample of carefully selected synthetic planets. MLink provides high-quality interpolation across the entire parameter space by significantly reducing both the number of points with large interpolation errors and the maximum interpolation error compared to previously available schemes. For most cases, evolutionary tracks computed employing MLink and classical schemes lead to comparable planetary parameters at Gyr-timescales. However, particularly for planets close to the top edge of the radius gap, the difference between the predicted planetary radii at a given age of tracks obtained employing MLink and classical interpolation schemes can exceed the typical observational uncertainties. Machine learning can be successfully used to estimate atmospheric mass-loss rates from model grids paving the way to explore future larger and more complex grids of models computed accounting for more physical processes.

astro-ph.EP↗

arXiv2025

Predicting Steady-State Behavior in Complex Networks with Graph Neural Networks

In complex systems, information propagation can be defined as diffused or delocalized, weakly localized, and strongly localized. This study investigates the application of graph neural network models to learn the behavior of a linear dynamical system on networks. A graph convolution and attention-based neural network framework has been developed to identify the steady-state behavior of the linear dynamical system. We reveal that our trained model distinguishes the different states with high accuracy. Furthermore, we have evaluated model performance with real-world data. In addition, to understand the explainability of our model, we provide an analytical derivation for the forward and backward propagation of our framework.

cs.LG↗

arXiv2024

Machine learning-based classification for Single Photon Space Debris Light Curves

The growing number of man-made debris in Earth's orbit poses a threat to active satellite missions due to the risk of collision. Characterizing unknown debris is, therefore, of high interest. Light Curves (LCs) are temporal variations of object brightness and have been shown to contain information such as shape, attitude, and rotational state. Since 2015, the Satellite Laser Ranging (SLR) group of Space Research Institute (IWF) Graz has been building a space debris LC catalogue. The LCs are captured on a Single Photon basis, which sets them apart from CCD-based measurements. In recent years, Machine Learning (ML) models have emerged as a viable technique for analyzing LCs. This work aims to classify Single Photon Space Debris using the ML framework. We have explored LC classification using k-Nearest Neighbour (k-NN), Random Forest (RDF), XGBoost (XGB), and Convolutional Neural Network (CNN) classifiers in order to assess the difference in performance between traditional and deep models. Instead of performing classification on the direct LCs data, we extracted features from the data first using an automated pipeline. We apply our models on three tasks, which are classifying individual objects, objects grouped into families according to origin (e.g., GLONASS satellites), and grouping into general types (e.g., rocket bodies). We successfully classified Space Debris LCs captured on Single Photon basis, obtaining accuracies as high as 90.7%. Further, our experiments show that the classifiers provide better classification accuracy with automated extracted features than other methods.

astro-ph.IM↗

arXiv2024

A Novel Momentum-Based Deep Learning Techniques for Medical Image Classification and Segmentation

Accurately segmenting different organs from medical images is a critical prerequisite for computer-assisted diagnosis and intervention planning. This study proposes a deep learning-based approach for segmenting various organs from CT and MRI scans and classifying diseases. Our study introduces a novel technique integrating momentum within residual blocks for enhanced training dynamics in medical image analysis. We applied our method in two distinct tasks: segmenting liver, lung, & colon data and classifying abdominal pelvic CT and MRI scans. The proposed approach has shown promising results, outperforming state-of-the-art methods on publicly available benchmarking datasets. For instance, in the lung segmentation dataset, our approach yielded significant enhancements over the TransNetR model, including a 5.72% increase in dice score, a 5.04% improvement in mean Intersection over Union (mIoU), an 8.02% improvement in recall, and a 4.42% improvement in precision. Hence, incorporating momentum led to state-of-the-art performance in both segmentation and classification tasks, representing a significant advancement in the field of medical imaging.

cs.CV↗

arXiv2024

Mergers of hairy black holes: Constraining topological couplings from entropy

Hairy black-holes are a unique prediction of certain theories that extend General Relativity (GR) with a scalar field. The presence of scalar hair is reflected non-trivially in the entropy of the black hole along with any topological coupling that may be present in the action. Demanding that a system of two merging black holes obeys the global second law of thermodynamics imposes a bound on this topological coupling coefficient. In this work we study how this bound is pushed from its GR value by the presence of scalar hair by considering estimates of binary black-hole merger parameters through inference studies of both mock and real gravitational-wave (GW) events. Although the scalar charge may produce a statistically significant deviation of the change in entropy over the GR prediction, we find no evidence of this happening in the data from real GW events taken from GWTC-1. We also find the entropy change to be susceptible to biases arising out of GW inferences which ends up being two orders of magnitude larger, therefore overwhelming any change, if at all, induced by the scalar hair.

gr-qc↗

arXiv2024

Fast and faithful interpolation of numerical relativity surrogate waveforms using meshfree approximation

Several theoretical waveform models have been developed over the years to capture the gravitational wave emission from the dynamical evolution of compact binary systems of neutron stars and black holes. As ground-based detectors improve their sensitivity at low frequencies, the real-time computation of these waveforms can become computationally expensive, exacerbating the steep cost of rapidly reconstructing source parameters using Bayesian methods. This paper describes an efficient numerical algorithm for generating high-fidelity interpolated compact binary waveforms at an arbitrary point in the signal manifold by leveraging computational linear algebra techniques such as singular value decomposition and meshfree approximation. The results are presented for the time-domain \texttt{NRHybSur3dq8} inspiral-merger-ringdown (IMR) waveform model that is fine tuned to numerical relativity simulations and parameterized by the two component-masses and two aligned spins. For demonstration, we target a specific region of the intrinsic parameter space inspired by the previously inferred parameters of the \texttt{GW200311\_115853} event -- a binary black hole system whose merger was recorded by the network of advanced-LIGO and Virgo detectors during the third observation run. We show that the meshfree interpolated waveforms can be evaluated in $\sim 2.3$ ms, which is about $\times 38$ faster than its brute-force (frequency-domain tapered) implementation in the \textsc{PyCBC} software package at a median accuracy of $\sim \mathcal{O}(10^{-5})$. The algorithm is computationally efficient and scales favourably with an increasing number of dimensions of the parameter space. This technique may find use in rapid parameter estimation and source reconstruction studies.

gr-qc↗

arXiv2023

Prompt sky localization of compact binary sources using a meshfree approximation

The number of gravitational wave signals from the merger of compact binary systems detected in the network of advanced LIGO and Virgo detectors is expected to increase considerably in the upcoming science runs. Once a confident detection is made, it is crucial to reconstruct the source's properties rapidly, particularly the sky position and chirp mass, to follow up on these transient sources with telescopes operating at different electromagnetic bands for multi-messenger astronomy. In this context, we present a rapid parameter estimation (PE) method aided by mesh-free approximations to accurately reconstruct properties of compact binary sources from data gathered by a network of gravitational wave detectors. This approach builds upon our previous algorithm [L. Pathak et al., Fast likelihood evaluation using meshfree approximations for reconstructing compact binary sources, https://journals.aps.org/prd/abstract/10.1103/PhysRevD.108.064055, Phys. Rev. D 108, 064055 (2023)] to expedite the evaluation of the likelihood function and extend it to enable coherent network PE in a ten-dimensional parameter space, including sky position and polarization angle. Additionally, we propose an optimized interpolation node placement strategy during the start-up stage to enhance the accuracy of the marginalized posterior distributions. With this updated method, we can estimate the properties of binary neutron star (BNS) sources in approximately 2.4~(2.7) min for the \TaylorF~(\texttt{IMRPhenomD}) signal model by utilizing 64 CPU cores on a shared memory architecture. Furthermore, our approach can be integrated into existing parameter estimation pipelines, providing a valuable tool for the broader scientific community. We also highlight some areas for improvements to this algorithm in the future, which includes overcoming the limitations due to narrow prior bounds.

gr-qc↗

arXiv2022

Fast likelihood evaluation using meshfree approximations for reconstructing compact binary sources

Several rapid parameter estimation methods have recently been advanced to deal with the computational challenges of the problem of Bayesian inference of the properties of compact binary sources detected in the upcoming science runs of the terrestrial network of gravitational wave detectors. Some of these methods are well-optimized to reconstruct gravitational wave signals in nearly real-time necessary for multi-messenger astronomy. In this context, this work presents a new, computationally efficient algorithm for fast evaluation of the likelihood function using a combination of numerical linear algebra and mesh-free interpolation methods. The proposed method can rapidly evaluate the likelihood function at any arbitrary point of the sample space at a negligible loss of accuracy and is an alternative to the grid-based parameter estimation schemes. We obtain posterior samples over model parameters for a canonical binary neutron star system by interfacing our fast likelihood evaluation method with the nested sampling algorithm. The marginalized posterior distributions obtained from these samples are statistically identical to those obtained by brute force calculations. We find that such Bayesian posteriors can be determined within a few minutes of detecting such transient compact binary sources, thereby improving the chances of their prompt follow-up observations with telescopes at different wavelengths. It may be possible to apply the blueprint of the meshfree technique presented in this study to Bayesian inference problems in other domains.

gr-qc↗

arXiv2022

Detection of Gravitational Wave Signals from Precessing Binary Black Hole Systems using Convolutional Neural Network

Current searches for gravitational waves (GWs) from black hole binaries using the LIGO and Virgo observatories are limited to analytical models for systems with black hole spins aligned (or anti-aligned) with the orbital angular momentum of the binary. Detecting black hole binaries with precessing spinsis crucial for gaining unique astrophysical insights into the formation of these sources. Therefore, it is essential to develop a search strategy capable of identifying compact binaries with precessing spins. Aligned-spin waveform models are inadequate for detecting compact binaries with high precessing spins. While several efforts have been made to construct template banks for detecting precessing binaries using matched filtering, this approach requires many templates to cover the entire search parameter space, significantly increasing the computational cost. This work explores the detection of GW signals from binary black holes(BBH) with both aligned and precessing spins using a convolutional neural network (CNN). We frame the detection of GW signals from aligned or precessing BBH systems as a hierarchical binary classification problem. The first CNN model classifies strain data as either pure noise or noisy signals (GWs from BBH). A second CNN model then classifies the detected noisy signal data as originating from either precessing or non-precessing (aligned/anti-aligned) systems. Using simulated data, the trained classifier distinguishes between noise and noisy GW signals with more than 99% accuracy. The second classifier further differentiates between aligned and highly precessing signals with around 95% accuracy. We extended our analysis to a multi-detector framework by performing a coincident test. Additionally, we tested the performance of our trained architecture on data from the first three observation runs of LIGO to identify detected BBH events as either aligned or precessing.

gr-qc↗

arXiv2022

Simulating Transient Noise Bursts in LIGO with Generative Adversarial Networks

The noise of gravitational-wave (GW) interferometers limits their sensitivity and impacts the data quality, hindering the detection of GW signals from astrophysical sources. For transient searches, the most problematic are transient noise artifacts, known as glitches, that happen at a rate around $ 1 \text{ min}^{-1}$, and can mimic GW signals. Because of this, there is a need for better modeling and inclusion of glitches in large-scale studies, such as stress testing the pipelines. In this proof-of concept work we employ Generative Adversarial Networks (GAN), a state-of-the-art Deep Learning algorithm inspired by Game Theory, to learn the underlying distribution of blip glitches and to generate artificial populations. We reconstruct the glitch in the time-domain, providing a smooth input that the GAN can learn. With this methodology, we can create distributions of $\sim 10^{3}$ glitches from Hanford and Livingston detectors in less than one second. Furthermore, we employ several metrics to measure the performance of our methodology and the quality of its generations. This investigation will be extended in the future to different glitch classes with the final goal of creating an open-source interface for mock data generation.

astro-ph.IM↗

arXiv2021

Employing Deep Learning for Detection of Gravitational Waves from Compact Binary Coalescences

The matched filtering paradigm is the mainstay of gravitational wave (GW) searches from astrophysical coalescing compact binaries. The compact binary coalescence (CBC) search pipelines perform the matched filter between the GW detector's data and a large set of analytical waveforms. However, the computational cost of performing matched filter is very high as the required number of the analytical waveforms is also high. Recently, various deep learning-based methods have been deployed to identify a GW signal in the detector output as an alternative to computationally expensive matched filtering techniques. In past work, the researchers have considered the detection of GW signal mainly as a classification problem, in which they train the deep learning-based architecture by considering the noise and the GW signal as two different classes. However, in this work, for the first time, we have combined the Convolutional Neural Network (CNN) and matched filter methods to reduce the computational cost of the search by reducing the number of matched filtering operations. We have implemented the CNN based architecture not only for classification of the signal but also to identify the location of the signal in the intrinsic parameter space. Identifying the location in which the detected signal lies enables us to perform the matched filter operations between the data and the analytical waveforms generated for the smaller region of the parameter space only - thereby reducing the computational cost of the search. We demonstrate our method for two-dimensional parameter space for stellar to high mass binary black hole systems. In particular, we are able to classify between pure noise and noisy BBH signals with 99% accuracy. Further, the detected signals have been sub-classified into patches in mass components with an average accuracy > 97%

gr-qc↗

arXiv2021

Detecting the early inspiral of a gravitational-wave signal with convolutional neural networks

We introduce a novel methodology for the operation of an early %warning alert system for gravitational waves. It is based on short convolutional neural networks. We focus on compact binary coalescences, for light, intermediate and heavy binary-neutron-star systems. The signals are 1-dimensional time series $-$ the whitened time-strain $-$ injected in Gaussian noise built from the power-spectral density of the LIGO detectors at design sensitivity. We build short 1-dimensional convolutional neural networks to detect these types of events by training them on part of the early inspiral. We show that such networks are able to retrieve these signals from a small portion of the waveform.

gr-qc↗

arXiv2021

Convolutional neural networks for the detection of the early inspiral of a gravitational-wave signal

GW170817 has led to the first example of multi-messenger astronomy with observations from gravitational wave interferometers and electromagnetic telescopes combined to characterise the source. However, detections of the early inspiral phase by the gravitational wave detectors would allow the observation of the earlier stages of the merger in the electromagnetic band, improving multi-messenger astronomy and giving access to new information. In this paper, we introduce a new machine-learning-based approach to produce early-warning alerts for an inspiraling binary neutron star system, based only on the early inspiral part of the signal. We give a proof of concept to show the possibility to use a combination of small convolutional neural networks trained on the whitened detector strain in the time domain to detect and classify early inspirals. Each of those is targeting a specific range of chirp masses dividing the binary neutron star category into three sub-classes: light, intermediate and heavy. In this work, we focus on one LIGO detector at design sensitivity and generate noise from the design power spectral density. We show that within this setup it is possible to produce an early alert up to 100 seconds before the merger for the best-case scenario. We also present some future upgrades that will enhance the detection capabilities of our convolutional neural networks. Finally, we also show that the current number of detections for a realistic binary neutron star population is comparable to that of matched filtering and that there is a high probability to detect GW170817- and GW190425-like events at design sensitivity.

gr-qc↗

arXiv2021

Random projections in gravitational-wave searches from compact binaries II: efficient reconstruction of the detection statistic

Low-latency gravitational wave search pipelines such as GstLAL take advantage of low-rank factorization of the template matrix via singular value decomposition (SVD). With unprecedented improvements in detector bandwidth and sensitivity in advanced-LIGO and Virgo detectors, one expects several orders of magnitude increase in the size of template banks. This poses a formidable computational challenge in factorizing huge template matrices. Previously, [in Kulkarni et al. [6]], we introduced the idea of random projection (RP)-based matrix factorization as a computationally viable alternative to SVD, applicable for large template banks. This follow-up paper demonstrates the application of a block-wise randomized matrix factorization (RMF) algorithm for computing low-rank factorizations at a preset average fractional loss of SNR. This new scheme is shown to be more efficient in the context of the LLOID framework of the GstLAL search pipeline. Further, it is well-known that for huge template banks, the total computational cost of the search is dominated by reconstructing the detection statistic compared to that of filtering the data. However, optimizing the reconstruction cost has not been addressed satisfactorily so far in the available literature. We show that it is possible to approximately reconstruct the time-series of the matched-filter detection statistic at a fraction of the total cost using the matching pursuit algorithm. Combining the two algorithms presented in this paper can handle online searches involving large template banks more efficiently. We have analyzed the total computational cost in detail and offer various tips for optimally applying the RMF scheme in different parts of the parameter space. The algorithms presented in this paper are designed in a suitable manner that can be efficiently implemented over a distributed computing architecture.

gr-qc↗

arXiv2020

Automating the Inclusion of Subthreshold Signal-to-Noise Ratios for Rapid Gravitational-Wave Localization

The accurate localization of gravitational-wave (GW) events in low-latency is a crucial element in the search for further multimessenger signals from these cataclysmic events. The localization of these events in low-latency uses signal-to-noise ratio (SNR) time-series from matched-filtered searches which identify candidate events. Here we report on an improvement to the GstLAL-based inspiral pipeline, the low-latency pipeline that identified GW170817 and GW190425, which automates the use of SNRs from all detectors in the network in rapid localization of GW events. This improvement was incorporated into the detection pipeline prior to the recent third observing run of the Advanced LIGO and Advanced Virgo detector network. Previously for this pipeline, manual intervention was required to use SNRs from all detectors if a candidate GW event was below an SNR threshold for any detector in the network. The use of SNRs from subthreshold events can meaningfully decrease the area of the 90% confidence region estimated by rapid localization. To demonstrate this, we present a study of the simulated detections of $\mathcal{O}(2\times10^4)$ binary neutron stars using a network mirroring the second observational run of the Advanced LIGO and Virgo detectors. When incorporating subthreshold SNRs in rapid localization, we find that the fraction of events that can be localized down to $100~\mathrm{deg}^2$ or smaller increases by a factor 1.18.

astro-ph.IM↗