arXiv subjects

Melissa Lopez

Publications and source records attributed to Melissa Lopez.

14 recordsLinked to original sources

arXiv2026

Realistic Time-Domain Synthesis of Gravitational-Wave Detector Glitches using Class-Conditional Derivative Generative Adversarial Networks

Gravitational-wave detectors are highly sensitive instruments susceptible to numerous noise sources. Short-duration transient noise events, known as glitches, pose a particular challenge for data analysis pipelines as they can mimic or obscure astrophysical signals. We present GlitchGAN, a class-conditional generative model that is capable of synthesizing realistic glitches directly in the time domain. The model is trained on high-quality reconstructions of seven common glitch types observed during LIGO's third observing run (O3): Blip, Fast Scattering, Koi Fish, Low-Frequency Burst, Scattered Light, Tomte, and Whistle. We show that GlitchGAN generalizes effectively, learning to reproduce a diverse and physically consistent glitch space directly from these reconstructions. Moreover, because the model is conditioned on glitch class, it can generate \textit{hybrid} or transitional glitch morphologies by interpolating across the class-conditioning vector after training. GlitchGAN generates 1000 glitches in under 22 seconds on a CPU, making it suitable for large-scale glitch synthesis for detector simulations, mock data challenges, and pipeline validation. Synthetic glitches are validated against real glitches using the Gravity Spy classifier, widely used in the GW community for glitch classification, and an unsupervised analysis using UMAP embeddings. Gravity Spy classifies the majority of GlitchGAN's synthetic glitches as the correct class while the UMAP analysis shows substantial overlap between real and synthetic samples in the reduced latent space. We further highlight a critical limitation of magnitude-only spectrograms: classifiers operating on magnitude $Q$-transforms can confidently misclassify physically unrealistic glitches from less robust models, underscoring the need for complementary validation methods that preserve phase information.

astro-ph.IM↗

arXiv2024

Ameliorating transient noise bursts in gravitational-wave searches for intermediate-mass black holes

The direct observation of intermediate-mass black holes (IMBH) populations would not only strengthen the possible evolutionary link between stellar and supermassive black holes, but unveil the details of the pair-instability mechanism and elucidate their influence in galaxy formation. Conclusive observation of IMBHs remained elusive until the detection of gravitational-wave (GW) signal GW190521, which lies with high confidence in the mass gap predicted by the pair-instability mechanism. Despite falling in the sensitivity band of current GW detectors, IMBH searches are challenging due to their similarity to transient bursts of detector noise, known as glitches. In this proof-of-concept work, we combine a matched-filter algorithm with a Machine Learning (ML) method to differentiate IMBH signals from non-transient burst noise, known as glitches. In particular, we build a multi-layer perceptron network to perform a multi-class classification of the output triggers of matched-filter. In this way we are able to distinguish simulated GW IMBH signals from different classes of glitches that occurred during the third observing run (O3) {in single detector data}. {We train, validate, and test our model on O3a data, reaching a true positive rate of over $90\%$ for simulated IMBH signals. To test the generalization ability over the evolutionary observing run, we test on the useen data of O3b, which yields a true positive rate of over $70\%$} . We also combine data from multiple detectors to search for simulated IMBH signals in real detector noise, providing a significance measure for the output of our ML method.

astro-ph.IM↗

arXiv2024

Null Stream Based Third-generation-ready Glitch Mitigation for Gravitational Wave Measurements

Gravitational Wave (GW) detectors routinely encounter transient noise bursts, known as glitches, which are caused by either instrumental or environmental factors. Due to their high occurrence rate, glitches can overlap with GW signals, as in the notable case of GW170817, the first detection of a binary neutron star merger. Accurate reconstruction and subtraction of these glitches is a challenging problem that must be addressed to ensure that scientific conclusions drawn from the data are reliable. This problem will intensify with third-generation observatories like the Einstein Telescope (ET) due to their higher detection rates of GWs and the longer duration of signals within the sensitivity band of the detectors. Robust glitch mitigation algorithms are, therefore, crucial for maximizing the scientific output of next-generation GW observatories. For the first time, we demonstrate how the null stream inherent in ET's unique triangular configuration can be leveraged by state-of-the-art glitch characterization methodology to essentially undo the effect of glitches for the purpose of estimating the parameters of the source. The null stream based approach enables characterization and subtraction of glitches that occur arbitrarily close to the peak of the signal without any significant effect on the quality of parameter measurements, and achieves an order of magnitude computational speed-up compared to when the null stream is not available. By contrast, without the null stream, significant biases can occur in the glitch reconstruction, which deteriorate the quality of subsequent measurements of the source parameters. This demonstrates a clear edge which the null stream can offer for precision GW science in the ET era.

gr-qc↗

arXiv2024

Improving early detection of gravitational waves from binary neutron stars using CNNs and FPGAs

The detection of gravitational waves (GWs) from binary neutron stars (BNSs) with possible telescope follow-ups opens a window to ground-breaking discoveries in the field of multi-messenger astronomy. With the improved sensitivity of current and future GW detectors, more BNS detections are expected in the future. Therefore, enhancing low-latency GW search algorithms to achieve rapid speed, high accuracy, and low computational cost is essential. One innovative solution to reduce latency is the use of machine learning (ML) methods embedded in field-programmable gate arrays (FPGAs). In this work, we present a novel \texttt{WaveNet}-based method, leveraging the state-of-the-art ML model, to produce early-warning alerts for BNS systems. Using simulated GW signals embedded in Gaussian noise from the Advanced LIGO and Advanced Virgo detectors' third observing run (O3) as a proof-of-concept dataset, we demonstrate significant performance improvements. Compared to the current leading ML-based early-warning system, our approach enhances detection accuracy from 66.81\% to 76.22\% at a 1\% false alarm probability. Furthermore, we evaluate the time, energy, and economical cost of our model across CPU, GPU, and FPGA platforms, showcasing its potential for deployment in real-time gravitational wave detection pipelines.

astro-ph.IM↗

arXiv2024

cDVGAN: One Flexible Model for Multi-class Gravitational Wave Signal and Glitch Generation

Simulating realistic time-domain observations of gravitational waves (GWs) and GW detector glitches can help in advancing GW data analysis. Simulated data can be used in downstream tasks by augmenting datasets for signal searches, balancing data sets for machine learning, and validating detection schemes. In this work, we present Conditional Derivative GAN (cDVGAN), a novel conditional model in the Generative Adversarial Network framework for simulating multiple classes of time-domain observations that represent gravitational waves (GWs) and detector glitches. cDVGAN can also generate generalized hybrid samples that span the variation between classes through interpolation in the conditioned class vector. cDVGAN introduces an additional player into the typical 2-player adversarial game of GANs, where an auxiliary discriminator analyzes the first-order derivative time-series. Our results show that this provides synthetic data that better captures the features of the original data. cDVGAN conditions on three classes, two denoised from LIGO blip and tomte glitch events from its 3rd observing run (O3), and the third representing binary black hole (BBH) mergers. Our proposed cDVGAN outperforms 4 different baseline GAN models in replicating the features of the three classes. Specifically, our experiments show that training convolutional neural networks (CNNs) with our cDVGAN-generated data improves the detection of samples embedded in detector noise beyond the synthetic data from other state-of-the-art GAN models. Our best synthetic dataset yields as much as a 4.2% increase in area-under-the-curve (AUC) performance compared to synthetic datasets from baseline GANs. Moreover, training the CNN with hybrid samples from our cDVGAN outperforms CNNs trained only on the standard classes, when identifying real samples embedded in LIGO detector background (4% AUC improvement for cDVGAN).

physics.ins-det↗

arXiv2023

Detection of anomalies amongst LIGO's glitch populations with autoencoders

Gravitational-wave (GW) interferometers are able to detect a change in distance of $\sim$ 1/10,000th the size of a proton. Such sensitivity leads to large appearance rates of non-Gaussian transient noise bursts in the main detector strain, also known as glitches. These glitches come in a wide range of frequency-amplitude-time morphologies and are caused by environmental or instrumental processes, hindering searches for all sources of gravitational waves. Current approaches for their identification use supervised models to learn their morphology in the main strain, but do not consider relevant information provided by auxiliary channels that monitor the state of the interferometers nor provide a flexible framework for novel glitch morphologies. In this work, we present an unsupervised algorithm to find anomalous glitches. We encode a subset of auxiliary channels from LIGO Livingston in the fractal dimension, a measure for the complexity of the data, and learn the underlying distribution of the data using an auto-encoder with periodic convolutions. In this way, we uncover unknown glitch morphologies, and overlaps in time between different glitches and misclassifications. This led to the discovery of anomalies in $6.6 \%$ of the input data. The results of this investigation stress the learnable structure of auxiliary channels encoded in fractal dimension and provide a flexible framework to improve the state-of-the-art of glitch identification algorithms.

astro-ph.IM↗

arXiv2023

Gravitational-Wave Searches for Cosmic String Cusps in Einstein Telescope Data using Deep Learning

Gravitational-wave searches for cosmic strings are currently hindered by the presence of detector glitches, some classes of which strongly resemble cosmic string signals. This confusion greatly reduces the efficiency of searches. A deep-learning model is proposed for the task of distinguishing between gravitational wave signals from cosmic string cusps and simulated blip glitches in design sensitivity data from the future Einstein Telescope. The model is an ensemble consisting of three convolutional neural networks, achieving an accuracy of 79%, a true positive rate of 76%, and a false positive rate of 18%. This marks the first time convolutional neural networks have been trained on a realistic population of Einstein Telescope glitches. On a dataset consisting of signals and glitches, the model is shown to outperform matched filtering, specifically being better at rejecting glitches. The behaviour of the model is interpreted through the application of several methods, including a novel technique called waveform surgery, used to quantify the importance of waveform sections to a classification model. In addition, a method to visualise convolutional neural network activations for one-dimensional time series is proposed and used. These analyses help further the understanding of the morphological differences between cosmic string cusp signals and blip glitches. Because of its classification speed in the order of magnitude of milliseconds, the deep-learning model is suitable for future use as part of a real-time detection pipeline. The deep-learning model is transverse and can therefore potentially be applied to other transient searches.

astro-ph.IM↗

arXiv2023

Searching for ring-like structures in the Cosmic Microwave Background

In this research, we present an alternative methodology to search for ring-like structures in the sky with unusually large temperature gradients, namely Hawking points (HP), in the Cosmic Microwave Background (CMB), which are possible observational effects associated with Conformal Cyclic Cosmology (CCC). To assess the performance of our method, we constructed an artificial data set of HP, according to CCC, and we were able to retrieve $95 \%$ of ring-like anomalies from it. Furthermore, we scanned the \textit{Planck} CMB sky map and compared it to simulations according to $ΛCDM$, where we applied robust statistical tests to assess the existence of HP. Even though no significant ring-like structures were observed, we report the largest excess of HP candidates found at $α= $1\% significance level for the analyzed sky maps (CMB at 70GHz, SEVEM, SMICA, and Commander-Ruler), and we stress the need to continue the theoretical and experimental research in this direction.

astro-ph.CO↗

arXiv2022

Simulating Transient Noise Bursts in LIGO with gengli

In the field of gravitational-wave (GW) interferometers, the most severe limitation to the detection of transient signals from astrophysical sources comes from transient noise artefacts, known as glitches, that happens at a rate around $1$ per minute. Because glitches reduce the amount of scientific data available, there is a need for better modelling and inclusion of glitches in large-scale studies, such as stress testing the search pipelines and increasing the confidence of detection. In this work, we employ a Generative Adversarial Network (GAN) to produce a particular class of glitches ({\it blip}) in the time domain. We share the trained network through a user-friendly open-source software package called \texttt{gengli} and provide practical examples of its usage.

astro-ph.IM↗

arXiv2022

Convolutional neural network for gravitational-wave early alert: Going down in frequency

We present here the latest development of a machine-learning pipeline for pre-merger alerts from gravitational waves coming from binary neutron stars. This work starts from the convolutional neural networks introduced in our previous paper (PhysRevD.103.102003) that searched for three classes of early inspirals in simulated Gaussian noise colored with the design-sensitivity power-spectral density of LIGO. Our new network is able to search for any type of binary neutron stars, it can take into account all the detectors available, and it can see the events even earlier than the previous one. We study the performance of our method in three different types of noise: Gaussian O3 noise, real O3 noise, and predicted O4 noise. We show that our network performs almost as well in non-Gaussian noise as in Gaussian noise: our method is robust w.r.t. glitches and artifacts present in real noise. Although it would not have been able to trigger on the BNSs detected during O3 because their signal-to-noise ratio was too weak, we expect our network to find around 3 BNSs during O4 with a time before the merger between 3 and 88 s in advance.

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↗

arXiv2022

Understanding Iterative Revision from Human-Written Text

Writing is, by nature, a strategic, adaptive, and more importantly, an iterative process. A crucial part of writing is editing and revising the text. Previous works on text revision have focused on defining edit intention taxonomies within a single domain or developing computational models with a single level of edit granularity, such as sentence-level edits, which differ from human's revision cycles. This work describes IteraTeR: the first large-scale, multi-domain, edit-intention annotated corpus of iteratively revised text. In particular, IteraTeR is collected based on a new framework to comprehensively model the iterative text revisions that generalize to various domains of formal writing, edit intentions, revision depths, and granularities. When we incorporate our annotated edit intentions, both generative and edit-based text revision models significantly improve automatic evaluations. Through our work, we better understand the text revision process, making vital connections between edit intentions and writing quality, enabling the creation of diverse corpora to support computational modeling of iterative text revisions.

cs.CL↗

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↗