arXiv subjects

Osvaldo Gramaxo Freitas

Publications and source records attributed to Osvaldo Gramaxo Freitas.

5 recordsLinked to original sources

arXiv2026

DANSur_HM: Modularly incorporating higher modes in a deep learning based gravitational-wave surrogate

Numerical relativity (NR) simulations provide the most faithful representation of the gravitational waves (GWs) emitted by binary black hole (BBH) systems during merger. In the context of GW astronomy, tasks such as parameter estimation can require vast numbers of waveform evaluations per second across the entire parameter space. Since performing full NR simulations for each evaluation is not computationally feasible, interpolating methods for existing NR waveforms, known as surrogate models, have been developed with marked success. In this paper, we build on our previous work to introduce methods to train a fast surrogate model based on neural networks in order to generate BBH merger waveforms, including the fundamental (2,2) mode, as well as the (3,3), (2,1), (4,4), (3,2), (4,3) and (5,5) higher-order modes. Applying a pretraining step on approximant data before fine-tuning on NR data allows us to smooth out the parameter space, and making use of the parallelization ability of GPUs to project the NR waveforms in the inclination-phase $(ι, ϕ)$ sphere during training allows the fitting of all the explored modes simultaneously. The developed surrogate model, \texttt{DANSur\_HM}, achieves average mismatches of the order of $10^{-4}$, with the worst mismatch at $2.5\times10^{-3}$, and achieves throughput above $6\times10^5$ waveforms/second on an NVIDIA V100 GPU. Parameter estimation tests confirm the usefulness of the inclusion of higher modes.

gr-qc↗

arXiv2026

An autoencoder-based surrogate waveform model for quasi-circular binary-black-hole mergers

The generation of accurate waveforms from binary black hole (BBH) mergers is a major effort in Gravitational-Wave Astronomy. In recent years, machine-learning-based surrogate models for BBH waveforms have been proposed. Those offer the potential to dramatically accelerate waveform generation while maintaining accuracy competitive with that of traditional waveform approximants. In this work, we investigate the viability of autoencoders as generative models for gravitational-wave signals from quasi-circular BBH mergers. We introduce AESur3dq8, a novel surrogate waveform model based on autoencoders that enables the rapid and accurate construction of large template banks, producing millions of waveforms in under a second using modest computational resources. The model is trained on the numerical-relativity-informed surrogate NRHybSur3dq8 and subsequently fine-tuned using the SXS catalog of BBH simulations. We demonstrate that waveforms generated by AESur3dq8 achieve mismatches of order $10^{-4}$ with respect to Numerical Relativity waveforms, and that parameter estimation performed with these templates yields results fully consistent with those reported by the LIGO-Virgo-KAGRA Collaboration for observed gravitational-wave events.

astro-ph.IM↗

arXiv2025

A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms

Gravitational-wave approximants are essential for gravitational-wave astronomy, allowing the coverage binary black hole parameter space for inference or match filtering without costly numerical relativity (NR) simulations, but generally trading some accuracy for computational efficiency. To reduce this trade-off, NR surrogate models can be constructed using interpolation within NR waveform space. We present a 2-stage training approach for neural network-based NR surrogate models. Initially trained on approximant-generated waveforms and then fine-tuned with NR data, these dual-stage artificial neural surrogate (\texttt{DANSur}) models offer rapid and competitively accurate waveform generation, generating millions in under 20ms on a GPU while keeping mean mismatches with NR around $10^{-4}$. Implemented in the \textsc{bilby} framework, we show they can be used for parameter estimation tasks.

gr-qc↗

arXiv2025

Parameter estimation of microlensed gravitational waves with Conditional Variational Autoencoders

Gravitational lensing of gravitational waves (GWs) provides a unique opportunity to study cosmology and astrophysics at multiple scales. Detecting microlensing signatures, in particular, requires efficient parameter estimation methods due to the high computational cost of traditional Bayesian inference. In this paper we explore the use of deep learning, namely Conditional Variational Autoencoders (CVAE), to estimate parameters of microlensed binary black hole (simulated) waveforms. We find that our CVAE model yields accurate parameter estimation and significant computational savings compared to Bayesian methods such as Bilby (up to five orders of magnitude faster inferences). Moreover, the incorporation of CVAE-generated priors into Bilby, based on the 95% confidence intervals of the CVAE posterior for the lensing parameters, reduces Bilby's average runtime by around 48% without any penalty on accuracy. Our results suggest that a CVAE model is a promising tool for future low-latency searches of lensed signals. Further applications to actual signals and integration with advanced pipelines could help extend the capabilities of GW observatories in detecting microlensing events.

gr-qc↗

arXiv2023

Comparison of neural network architectures for feature extraction from binary black hole merger waveforms

We evaluate several neural-network architectures, both convolutional and recurrent, for gravitational-wave time-series feature extraction by performing point parameter estimation on noisy waveforms from binary-black-hole mergers. We build datasets of 100,000 elements for each of four different waveform models (or approximants) in order to test how approximant choice affects feature extraction. Our choices include \texttt{SEOBNRv4P} and \texttt{IMRPhenomPv3}, which contain only the dominant quadrupole emission mode, alongside \texttt{IMRPhenomPv3HM} and \texttt{NRHybSur3dq8}, which also account for high-order modes. Each dataset element is injected into detector noise corresponding to the third observing run of the LIGO-Virgo-KAGRA (LVK) collaboration. We identify the Temporal Convolutional Network (TCN) architecture as the overall best performer in terms of training and validation losses and absence of overfitting to data. Comparison of results between datasets shows that the choice of waveform approximant for the creation of a dataset conditions the feature extraction ability of a trained network. Hence, care should be taken when building a dataset for the training of neural networks, as certain approximants may result in better network convergence of evaluation metrics. However, this performance does not necessarily translate to data which is more faithful to numerical relativity simulations. We also apply this network on actual signals from LVK runs, finding that its feature-extracting performance can be effective on real data.

gr-qc↗