Gravitational wave lensing, particularly microlensing by compact dark matter (DM), offers a unique avenue to probe the nature of dark matter. However, conventional detection methods are often computationally expensive, inefficient, and sensitive to waveform systematics. In this work, we introduce the Wavelet Convolution Detector (WCD), a deep learning framework specifically designed to identify wave-optics diffraction patterns imprinted in gravitationally lensed signals. The WCD integrates multi-scale wavelet analysis within residual convolutional blocks to efficiently extract time-frequency interference structures, and is trained on a realistically generated dataset incorporating compact DM mass functions and astrophysical lensing probabilities. This work is the first machine learning-based approach capable of identifying such wave-optics signatures in lensed gravitational waves. Tested on simulated binary black hole events, the model achieves 92.2\% accuracy (AUC=0.965), with performance rising to AUC$\sim$0.99 at high SNR. Crucially, it maintains high discriminative power across a wide range of lens masses without retraining, demonstrating particular strength in the low-impact-parameter and high-lens-mass regimes where wave-optics effects are most pronounced. Compared to Bayesian inference, the WCD provides orders-of-magnitude faster inference, making it a scalable and efficient tool for discovering compact DM through lensed gravitational waves in the era of third-generation detectors.
The Small Magellanic Cloud (SMC) is the nearest low-metallicity dwarf galaxy. Its proximity and low reddening has enabled us to detect its Wolf-Rayet (WR) star population with 12 known objects. Quantitative spectroscopy of the stars revealed half of these WR stars to be strong sources of He ii ionizing flux, but the average metallicity of the SMC is below where WR bumps are usually detected in integrated galaxy spectra showing nebular He ii emission. Utilizing the Local Volume Mapper (LVM), we investigate regions around the six SMC WN3h stars, whose winds are thin enough to avoid He recombination and allow photons with > 54 eV to escape. Focusing on He ii 4686 Å, we show that the broad stellar wind component, the strongest optical diagnostic of the WN3h stars, is diluted within 24 pc in the integrated light from LVM, making the WR stars hard to detect in low-metallicity integrated regions. In addition, we compare the He ii ionizing flux from LVM with the values inferred from the stellar atmosphere code PoWR and find that the nebular emission around them only in some cases reflects the high amounts emitted by the stars. We conclude that early-type WN stars with comparably weak winds are viable sources to produce the observed He ii ionizing flux in low-metallicity galaxies. The easy dilution of the stellar signatures can explain the rareness of WR bump detections at 12 + log O/H < 8.0, while at the same time providing major candidates for the observed excess of nebular He ii emission. This constitutes a challenge for population synthesis models across all redshifts as the evolutionary path towards this observed WR population at low metallicity remains enigmatic.
this https URL 35 pages, 6 figures, 1 table, 98 references
this https URL 23 pages, 3 figures, 101 references