Revealing hidden repeaters in the CHIME/FRB catalogue: semisupervised insights into the fast radio burst population

Abstract

Fast radio bursts (FRBs) are millisecond-duration extragalactic transients, observationally classified as repeaters or non-repeaters. This classification may be biased, as some apparently non-repeating sources could simply have undetected subsequent bursts. To address this, we develop a semisupervised learning framework to identify distinguishing features of repeaters using primary observational parameters from the Blinkverse data base, which draws from the CHIME/FRB catalogues. The framework combines labelled data (known repeaters and confidently classified non-repeaters) with unlabelled sources previously flagged as non-repeaters but exhibiting repeater-like characteristics. We employ uniform manifold approximation and projection with a nearest neighbour scheme to select potential candidates, followed by semisupervised 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.