Dr. Dimple Panchal

Gamma-ray bursts (GRBs) are one of the most luminous transient astrophysical phenomena in the Universe, with isotropic equivalent energies reaching up to 10^54 ergs. GRB prompt emission spectra typically span the gamma-ray energy range from keV to MeV, exhibiting durations that range from milliseconds to several minutes. GRBs have been detected at cosmological redshifts over 9, offering a window to probe the early universe. Despite several decades of intense observational and theoretical study, fundamental questions regarding the emission mechanisms, progenitor systems, central engines, relativistic jet launching mechanisms, and physical processes governing GRBs remain open challenges. A central yet unsolved problem in GRB research is the classification of these energetic explosions. Different classification schemes based on properties such as duration, fluence, spectral lags, afterglow characteristics, host galaxy types and locations, and other features have been proposed. However, it remains unclear how effectively these classification systems correlate with intrinsically distinct classes of GRB progenitors and central engines. This talk explores how machine learning can revolutionize GRB classification. By analyzing the vast parameter space of GRBs, machine learning algorithms can potentially identify new, physically motivated classes and uncover hidden relationships within the data.