<p>Mine disasters occur frequently during deep coal-mining operations in China; however, current monitoring and early-warning methods for rock bursts remain insufficient. To address this, this paper proposes an early-warning method for rock bursts based on the fractal dimension of microseismic energy. Through the establishment of an integral expression relationship between microseismic energy and fractal dimension, the spatio-temporal distribution characteristics of microseismic events are analyzed, revealing the precursor patterns of rock bursts. The results indicate that prior to the occurrence of a rock burst, parameters such as microseismic energy, event frequency, and fractal dimension all exhibit significant precursor characteristics. Furthermore, the temporal evolution of the fractal dimension can be divided into four distinct stages: stable, early-warning, deformation, and re-stabilization periods. This method provides a new approach for the quantitative early warning of rock bursts.</p>