Abstract: This study experimentally investigates the active control of a Mach 1.5 round jet using multiple steady radial microjets to enhance jet mixing. The control parameters include the pressure ratio of the main jet exit, the mass flow ratio of microjet to main jet, and the number of microjets. The effect of these parameters on supersonic jet mixing is revealed through experimental results. Results indicate that as the pressure ratio increases, the control performance of the supersonic jet gradually decreases from under- to over-expanded conditions. There is a complex nonlinear relationship between the mass flow ratio and the core length of the supersonic jet. Besides, increasing the number of microjets does not enhance the supersonic jet mixing. While the control effect decreases with the increase of the pressure ratio of the main jet. For pressure ratios of 2.50, 3.00, 3.67, 5.00, and 7.00, the optimal core length can be reduced by up to 62%, 60%, 53%, 46%, and 8%, respectively. Two prediction models are proposed to link the control parameters with the control targets based on the Taylor expansion and BP neural network algorithm. Both models exhibit better prediction ability near the optimal value. When predictions deviate from the optimal region, the BP neural network yields more accurate estimates of the supersonic jet core length, with a prediction error only 6% of that based on the Taylor expansion method.