The invention discloses a quantitative rainfall prediction method based on radar reflectivity extrapolation and relates to the technical field of atmospheric science. The method comprises the steps: S1, collecting radar base data for prediction and generating a radar echo reflectivity image through a reflectivity factor in the radar base data; S2, solving a pre-constructed optical flow equation based on the radar echo reflectivity image to obtain a motion field of radar echo; S3, identifying a strong convection region in the motion field of the radar echo by using a pre-constructed identification model and tracking and positioning a strong convection region; S4, constructing a radar echo extrapolation model, training the radar echo extrapolation model by using the strong convection region,and predicting radar echo data; and S5, converting the radar echo data by using a trained quantitative precipitation neural network prediction model to obtain predicted precipitation. The method hasthe advantages of simplicity and high prediction accuracy.