The present paper mainly deals with the prediction of blast-induced ground vibration level at Tourah Mine in Egypt. The safe charge of explosive and peak particle velocity (PPV) were recorded for 79 blast events (79 blast data sets) at various distances. These datasets were used and analyzed by the widely used vibration predictors. From the six predictors, vibration levels were calculated and compared with new monitored 15 blast data sets. Again, the same data sets were used to validate and test the three-layer feed-forward back-propagation neural network to predict the PPV. Different propagations equations were derived by using the shapes of the selected predictors formulae. It is found that among all the predictors, ANN provides very near prediction with high degree of correlation.