Blasting is the controlled use of explosives to excavate, break down or remove rock in construction projects and mining industrials. Air overpressure or airblast is one of the undesirable effects of blasting operation that affects the surrounding environment and may cause damage to adjacent structures. Blasting designers concern about the airblast induced by blasting as the adverse and unintended effects of explosive usage on the surrounding areas. Prediction of airblast is a significant part of blasting damage assessment. Several methods were developed based on the empirical relationships obtained from field studies to predict blasting induced airblast. Nevertheless, these methods usually predict with considerable error due to the fact that the methods do not consider effective parameters on airblast phenomena. This paper presents a new method based on artificial neural networks to predict blastinginduced airblast. Thirty eight blasting operations were monitored from two granite quarry sites in Malaysia, and the obtained data were used to create an artificial neural network model to predict airblast induced by blasting. The results indicate that this method is able to predict blasting-induced airblast with reasonable accuracy.