ORIGINAL ARTICLE Blast-induced air and ground vibration prediction: a particle swarm optimization-based artiﬁcial neural network approach Mohsen Hajihassani 1 • Danial Jahed Armaghani 2 • Masoud Monjezi 3 • Edy Tonnizam Mohamad 2 • Aminaton Marto 2 Received: 28 January 2014 / Accepted: 1 March 2015 Ó Springer-Verlag Berlin Heidelberg 2015 Abstract Mines, quarries, and construction sites face environmental damages due to blasting environmental impacts such as ground vibration and air overpressure. These phenomena may cause damage to structures, groundwater, and ecology of the nearby area. Several empirical predictors have been proposed by various scholars to estimate ground vibration and air overpressure, but these methods are inapplicable in many conditions. However, prediction of ground vibration and air over- pressure is complicated as a consequence of the fact that a large number of inﬂuential parameters are involved. In this study, a hybrid model of an artiﬁcial neural network and a particle swarm optimization algorithm was implemented to predict ground vibration and air overpressure induced by blasting. To develop this model, 88 datasets including the parameters with the greatest inﬂuence on ground vibration and air overpressure were collected from a granite quarry site in Malaysia. The results obtained by the proposed model were compared with the measured values as well as with the results of empirical predictors. The results indicate that the proposed model is an applicable and accurate tool to predict ground vibration and air overpressure induced by blasting. Keywords Vibration blasting impacts  Ground vibration  Air overpressure  Artiﬁcial neural network  Particle swarm optimization Introduction In rock quarry blasting, only 20–30 % of the energy pro- duced by explosives is utilized to fragment and displace the rock mass. The rest of the energy is wasted and produces undesirable environmental impacts such as ground vibra- tion, air overpressure (AOp), ﬂyrock, and back-break (Se- garra et al. 2010; Monjezi et al. 2012; Raina et al. 2014; Jahed Armaghani et al. 2014; Marto et al. 2014; Ebrahimi et al. 2015). Various empirical predictors have been established to predict ground vibration and AOp induced by blasting. However, such approaches only consider limited numbers of parameters inﬂuencing ground vibra- tion and AOp, although these phenomena are also affected by other controllable or uncontrollable parameters such as blast geometry and geological conditions (Douglas 1989; Singh and Singh 2005). As a result, in many cases, em- pirical methods are not accurate enough, while prediction of the ground vibration and AOp with a high degree of accuracy is important to estimate the blasting safety area. In addition to the empirical equations, the use of sta- tistical methods such as simple and multiple regression & Masoud Monjezi monjezi@modares.ac.ir Mohsen Hajihassani mohsen_hajihassani@yahoo.com Danial Jahed Armaghani danialarmaghani@yahoo.com Edy Tonnizam Mohamad edy@utm.my Aminaton Marto aminaton@utm.my 1 Construction Research Alliance, Universiti Teknologi Malaysia, UTM Skudai, 81310 Johor, Malaysia 2 Department of Geotechnics and Transportation, Faculty of Civil Engineering, Universiti Teknologi Malaysia, UTM Skudai, 81310 Johor, Malaysia 3 Department of Mining, Tarbiat Modares University, 14115-143 Tehran, Iran 123 Environ Earth Sci DOI 10.1007/s12665-015-4274-1