Ground vibration is one of the most important undesirable effects induced by blasting operations in the mining or tunneling projects. Hence, developing a precise model for prediction of ground vibration would be much beneficial to control environmental issues of blasting. The present study proposes a new hybrid machine learning (ML) technique, i.e., autonomous groups particles swarm optimization (AGPSO)–extreme learning machine (ELM) to predict ground vibration resulting from blasting. In fact, AGPSO–ELM model is a modified version of PSO–ELM that can solve problems in a way with higher prediction performance. For comparison purposes, PSO–ELM, minimax probability machine regression, least square–support vector machine and Gaussian process regression models were also proposed to estimate ground vibration. The said ML models were trained and tested based on a database comprising of 102 datasets collected from a quarry site in Malaysia. In the modeling of ML techniques, six input parameters were considered: burden to spacing ratio, maximum charge per delay, stemming, distance from the blasting-face, powder factor and hole depth. The results of ML techniques were evaluated in both stages of training and testing based on five fitness parameters criteria. Considering results of both training and testing datasets, AGPSO–ELM model was able to provide higher prediction performance for PPV prediction. Root-mean-square error values of (0.08 and 0.08) and coefficient of determination values of (0.92 and 0.90) were obtained, respectively, for training and testing datasets of AGPSO–ELM model which revealed that the new hybrid model is capable enough to forecast ground vibration induced by blasting. The newly proposed model can be used in other fields of science and engineering in order to get high accuracy level of prediction.