Abstarct: The goal of the optimal blasting pattern is to achieve the appropriate degree of fragmentation and reduce environmental effects such as ground vibration, rock-falls, back-break and air explosions. In the meantime, ground vibration has particular importance. In order to achieve a suitable blasting pattern with the least amount of vibration, the design of the explosion pattern is done by combining technical knowledge, previous experiences and data of similar designs. It then moves to an optimal boundary for economic and environmental priorities. According to the final design of the Sungon copper mine and the increase in its extractable reserves, and as a result of the development of the pit, blasting operations with different structural conditions are carried out at very close distances from the structures of office, residential, and industrial buildings. The lack of certainty in the earth has challenged the design and planning of blasting projects. To predict and manage this lack of certainty, human intelligence is incapable of predicting all possible states of a phenomenon. The use of artificial intelligence, and especially its independent subcategory, soft computing, is essential as a reliable and fast tool. In this thesis, with a different perspective than other researches, blasting patterns, according to parameters such as diameter of the hole, burden and spacing of the holes, height of the hole and the amount of explosive compared to the criterion of ground vibration rate with field observation and use of soft computing and decision making models have been evaluated at the Sungon copper mine, and the most appropriate pattern for reducing ground vibration has been identified. In the first step, Group Method of Data Handling-Type Neural Network is used as one of the most practical optimization algorithms to solve complicated and uncertain problems in this modeling. In addition, baxsed on expertise and experience of experts, the degree of ground vibration produced by each blasting is qualitatively classified into four different ranges of very high, high, normal and low in the form of unacceptable (very high and High) and acceptable (normal and low) clusters. A model with an accuracy of 97.2% and an error of 2.8% in determining the classification pattern for training data and an accuracy of 87.5% and an error of 12.5% in determining the classification pattern for Test data was selected as an extended classification model. baxsed on the results obtained from the analyses, the developed model has a high flexibility and ability in the binary prediction of blasting patterns with an acceptable vibration magnitude. In the next step, a combination of the imperialist competitive algorithm and k-means algorithm was used for clustering the measured data. In the second step, one of the multi-criteria decision making methods namely the TOPSIS (Technique for Order Performance by Similarity to Ideal Solution) was used for the final ranking. Finally, after evaluating and ranking the studied patterns, the blasting pattern No. 27 was selected. This pattern was used with the properties, including the hole diameter of 16.5 cm, number of hole of 13, spacing of 4 m, burden of 3 m and ammonium nitrate fuel oil of 1100 Kg as the most appropriate blasting pattern leading to the minimum ground vibration and reduction of damages to the environment and structures constructed around the mine.