Artificial intelligent is the latest approach to geophysical data inversion which is used to estimate the size of anomaly and determine the depth and geometry of basement. In this method, the relationship between the data and model space is determined by deep learning algorithms. To this end, the learning network model is first designed and then trained. It should be noted that, a large amount of synthetic data is needed to train the model. In the end, the trained model is used to predict the real data. In this way, the deep neural network method was used to the inversion of magnetic data. For the sake of the deep neural network (DNN) training, 200,000 synthetic data were produced and then the DNN model was used to predict the depth of basement on a magnetic data profile in the Bishop area. Meantime, the result was acceptable. To round of the discussion in this article, the DNN model was used to predict the depth of sedimentary basin in the Central Iran, which the results are correlated with the seismic interpretation.