Abstarct: One of the most important parameters in transportation studies and management is the number of trips between origin and destination, which is shown using the travel matrix. Because preparing a trip matrix requires a lot of time and money, in recent years, several methods have been developed and used to estimate the travel matrix. The aim of this study is to use artificial intelligence to provide a suitable estimate of the travel matrix using the population living in the areas of origin and destination and the total area of land use infrastructure located in each area. For this purpose, previous researches were reviewed and it was concluded that a research similar to the subject of this research can be completed using artificial intelligence. After that, the data related to the population census as well as the total area of land use infrastructure in the municipal areas in the cities of Mashhad and Isfahan were collected. Using methods 1) MATLAB 2013 software toolbox neural network 2) Multilxayer neural network without limitation of validation data 3) Neural network with noise data removal 4) Feed-forward neural network were used to estimate the travel matrix. In this study, the most appropriate results were obtained when using normalized data in a multilxayer neural network without limitation of validation data.