With the development of mobile communication technology, the demand for mobile devices continues to rise. Acoustic devices such as radio frequency (RF) filters and duplexers are widely used in mobile handsets because of their excellent electric performance characteristics. However, the key bottleneck is how to convert a lumped circuit model into the structure parameters of an acoustic resonator for RF circuit designers so that they can apply RF circuit design tools in designing surface acoustic wave (SAW) devices. The neural network (NN) has been widely applied in various science and management areas for its powerful learning and mapping capabilities. In this paper, a method of building a bridge between the lumped equivalent circuit (EC) model and structure parameters of a SAW resonator is proposed. The approach begins with establishing a database that shows the relationship between the values of the lumped EC and corresponding structure parameters of the SAW resonator. A four-layered NN with the back-propagation (BP) algorithm is adopted to determine the relationship between the structure parameters of the SAW resonator and the lumped EC. Then, other input/output pairs are presented to check if the estimated lumped EC matched with original circuit. Finally, as an example, the design of a long term evolution (LTE) transmitter (Tx) filter is developed to demonstrate the proposed approach.