Rain attenuation caused by electromagnetic scattering and absorption is a major design parameter for setting up satellite communication systems operating at frequencies above 10 GHz. In this paper, a method for predicting rain attenuation in terrestrial point-to-point line of sight links at 97 GHz is proposed using previously available experimental data obtained in the south of UK over a period of more than a year. Rainfall rate and percentage of time are used as input data in the proposed prediction method. Results show that our prediction method based on artificial neural networks reveals very good agreement with the experimental data.