Forecasting of solar irradiance will become a major issue in the future integration of solar energy resources into existing energy supply structures. As far as short-term time horizons (up to 2h) are concerned, satellite data are a high quality source for information about radiation with excellent temporal and spatial resolution. Due to the strong impact of cloudiness on surface irradiance the description of the temporal development of the cloud situation is essential for irradiance forecasting. As a measure of cloudiness, cloud index images according to the Heliosat method are calculated from METEOSAT images. To predict the future cloud index image from a sequence of subsequent images different approaches were applied. A statistical method was used to derive motion vector fields from two consecutive images. The future image then is determined by applying the calculated motion vector field to the actual image. As a completely different approach Neural Networks in combination with Principal Component Analysis were used to describe the development of the cloud structure. The accuracy of the predicted cloud images was analysed and compared for both methods. Motion vector fields showed a superior performance and were chosen for further evaluations. Finally, solar surface irradiance was derived from the predicted cloud index images with the Heliosat method and compared to ground measurements.