The aim of this research is to investigate the use of the modern prediction algorithms in seabed mapping. These prediction algorithms can be used in enhancing the quality of the measured bathymetric data to help in filtering the measured data and excluding noise from actual data to ensure higher seabed mapping accuracy for more secure navigation. The work involves the development of a general purpose sonar simulation platform to generate the required data for testing the different prediction algorithms. The simulation platform consists of a seabed simulator and an interferometric sonar simulator for bathymetric measurements. Two methods of building the seabed simulator have been investigated and applied; the fractal geometry based method and the random generator based method. The interferometric sonar simulator is based on SAS (Synthetic Aperture Sonar) which is a widely accepted modern technology. The predictors investigated in this work are based on KNN (K Nearest Neighbours) and dynamic ANN (Artificial Neural Networks). Both dynamic feedforward and dynamic recurrent networks are investigated. The comparison between the performances of these different predictors reveals that dynamic recurrent networks outperform the other types of predictors and the Nonlinear AutoRegressive eXogenous (NARX) Neural Network is the best.