Mapping ocean sediments by RBF networks

Estimation of ocean-sediment properties by sparse noisy measurements using generalized Radial Basis Function networks is proposed. Given a set of scattered data points, an RBF network is able to generate a continuous smooth approximation for sediment properties as a function of the x-y-z position, where z is the sediment depth. Advantages and disadvantages of the method are discussed, from both a physical and a computational viewpoint. An example using sediment density data obtained by sparse core measurements and different configurations of RBF networks is presented