Dynamic system simulations require relating the inputs to the multivariate output which can be a function of time space coordinates. In this work, we propose a methodology for the metamodeling of dynamic simulation models via Multivariate Adaptive Regression Splines (MARS). To handle incomplete output processes, where the simulation model does not produce an output in some steps due to missing inputs, we have devised a two-stage metamodeling scheme. The methodology is demonstrated on a dynamic radar simulation model. The prediction performance of the resulting metamodel is tested with four different sampling techniques (i.e., designs) and 16 sample sizes. We also investigate the effect of alternative coordinate system representations on the metamodeling performance. The results suggest that MARS is an effective method for metamodeling dynamic simulations, particularly, when expert judgment is not readily available. Results also show that there are interactions between the coordinate systems and sampling techniques, and some design-representation-size combinations are very promising in the metamodeling of radar simulations. (C) 2016 International Association for Mathematics and Computers in Simulation (IMACS). Published by Elsevier B.V. All rights reserved.