Over the last decade, using graphics processing units (GPUs) for computations has given a significant boost to varied scientific fields and even to our everyday lives. An emergent branch is modeling, parameter identification, simulation, and control of solid oxide fuel cells (SOFCs). SOFCs convert chemical energy into electricity with a high degree of efficiency and in a low-waste manner. Models for SOFC temperature are based on partial-differential equations, which are usually discretized with respect to space and time into algebraic equations. A disadvantage of this technique is the lack of flexibility, which is unsuitable for control or for guaranteed prevention of overheating that can accelerate stack degradation. In our past publications, it has been shown that it is possible to arrive at dynamic SOFC models consisting of a set of ordinary differential equations which are cooperative. In this contribution, we extend the GPU-based parameter identification technique we used for a reduced distributed heating system to cover cooperative SOFC models with the help of interval analysis to deal with uncertainty. Additionally, we show how the amount of data for controlled and measured system inputs and outputs can be reduced by using interval Bézier curves.