Many DPSs work in a large-scale operation range and the operation range consists of several different ranges, in which the processes are coupled complex energy transfer and featured by the a nonlinear DPS. Also, the dynamics in different range and energy transfer between different ranges are quite different and complex. All these factors increase the modeling difficulty of the DPS. To address this issue, a spatiotemporal model is proposed using multi-model idea, namely multi-kernel extraction, to reconstruct dynamics of this kind of processes. First, a multi-kernel global SBF construction method is developed to extract the global spatial features of the DPS. For each local range, it constructs the SBF to represent the energy exchange on space. To reflect the global spatial feature, these SBFs are integrated by using Gaussian mixture strategy to form a global SBF. Then, the temporal dynamics can be obtained by projecting the spatiotemporal data on this global spatial function. Integrating the global SBF and temporal model, the spatiotemporal model is constructed for the DPS with large-scale operation range, using theoretical analysis and experiment, modeling effect of the proposed model is verified.