In order to predict world uranium resource price, an empirical mode decomposition(EMD), phase space reconstruction(PSR) based extreme learning machine(ELM) ensemble learning paradigm is proposed. The original uranium resource price series are first decomposed into a finite number of independent intrinsic mode functions(IMFs), with different frequencies. Then the IMFs are composed into three sub-series based on the fine-to-coarse reconstruction rule, and different
ELM models are used to model based on phase space reconstruction and forecast the three sub-series respectively according to the intrinsic characteristic time scales. Finally, these forecasting results are combined to output the ultimate forecasting result. The proposed model is applied to uranium resource price tendency forecasting example, and the simulation results show that the forecasting performance of the hybrid model outperforms the single ELM and RBF ahead forecasting.