论文部分内容阅读
降雨预报是水文预报的重要环节,提高其准确性是进行洪水、径流等预报的前提。针对目前预测方法中存在的易落入局部极小值、收敛速度慢和收敛对初值敏感等问题,将多种群遗传算法(MPGA)与反向传播(BP)神经网络模型相结合,提出了一种适用于降雨预报的多种群遗传神经网络模型(MPGA-BP)。实例计算结果表明,该模型具有良好的预报性能和泛化能力,为降雨准确预测提供了有力的技术支持。
Rainfall forecasting is an important part of hydrological forecasting. Improving its accuracy is the prerequisite for forecasting floods and runoffs. Aiming at the problems such as the local minimum, the slow convergence and the sensitivity to the initial value of convergence in the current prediction methods, the multi-population genetic algorithm (MPGA) and back propagation (BP) neural network model are proposed A Multi-population Genetic Neural Network Model Suitable for Rainfall Prediction (MPGA-BP). The calculated results show that the model has good prediction performance and generalization ability, which provides powerful technical support for accurate rainfall forecasting.