基于粒子群优化的BP网络模型在旱涝预测中的应用

Application of BP Network Model Based on PSO for the Forecast of Drought and Flood

旱涝预测为旱涝灾害防御措施的研究提供重要的依据。运用PSO优化的BP神经网络建立了旱涝预测模型。PSO优化的BP神经网络既发挥了BP神经网络在预测领域的优点,同时又结合了PSO算法全局搜索能力强、收敛速度快等特点进行预测。预测结果表明:辽宁省本溪地区11年实测数据对PSO优化的BP神经网络模型进行验证,PSO优化的BP神经网络模型的预测结果明显好于未经优化的,模型精度得到了一定程度的提高,能满足本溪地区旱涝预测的实际需要。

Drought and flood forecasting for the defense of the measures of droughts and floods provided an important basis for research. BP network model based on PSO established a drought and flood forecasting model, BP network model based on PSO, both played a BP neural network in the area of the advantages of projections. At the same time, PSO algorithm combined the global search capability, fast convergence, and other characteristics to forecast. The forecast result showed that the measured data of Benxi area in past years verified BP network model based on PSO model. BP network model based on PSO model predicted significantly better than without optimization. Model accuracy has been improved to a certain extent to meet the actual needs of drought and flood forecasting in Benxi.