基于IACO-BP算法的洪涝灾害应急物资需求预测

Demand predicting of emergency supplies for flood disaster based on IACO-BP algorithm

为了提高洪涝灾害应急物资需求预测的准确性,提出了一种改进蚁群优化BP神经网络智能算法.以受灾转移人数为预测对象,选取受灾人口、最大降雨量、洪水等级、降雨等级、受灾范围、房屋倒塌数、降雨时长和预报水平等洪涝灾害指标为研究因素,获得基于IACO-BP算法的受灾转移人数预测模型.结合库存管理知识间接预测洪涝灾害应急物资需求量.结果表明:IACO-BP算法获得预测值的均方误差比BP和PSO-BP算法获得的均方误差分别小93. 62%和90. 91%; IACO-BP、PSO-BP和BP网络运行时间分别为3、10和33 s; IACO-BP算法具有更高的精度和网络迭代效率.

In order to improve the accuracy of demand prediction of emergency supplies for the flood disaster,an improved BP neural network intelligent algorithm(IACO-BP)by ant colony optimization was proposed.Taking the number of disaster-related migrants as the prediction object,such indicators of flood disaster as disaster-related population,maximum rainfall,flood grade,rainfall grade,disaster area,number of collapsed houses,rainfall duration and forecast level were selected as the research factors to obtain the prediction model for the disaster-related migrants based on the IACO-BP algorithm.Combined with the inventory management knowledge,the demand amount of emergency supplies for flood disaster was indirectly predicted.The results showthat the mean square error of prediction value obtained with the IACO-BP algorithm is lower by 93.62%and 90.91%than that with BP and PSO-BP algorithms,respectively.The network running time of IACO-BP,PSO-BP and BP is 3 s,10 s and 33 s,respectively.The IACO-BP algorithm has higher accuracy and network iteration efficiency.