BP神经网络在建模中的参数优化问题研究  

Study on the Parameter Optimization Problem of BP Neural Network in the Modeling

作　　者：曾晓青 

机构地区：[1]国家气象中心,北京100081

出　　处：《气象》2013年第3期333-339,共7页Meteorological Monthly

基　　金：公益性行业(气象)科研专项(GYHY201106010和GYHY201106034);国家科技支撑计划项目(2009BAC53B02)共同资助

摘　　要：神经网络方法已经在过去很多年中得到了大量研究,特别是基于误差反向传播算法的人工神经网络(简称BP-ANN)在很多天气预报业务上发挥了重要作用。对于BP-ANN训练有这样的一个问题,在同一个样本模型、同样的网络结构和同样的输入参数情况下,每次训练得到的权重和最终的误差结果几乎都是不一样的,有的会很好,有的会较差。在利用BP-ANN建模训练中,希望都寻找到因子模型的局部最优解,使它具有较好的泛化能力。为了提高BP-ANN在业务预报中的建模和预测能力,将对BP-ANN进行改进试验。利用2009—2010年每年5月15日至9月15日的T639模式预测数据和北京地区4个站点的最高温度实况资料作为建模样本数据,对4个站点进行数值模拟试验。通过对4个模型样本的拟合建模试验发现:BP-ANN的随机初始权重场服从高斯分布,或者初始权重场进行多次初始化,或者采用动态的隐层神经元网络结构都能让BP-ANN对样本的拟合命中率有一定的提高。最后选择2011年5月15日至9月15日115天的资料作为预报测试数据,集成3种改进方法于一个BP-ANN中,和未改进前的BP-ANN进行比较,对比后发现优化后的BP-ANN训练出的模型预测得到的验证样本预测命中率要高于未优化的BP-ANN训练出的模型得到的验证样本预测命中率,优化后的BP-ANN具有更好的泛化能力。The neural network approach has been extensively studied in the past years. Especially, the artificial neural network based on error back-propagation algorithm （BP-ANN） has played an important role in weather forecasting. But there is a problem for the BP-ANN training. With the same sample model, the same network structure and the same input parameters, the weight and the final error results from each training are always not the same. Some final error results are good, but some poorer. So in the use of the BP-ANN modeling training, we hope to find out a local optimal solution of the predictor model, helping the models estabish better generalization ability. In order to improve the BP-ANN modeling and forecas- ting capability in forecasting operations, two-year （2009--2011, each year from May 15 to September 15） forecast data from T639 and the maximum observed temperature from four stations in Beijing are used for numerical simulation. It is found by fitting modeling trials on four model samples that by using three improved methods, BP-ANN＇s random weights have a Gaussian distribution or initial weights field are initialized repeatedly, and with hidden layer neurons using dynamic network structure, hit rate from BPANN fitting of the sample has improved to some extent. The last but the most important, taking the data of 115 days （from 15 May to 15 September 2011） as a forecast test data, three improved methods are integrated in BP-ANN. Compared with the BP-ANN before improvement, the result is found to be. hit rate from validation sample using the improved BP-ANN is higher than the non-improved BP-ANN, and the optimized BP-ANN has better generalization ability.

关 键 词：BP-神经网络 高斯分布 权重初始场 动态的神经元 泛化能力 

分 类 号：P456[天文地球—大气科学及气象学]