基于自然正交展开的神经网络长期预报模型

对月降水量的前期500hPa高度场、海温场相关预报因子进行E0F展开，并取其中与预报量相关程度较高的主成分，结合人工神经网络技术，建立了一种新的短期气候预测模型。将这种新的预报模型与同样根据这些预报因子建立的回归预报模型进行了对比分析。结果表明，这种新的短期气候预测模型由于集中了众多预报因子的预报信息，并有效地利用了神经网络方法的非线性映射能力，因此比传统预报方法的预报精度显著提高，并且稳定性好，具有很好的应用前景。

Long-term prediction model of neural network based on empirical orthogonal functions

Upon using an artificial neural network (ANN) a new short term climate forecast model with the monthly mean rainfall in June in the north of Guangxi as predictand is developed by means of making empirical orthogonal functions (EOF) to the predictors of previous 500hPa height and sea surface temperatures (SSTs), and selecting the high relative principal components. Predictive capability between the new model and linear regression model for the same predictors is discussed based on the independent samples. Evidence suggests that the prognostic ability of the new model with high stability is superior to that of a traditional scheme, due to its condensing the more forecasting information, efficiently utilizing ANN non linear mapping.