基于支持向量机的洪水预报模型初

用传统的机器学习方法进行洪水预报建模存在泛化能力难以保障，训练速度慢等一些困难。对统计学习理论和支持向量机的基本内容和核心思想进行了简要的介绍，探讨了基于支持向量机的洪水预报模型的建模方法。通过实例中的应用，该模型显示了泛化能力强，训练速度快，便于建模等优点，有良好的应用前景。

Preliminary Discussion on Flood Forecast Model Based on Support Vector Machine

Traditional learning machine methods like artificial neural networks have the disadvantages of slow training speed, low generalization capability etc. The highlights of statistical learning theory (SLT), the principle and the crucial elements of support vector machine (SVM) were introduced, and the method for flood forecast modeling based on support vector machine was discussed. In case study, the flood forecast model based on SVM exhibited its properties of high generalization capability, fast training, and easy modeling.