基于SVR的指标规范值的水资源可持续利用评价模型

针对现有的水资源可持续利用评价的回归支持向量机模型（LS-SVR）的不足，提出了水资源系统指标参照值和指标规范变换式的设置原则和方法，使不同的水资源指标经规范变换后皆“等效”于某一个规范指标，进而建立适用于任意m项指标规范值表示的回归支持向量机水资源可持续利用评价模型（NV-LS-SVR）。将NV-LS-SVR模型应用于汉中盆地和淮河流域12个地区水资源可持续利用评价中，评价结果与BP神经网络的评价结果基本一致，验证了该模型的可行性和实用性，为水资源可持续利用评价提供了参考。

Evaluation Model for Sustainable Utilization of Water Resources Based on Normalized Index Values of Support Vector Regression

Aiming at the defects of the existing mode of support vector regression.(LS-SVR) for the evaluation of sustainable utilization of water resources, this paper proposed design principles and methods of reference values and the normalized transformation forms for all indexes of water resources systems. On the basis of normalized transformations for indexes of water resources systems, the normalized different indexes of water resources systems were equivalent to a certain normalized index. Furthermore, the evaluation model based support vector regression(NV-LS-SVR) ,which is suitable for any m normalized indexes values of sustainable utilization of water resources, was established. Then, the NV-LS-SVR model was applied to assess the sustainable utilization of water resources in the 12 areas of Hanzhong basin and Huaihai River Basin. Feasibility and practicability of this model were verified due to the basic consistency of the evaluation results between the model and BP artificial neural networks. The model provides reference for the evaluation of sustainable utilization of water resources.