摘要
文中分析了常用的水体质量评价模型的缺陷,提出了基于序列二次规划算法SQP(Sequentialquadraticprogramming)的投影寻踪评价模型,并利用多项式插值的方法进行水质分类,取得了符合客观实际的评价结果。某水源地地下水质量评价结果表明:用投影寻踪方法可以揭示高维数据的结构特征;所建立的评价模型不仅简单、直观和易于理解,而且结果合理。为水源地的保护和合理利用提供了决策依据。
In this paper, limitations of the traditional models of water quality evaluation are analyzed, and a projection pursuit evaluation model based on sequential quadratic programming algorithms is set forth. Classification of water quality is carried out using a polynomial interpolation method and the results are in a good agreement with the practical situations. The results show that using projection pursuit method can disclose the structure features of the high dimensional data. The evaluation model is simple and easy to understand. The results are valid and provide a decision basis for reasonable protection and utilization of wellfields.
出处
《水文地质工程地质》
CAS
CSCD
北大核心
2005年第5期9-12,共4页
Hydrogeology & Engineering Geology
基金
国家自然科学基金(40202027)
霍英东教育基金(91079)
关键词
序列二次规划算法
投影寻踪
地下水质量评价
Sequential Quadratic Programming Algorithms
projection pursuit
groundwater quality evaluation
