摘要
针对以往土壤肥力质量综合评价方法存在人为权重赋值误差,以及简便计算等方面的不足的问题,提出了投影寻踪等级评价模型对土壤肥力质量进行综合评价。投影寻踪等级评价模型方法依据标准样本自身的数据特性寻求最佳投影方向,通过最佳投影方向与评价指标的线性投影得到投影指标值,依据投影指标值对样本进行统一评价和分类,并利用最佳投影方向判断各评价指标对综合评价目标的贡献大小。模型日的应用较好地对西藏米拉山区不同海拔土壤肥力质量进行评定,并对单一指标对土壤肥力质量贡献大小进行了分析,其结果将有助于西藏土壤的合理利用,为今后的土地利用分析决策提供重要参考。
In this study,projection pursuit grade evaluation(or PPE for short) model was applied in soil fertility quality assessment.Comparing with traditional assessments,this method had advantages of efficient simulation and non-human factors.By projecting high dimensional data to low dimensional space and then finding the optimum projection vector of data in one-dimensional space,projection pursuit was an effective method in comprehensive and multi-index evaluation.The projection assessment indices' contributions towards the comprehensive assessment objective were determined by the best direction of projection.Taking vertical distributional character of in nutritional composition in soil in Mila Mountains as the research object,we assessed local soil fertility quality and analyzed the contribution values of soil fertility quality indices with PPE approach.Through analyses,we found that the soil fertility quality in study area was better than the CK with the time going on.The valuation results,which being more precise and reasonable,were helpful for the reasonable utility to the soil in Tibet,and provided an important reference for analysis and decision in future.
出处
《土壤通报》
CAS
CSCD
北大核心
2011年第3期518-522,共5页
Chinese Journal of Soil Science
基金
国家科技攻关计划重大专项"生态农业技术体系研究与示范"专题"中国森林生态网络体系‘线’的研究与示范(2002BA516A-16)"
西藏自治区科技厅基金项目"鬼臼毒素两个关键酶基因的克隆"资助
关键词
投影寻踪
实码加速遗传算法
土壤肥力质量
评价
Projection pursuit(PP)
Projection pursuit grade evaluation model(PPE)
Real Coding Based Accelerating Genetic Algorithm(RAGA)
Soil fertility quality
Assessment