PPE模型在农业生产气候敏感性等级评价中的应用研究

Applying RAGA-based PPE model to evaluate agricultural production sensitivity to climate change

目前的农业生产气候敏感性综合评价多采用模糊聚类分析与模糊综合评判以及层次分析等方法,其权重矩阵易受人为干扰,使分类与评价参杂人为因素。本文将高维降维技术———投影寻踪评价模型(PPE)应用于农业生产气候敏感性评价,利用改进的加速遗传算法(RAGA)优化投影方向,将多维数据指标转换到低维子空间。通过寻求最优投影方向及投影函数值实现对农业生产气候敏感性的分类与等级评价,避免了人为赋权的干扰,克服了常规投影寻踪方法计算量大、编程实现困难的缺点,取得了较好效果。采用投影寻踪模型进行农业生产气候敏感性综合评价,可为农业生产气候敏感性评价研究提供新方法。

The research on classification and evaluation of agricultural production sensitivity to climate change is often based on fuzzy theory or analytical hierarchy process（AHP）,which has an inevitable problem about weight matrix from experts,and its results may also be influenced by artificial factors.A new technique of falling dimension named projection pursuit is applied to agricultural production sensitivity study through using improved real-coding-based accelerating genetic algorithm to optimize the projection direction.Thus,it can transfer multi-dimension data into one dimension data,through searching for the optimum projection direction to realize agricultural sensitivity classification and its grade evaluation.The method can avoid artificial disturb,and overcome the shortcomings of large computation amount and difficulty of computer programming in traditional projection pursuit method,and acquire preferably effect.A projection pursuit model is presented for comprehensive evaluation of agricultural production sensitivity to climate.Thus,it provides a new method to the research on agricultural production sensitivity classification and grade evaluation.