基于属性识别模型的退耕地土壤肥力综合评价

Comprehensive Evaluation of Soil Fertility Abandoned Cropland Based on Attribute Recognition Model

运用基于熵权的属性识别模型,对延河流域不同退耕年限有机质、全氮、全磷、有效氮、速效磷、速效钾和pH值等7项土壤物理和化学指标进行综合评价。结果表明:退耕初期,土壤肥力指标之间权重相差较大,随着退耕年限的增加,各土壤肥力指标对土壤肥力的影响逐渐趋于一致;较退耕初期,退耕地1-5年和6-10年时,土壤肥力都有所下降,随着退耕年限的延长,土壤肥力逐渐恢复,但至退耕25-30年时,土壤肥力仍未恢复到退耕初期的水平;总体上延河流域退耕地总体肥力水平较低,提高土壤肥力水平势在必行。属性识别模型评价方法在很大程度上减小了主观因素的影响,评价结果直观实用,能为土壤肥力综合评价提供有力的技术支撑。

Attribute recognition model based on entropy weight was used to evaluate the soil fertility of different time of abandoned cropland in Yanhe watershed,which contained 7 physical and chemical indexes,including soil organic matter,total nitrogen,total phosphorus,available nitrogen,available phosphorus,available potassium and pH value etc.The results showed that： In early abandoned cropland,the entropy weight of soil fertility indexes had large difference.With prolonged,the impact of the entropy weight had gradual convergence on soil fertility.Relatively early abandoned cropland,the soil fertility had declined in 1-5 year and 6-10 year.With the length of abandoned cropland,soil fertility gradually restored.But by returning farmland to 25-30 year,the soil fertility had not been restored to the level of the early abandoned cropland.In general,the soil fertility of abandoned cropland is at lower level in Yanhe watershed,and to improve it is imperative.The method of attribute recognition model can reduce the impact of subjective factors in large extent.This method of results of visual and practical can provide strong technical support for comprehensive evaluation of soil fertility.