耕地变化空间抽样调查方案的精度与效率分析

Accuracy and efficiency of different spatial sampling schemes for cropland change monitoring

已有研究表明,利用遥感空间抽样方法来监测耕地变化是可行的,如何选择最佳空间抽样方案以提高效率、节省费用则是其需解决的核心问题。采用3种抽样方法(简单随机抽样、分层抽样、系统抽样)与2种抽样框(规则抽样框、不规则抽样框),设计了6种不同组合的遥感空间抽样方案进行试验;根据不同抽样框与平均每样本调查费用大小的关系,分析了不同耕地变化遥感空间抽样调查方案的精度与效率,并以北京市顺义区为例进行了试验验证,结果表明:采用分层-不规则框进行耕地变化遥感空间抽样调查具有较高的精度和效率。进一步的敏感性分析表明,分层-不规则框抽样调查方案在耕地变化程度不同的区域均能获得较高的估算精度,耕地变化程度对抽样估算精度的影响较小。而且它对遥感影像的解译精度要求较低,当遥感影像的解译精度在80%以上时,该抽样方案所获得的耕地变化抽样估算精度可以稳定在90%以上。从而提高了该抽样调查方案在不同地区的广泛适应性。

Previous researches have proved the feasibility of monitoring cropland changes using spatial sampling methods.However,how to improve efficiency and reduce cost by designing an optimal spatial sampling scheme is a key issue.Six sampling schemes were designed by combining three sampling methods（simple random sampling,stratified sampling and systematic sampling） with two sampling frames（regular frame and irregular frame） and their accuracy and efficiency were tested,based on the relationship between the average survey cost per sample and the practice factor of sampling frame.A case study in Shunyi District,Beijing,was carried out to test the validity of the optimal spatial sampling scheme.Results indicated that the stratified sampling with irregular frame scheme could achieve high sampling accuracy and efficiency for cropland change monitoring.Further sensitivity analysis showed that this scheme could be applied to different regions in despite of the variation of cropland change magnitude.The degree of cropland change has little effect on the estimation accuracy of sampling.Moreover,the sampling accuracy of this scheme is insensitive to remote sensing image interpretation accuracy.When the later is above 80%,the former remains above 90% steadily.This extends the application flexibility of the stratified sampling with irregular frame for cropland change monitoring.