A Method for Land Surveying Sampling Optimization Strategy

摘要

At present, how to select a limited but representativesample dataset from the existing land information database toguide the new round of land survey and assessment sampling is acritical issue for land sampling strategy study. As a case study todetermine and analyze the sample capacity and sample spatiallocation of land survey sampling for the study area, PanyuDistrict in Guangzhou, the paper developed the strategy based onthe combination of classical sampling technique and geographicalmodel under a certain confidence level and estimation accuracyrequirement, and the performance of the sampling strategy wasthen evaluated by the Global Geary's C and the Quick-BP neuralnetwork model respectively. The test result showed that,compared with traditional c-means clustering sampling method,the accuracy of the sampling prediction based on local Moranindex spatial clustering sampling method was increased by13.57% which abstracted better the land information in thedatabase.