一种基于MPS和ISOMAP的空间数据重建方法

A Reconstruction Method of Spatial Data Using MPS and ISOMAP

在空间数据重建过程中,条件数据对重建结果影响较大,在仅有少量条件数据的情况下,重建结果常常出现较多的不确定性,此时适合采用不确定性插值方法重建空间数据.作为目前不确定性插值的主流方法之一,多点信息统计法(multiple-point statistics,MPS)可以从训练图像提取模式的本质特征,然后将这些特征复制到待模拟区域.由于传统采用线性降维的MPS方法无法有效处理非线性数据,因此将等距特征映射(isometric mapping,ISOMAP)应用到MPS方法,以实现对非线性数据的降维.提出基于MPS和ISOMAP的空间数据重建方法,通过模式库构建、模式降维、模式分类、模式提取等步骤能够较为准确地重构出未知的空间数据,为MPS处理非线性空间数据提供了新思路.实验结果表明:该方法所重建的空间数据具有与训练图像相似的结构特征.

Conditional data influence the reconstructed results greatly in the reconstruction of spatialdata.Reconstructed results often show a number of uncertainties when only sparse conditional dataare available,so it is suitable to use indefinite interpolation to reconstruct spatial data.As one of themain indefinite interpolation methods,multiple-point statistics(M P S)can extract the intrinsicfeatures of patterns from training images and copy them to the simulated regions.Because thetraditional MPS methods using linear dimensionality reduction are not suitable to deal with nonlineardata,isometric mapping(ISOM AP)is combined with MPS to address the above issues.A methodusing MPS and ISOMAP for the reconstruction of spatial data is proposed for the accuratereconstruction of unknown spatial data by constructing pattern dataset,dimensionality reduction ofpatterns,classification of patterns and extraction of patterns,which has provided a new idea fordealing with nonlinear spatial data by MPS.The experimental results show that the structuralcharacteristics of reconstructed results using this method are similar to those of training images.