Estimation multivariate fuzzy data in spatial statistics with application

This research addresses how to estimate unmeasured points for fuzzy spatial data when the number of its elements (spatial sample) is small, which is not preferred in the estimation process. As we know, when the data size is large, the estimation results for unmeasured points are better, and thus the estimation variance is lower. Therefore, the idea of this research is how to benefit from other secondary (auxiliary) fuzzy data that has a strong correlation with the primary (main) data for estimating one of its unmeasured points using the Co-kriging technique, after finding the central point of the fuzzy data values. This technique was applied to fuzzy data in the field of wheat cultivation in Iraq, where the production quantity was considered the primary data (primary variable) to estimate one of its unknown points, and the cultivated area (secondary variable) was used. Encouraging results were obtained.