AI-GEOSTATS: CV via kriging ?
I am working on a project where we are looking at the local variance of crop density, by using a vegetative index (NDVI). The spot sensor readings are approx 4m apart (grid form) and cover a 160 acre field. Specific to my research, I am interested in the local CV (coefficient of variation) of crop density - but what constitutes local? My thought to answer this question is to 1.) estimate the variogram for the field, 2.) use the range as a search radius (definition of local) and 3.) use an objective function to estimate the weighted CV value points already on the collection grid (i.e. no prediction). In other words, I want to krige based on a spatially weighted CV rather than a spatially weighted mean.
I am relatively new to geostatistics. May I have some feedback on this procedure. Is it valid? Is there a better way? What are your thoughts?
Thanks very much and my best,
Oklahoma State University
[Non-text portions of this message have been removed]