A comparison of linear and non-linear kriging techniques for predicting the probability of exceeding a threshold value
This study investigates the effectiveness of different kriging techniques to predict the probability that the value of a variable at a location exceeds a threshold value, with particular application to variable rate application of fertilizer in agriculture. Most often, disjunctive kriging using Hermite polynomials is used to create probability maps of predictions, but it is shown here that simpler kriging techniques can be used to make predictions of similar quality when certain assumptions can be satisfied. Data was collected in 2017 using tractor mounted sensors on a farm in Southwestern Ontario. A measure of greenness, NDVI, was calculated and linked to GPS coordinates, which was then used to predict the harvestability of the land. Both linear and non-linear methods show high predictive ability, suggesting that linear kriging is a viable alternative. Additional data collection and analysis is suggested to validate these results and further refine the models.