From yield history to productivity zone identification with hidden Markov random fields

Modern precision agriculture equipment enables site-specific management by allowing different treatments for different parts of a field. This ability to subdivide the field calls for identifying management zones. A compromise between treating a field uniformly and treating every plant individually is needed, as the former does not maximize yields and the latter is often impractical. This work presents an algorithm for inferring the yield productivity zones (YPZ) for a field based on yield data from multiple years. The algorithm uses a hidden Markov random field model (HMRF) to find regions of the field which likely correspond to the same underlying yield distribution (i.e., productivity zones). These regions are modeled to be the same every year, but their distributions (i.e., yield characteristics) are allowed to vary with time to account for year-to-year variability (from e.g., weather effects, differing crops or crop varieties). The zone assignments and distributions are estimated using stochastic expectation maximization (SEM) and the maximizer of the posterior marginals (MPM). The underlying assumption of the model and algorithm is that the yields corresponding to a given YPZ will behave similarly and therefore derive from the same probability distribution. YPZs are useful inputs for determining management zones. An advantage of this method is that it is able to run with only the yield data which are automatically collected during harvest. Also, this method requires no crop specific calibration or configuration or normalization of the data by year.