ASABE Technical Library - Abstract

Abstract. Precision agriculture equipment enables treating different areas of a field differently, i.e., site specific management. This gives a potential for improved yield as well as better resource management, but also potential to make cropping management more complex. With these conflicting outcomes, the goal of precision agriculture is to be site-specific without being too site specific. This results in the concept of management zones, which are a compromise between treating a field uniformly and treating every plant individually.

This work presents an algorithm for inferring the management zones for a field based on yield data from multiple years. The algorithm is implemented using a Hidden Markov Model (HMM) where the management zones are seen as a hidden Markov Random Field (MRF). The algorithm seeks regions of the field which likely correspond to the same underlying yield distribution (i.e., “management zones”). These regions are assumed to be the same for each year, but allow their distributions to vary with time to account for year-to-year variability (from e.g., weather effects, differing crops). The zone assignments and distributions are estimated using Stochastic Expectation Maximization (SEM) and maximization of posterior marginals (MPM). The underlying assumption of the model and algorithm is that the yields corresponding to a given “management zone” will behave similarly, and therefore derive from the same probability distribution.

An advantage of this method is that it is able to run with only the yield data automatically collected during harvest, though it could be modified to leverage other (non-automatically collected) types of data, such as soil type and topography. The more data supplied to the algorithm, the more refined its estimates will be. Also, this method requires no crop specific calibration or configuration.