From yield history to productivity zone identification with hidden Markov random fields
- 18 Downloads
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.
KeywordsHidden Markov models Image segmentation Expectation–maximization algorithms Monte Carlo methods Yield Productivity zone Management zone
The authors would like to thank Ault Farms for supplying the yield data used. This work was supported by USDA/NIFA Project title: Improving Agricultural Management with Autogenic Mobile Technology, AWS Cloud Credits for Research, and FFAR Project title: An Open Source Framework and Community for Sharing Data and Algorithms.
- Diker, K., Heermann, D. F., & Buchleiter, G. W. (2003). Analysis of multi year yield data for delineating yield response zones. Paper 031086. St Joseph, MI, USA: ASAE.Google Scholar
- Elliott, R. J. (2008). Hidden Markov models: Estimation and control. New York, USA: Springer.Google Scholar
- Furr, G. F., Jr. (1987). Soil Conservation Service. Indiana, USA: Soil Survey of Fulton County.Google Scholar
- Gorse, C., Johnston, D., and Pritchard, M. (2012). Universal transverse mercator. In A dictionary of construction, surveying and civil engineering. Oxford, UK: Oxford University Press.Google Scholar
- IndianaMap. (2011). IndianaMap Framework Lidar. Indiana Statewide Imagery and LiDAR Program, distributed by OpenTopography. https://doi.org/10.5069/G9959FHZ.
- Kitchen, N. R., Sudduth, K. A., Myers, B., Drummond, S. T., & Hong, S. Y. (2003). Site-specific productivity zones delineated using bulk soil electrical conductivity. Paper 032340. St Joseph, MI, USA: ASAE.Google Scholar
- Layton, A. W., Krogmeier, J. V., Ault, A., & Buckmaster, D. R. (2018). Stochastic estimation of field management zones using multi-year yield data and a hidden Markov random field. Technical Report 485. West Lafayette, IN, USA: Department of Electrical and Computer Engineering, Purdue University.Google Scholar
- Layton, A. W., Wang, Y., Krogmeier, J. V., & Buckmaster, D. R. (2016). Robust estimation of field management zones using multi-year yield data and a hidden Markov random field. In Proceedings of the 2016 ASABE Annual International Meeting, Paper No. 162461641, pp 1–11 St. Joseph, MI, USA: ASABE. https://dx.doi.org/10.13031/aim.20162461641.
- Miyamoto, S. (2008). Algorithms for fuzzy clustering methods in c-means clustering with applications. Berlin, Germany: Springer. Includes bibliographical references (pp. 235–243) and index.Google Scholar
- Nawar, S., Corstanje, R., Halcro, G., Mulla, D., & Mouazen, A. M. (2017). Chapter four—delineation of soil management zones for variable-rate fertilization: A review (Vol. 143, pp. 175–245)., Advances in agronomy. Cambridge, MA, USA: Academic Press.Google Scholar
- Shepard, D. (1968). A two-dimensional interpolation function for irregularly-spaced data. In Proceedings of the 1968 23rd ACM National Conference, ACM’68, pp. 517–524. New York, NY, USA: ACM.Google Scholar
- Soil Survey Staff, Natural Resources Conservation Service, United States Department of Agriculture. Soil Survey Geographic (SSURGO) Database for Fulton County, Indiana. https://dx.doi.org/10.15482/USDA.ADC/1242479.