A zone-based approach for processing and interpreting variability in multi-temporal yield data sets

摘要: Abstract The availability of combine yield monitors since the early 1990′s means that long time-series (10+ years) data are now available in many arable production systems. Despite this, and maps still under-exploited under-valued by professionals agricultural sector. These historical need to be better considered analyzed because they only audited which growers practitioners can assess spatio-temporal response within a field. When done, mostly processed classification-based algorithms generate spatial temporal stability or provide management classes. This work details an alternate segmentation-based methodology first then characterize contiguous within-field zones from data. It operates on rather than interpolated maps. A seeded region growing algorithm is proposed enables both specification seeds zone segmentation multivariate (multi-temporal yield) attribute space. Novel metrics zoning derived textural image analysis. were applied two fields with (6+ combinable crops. case studies showed zone-based approach was effective delimitating relevant zones. generated had differing responses between neighbouring that were agronomic significant interest As this attempt apply data, areas for future development applications also proposed.