Relating Crop Yield Tosoil Functional Properties Created by Data Mining and Knowledge-Based Inference Soil Mapping Techniques.

Available maps created by the USDA-NRCS Soil Survey illustrate soil variability based on morphologic and taxonomic variability. The mapped soil variability may not relate to a functional variability such as yield potential. The objective of this research was to 1) develop soil maps based on properties which would relate to crop growth and 2) compare the soil maps with yield data. This project involved disaggregating SSURGO soil polygons and reaggregating the data using knowledge based inference modeling (ArcSIE) to create soil property maps. These property maps included available water holding capacity, soil organic matter and depth to water table. Yield monitor data was compared to soil property maps in three locations. Including landscape properties with soil functional properties provides a better indication of water movement and availability.