Data Fusion: Bringing Ag Data Layers Together to Make informed Management Decisions

Many farmers are collecting lots of spatial ag data – things like planting data, yield monitor data, soil samples, EC data, and aerial imagery. But most farmers are not fully benefiting from this data.

The 2015 Precision Agriculture Services Dealership Survey Results sponsored by CropLife magazine and the Departments of Agricultural Economics and Agronomy at Purdue University looks at precision agricultural technology uses among crop input dealers. The survey found that the most common way dealers report helping customers analyze their agriculture data was printing maps, such as yield, soil electrical conductivity, and soil maps (82%). Nearly 39% reported working with producers and analyzing data from their individual farms.

PrecAgServiceSurvey
©2015 by Bruce Erickson and David A. Widmar.

This points to a tremendous opportunity for increased analysis of ag data.

In preparation for our 2017 research study, we combined a number of layers to establish our management zones. These management zones were used in conjunction with aerial imagery to determine our in-season nitrogen application rate (additional posts coming soon!).

Fusing the Data Layers

We started with a total of 15 data layers, shown below.

15_Data_Fusion_Layers_2.png

The 15 layers were loaded into Management Zone Analyst (USDA-ARS). Management Zone Analyst is “a decision-aid for creating within-field management zones based on quantitative field information.”

The output of Management Zone Analyst showed bare soil reflectance blue band and 2005 yield were less correlated, therefore these 2 layers were removed from the clustering process. Using the resulting analysis with 13 data layers, a 2 management zone cluster was selected as shown below.

2_Management_Zones_Clipped
2 management zones developed with Management Zone Analyst (USDA-ARS).

Determining Yield Goal

The management zone map was clipped to include only the area of the research plot. From there, yield goals were assigned based on previous yield history and the farmer’s experience.

Yield_Goal_by_Zone_clipped
Yield goals by management zone.

 

Determining Optimum Nitrogen Rate (ONR)

The goal for this data fusion, was ultimately to determine an optimum N rate for various portions of the field. This optimum N rate (ONR) is then used with aerial imagery to determine the in-season N rate.

In order to transform our yield goal map to an optimum N rate map, we used the University of Nebraska – Lincoln Corn Nitrogen Recommendation Equation shown below.

UNL_Equation.png
(C) 2008, The Board of regents of the University of Nebraska on behalf of the University of Nebraska-Lincoln Extension. All rights reserved.

The University of Nebraska – Lincoln equation requires organic matter as one of the inputs. Because this varies across the field and organic matter had been sampled on a 2.5 acre grid, the following map was developed for use in the equation.

OM_clipped
Soil organic matter from 2.5 acre grid soil samples.

Using the organic matter map, yield goal map, and other constant values shown in the above equation, the optimum nitrogen rate was determined across the field.

ONR_clipped
Optimum nitrogen rates for study area.

In our next post we will discuss how aerial imagery was used in conjunction with the optimum nitrogen rate map to determine in-season nitrogen application.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s