The amount of data available in agriculture is increasing, as is the interest in creating value from that data. There are abundant opportunities for finding value in agricultural data, but much of that value comes from aggregating that data to create more encompassing datasets. While the information gained from aggregated datasets can be valuable for decision-making, the risk of making the incorrect decisions based on low quality or incomplete data can be high. Understanding how inaccurate data and missing data can impact the management decisions that are ultimately made using these dataset is important when collecting, analyzing, and interpreting agricultural data. This presentation will focus on data quality considerations when aggregating or interpreting aggregated data.

The use of data aggregation allows the ability to benchmark producer’s management strategies against their peers. Benchmarking allows producers to realize that there are other farmers who are operating more efficiently and more profitably with similar yields. Examples including the UNL-TAPS Farm Management Competition and other data sources will be discussed.  Future Extension efforts will focus on using farm management competitions and Natural Resource District farm data to set water and nitrogen benchmarks for producers.

Every year new sources of information become available which allow the better characterization of the spatial variability of crop development and the factors influencing it. The use of on-farm precision experiments allows us to go a step further and characterize the spatial variability in the crop response to management practices. However, most of the data can only be collected after the decision has been already made. In order to harness the full power of precision agriculture, we need to develop better predictive tools. Ideally, these tools should combine all the information available in a clear and intuitive way to guide the decisions. Combining these sources of information is a challenging task since it involves contrastingly different spatial and temporal resolutions and levels of uncertainty. The presentation will cover some of the tools and techniques the Data Intensive Farm Management Project has been developing to address this challenge.

Growers today are constantly looking to make practical sense, and take meaningful action, from the data they generate on their farms.  By understanding yield influences in individual fields, we can begin to examine the larger picture of yield trends across an entire operation.  Growers increasingly want to see beyond their own farms to anonymously compare results with their peers, in trusted, localized groups.  By comparing agronomic trends and yield influences through a depth of high-quality data at the Regional Group level, growers can make more informed decisions for their own operation and prove their profitability.