You are here
2016 Commodity Classic: Fact-Based Farming
In January 2013, Tyler McClendon decided it was time to take action. “As I learned about what was possible in data collection and systems, I realized we could feasibly build a solution,” he says.
The result is an Ag Big Data system that captures data in near-real time from a variety of source systems and then integrates that data in near-real time.
“It provides information and analytics for the McClendons to drive decision making at the tactical operation level as well as the strategic level of the organization,” says Doug Hackney, Enterprise Group, Ltd. “The most important thing about the system is that it is 100% farmer-owned and farmer-controlled data, which is a big issue.”
“This system frees us from having to use thumb-in-the-wind, gut feelings for decision making,” McClendon says. “It lets us know truths to guide what we do. It enables fact-based farming – that’s the Big Idea.”
At a macro level, fact-based farming fits into their business strategy. “My father and I spend a LOT of time locked in an office discussing risk, particularly market risk. In late 2012, we started to see some cracks in the markets. The song we sang from that point through 2014 was ‘Hard times, they are a coming.’ We can now see that those times are here,” he relates.
To get through them and to continue to be competitive, the father and son knew they would have to be cost conscious and to find better ways to do things. “Making decisions based on facts rather than intuition is an unbelievably powerful tool,” says McClendon. “We all know that we need to be more environmentally conscious. Combine that with the increasing amount of money involved in agriculture, and that means the expected level of due diligence is rising. We believe that is a very good thing.”
An example he shares involves building a crop-planning model that takes into account field-specific variables such as fertility needs and machine efficiency to decide what crop to plant in each field.
“From a profitability perspective, some of these things vary tremendously field by field,” he says. “For instance, if we have a field with low machine efficiency, meaning it takes a lot of machine hours per acre to complete a field trip, we should not plant cotton there because that crop requires a higher number of field trips than corn or soybeans.”
One of the biggest changes they’ve seen is the elimination of having to physically create records when a trip is made to a field.
“Since we have automated field trip data collection, that information is collected by telematics,” says McClendon. “We simply hook up the implement needed and do the job.”