Precision farming has been defined as: “A management concept which recognizes variability within the soil environment and maximizes economic agricultural production while minimizing environmental impact for a specific location.” Being a management concept, precision farming is based on a dynamic decision making process with specific objectives.
In its truest form, precision ag should be focused on and directed by the plant. The source of income in agronomic production is food, fiber and energy — all of which are derived from the plant. Precision ag is all about implementing best management practices, like the 4R’s, for a specific plant in a specific geographic location.
If this is the case, why is the dominant aspect of precision farming the equipment/technology? As a consultant, I am often confronted with the question “I have this great technology for precision ag, now how do I get the industry to use it?”
My response is often the same — “How does it affect the plant?” For a technology to be sustainable within the marketplace, it has to have a positive impact on the plant, thus creating revenue for the producer, that the producer is then willing to share with the technology.
Cost savings is good, but the greater potential for return is to positively affect the revenue side of the equation — positive interaction between the plant and the practices and products applied to it.
The first agronomic challenge I see is data. Precision farming operates in a continuous cycle of data, decision and deployment. The quantity of data is enormous and can only be expected to increase exponentially with the advent of IoT (Internet of Things).
Data needs to be understood, usable and readily available for the decision-making process.
“The decision making process of converting data into best management practice recommendations is in its infancy, at best…”
The biggest hole I see, is the lack of usable data from within the genetics/life science sector for product specific information. Corn is not corn, and agronomists need to understand the differences within corn and other crops. We do not have strong data on a specific plant and how it reacts to identified conditions.
The second agronomic challenge is the development of digital algorithms to be utilized in the decision making process. Precision ag works within a digital world where massive quantities of data are processed to derive best management practices and recommendations.
Without these algorithms, concepts like variable-rate are going to have a difficult time deriving an economic return. Much of the art of agriculture needs to be converted to digital capabilities and blended with science to develop effective algorithms.
So why would I ask if precision farming is being held hostage? It’s because of the imbalance of the 3D’s (data, decision, deployment). The equipment and related technology industries have given precision farming a vast array of tools, yet do we know how to use them?
We have the ability to capture data through imagery and sensors, yet do we know analytically how these readings relate to crop production? We get the cart in front of the horse with regards to precision ag. Engineers and technologists say they can do something and it becomes the agronomist’s role to figure out how to utilize it for the plant.
Deployment and data collection innovations are everywhere, yet the decision making process of converting data into best management practice recommendations is in its infancy, at best. The communications industry has streamlined the process of getting best management recommendations into the deployment process and getting field collected data out of the process.
The problem is, we don’t know what decision to put into it, the deployment process or necessarily what data is coming back from it. Agronomists are spending time trying to develop best management practices that utilize a technology developed by engineers and technologists.
Instead, agronomists should be spending time understanding the plant and what best management practices are beneficial for the plant in specific situations. These best management practices should than be turned over to the engineers and technologist to collect the data, develop algorithms and implement the best management practices.
Often times, we focus on the enabler — technology — rather than the economic driver, the plant. We must never forget the plant is the sole source of economic returns for agronomic production agriculture and need to focus there.