The primary challenges facing production agriculture today are the following:

  • an ever-growing global population;

  • climate trends that affect growing seasons;

  • the availability of water, seeds, fertilizer, and other resources; and

  • a present and continuing labor shortage.

Population. The Earth's population continues to grow, with current predictions indicating farmers will need to feed 9.7 billion people by 2050 (as shown in Figure 1). This is a 50% increase in demand for food when compared to today.

Climate trends. Climate trends are also affecting agriculture. These trends include increased variability in temperature and rainfall.

Temperatures are generally increasing. On the positive side, this increases the length of growing seasons; on the negative side, higher temperatures can lead to drier conditions and less favorable growing seasons.

Rainfall patterns are also changing. Some areas are receiving less rain than in the past, while some are receiving more. The incidence of rainfall events is also changing, with more frequent occurrences of high rates of rainfall, resulting in runoff and the potential for higher rates of soil erosion.

Resource availability. The aforementioned changes are driving producers of agricultural products to look for any means available to meet the increasing demands of growing populations while using resources more efficiently. This is being done by trying to make every seed count, every drop of fertilizer and herbicide count, every drop of water count, and every grain harvested count.

Labor shortage. The population in agricultural areas continues to decrease. More automation and autonomy will be needed to help existing producers continue to grow more food in an efficient and sustainable way.

Traditionally, operator safety and protection, vehicle dynamics, tractor/implement compatibility, and performance testing have been the primary areas in which standards are applied to agricultural equipment. Advancements in automation and autonomy are expanding the need for new standards development in agriculture.

In the field, advanced technology is being used to face the challenges facing agriculture. The intent of this approach is to manage each square meter of soil in a manner that will optimize food production given the climate conditions while also optimizing resource use. Figure 2 illustrates the concept that advanced technology provides the means to manage a field in increments of a square meter or smaller.
This approach to optimization is applied to all operations in the field. The operations shown in Figure 3 include tillage, planting, applications of agricultural chemicals (including fertilizer, herbicides, fungicides, and insecticides), and harvesting.

Smart machines. Traditionally, increased productivity has come from larger and faster machines. In the future, productivity increases will come from the use of data in creating a smart machine. Technology is being applied to control machines and to create, gather and communicate data related to machine use and field use. This data is organized on a field-by-field basis.

These smart machines must know where they are going, what they are doing, and where they have been. A farmer can monitor what machine is in what field, what operation is being performed, and the machine's condition, such as fuel use and machine health. Figure 4 illustrates the application of this technology.

Data from machines can also be included in the soil optimization effort. This data can pertain to seed type, fertilizer type and amount, weed type, and yield data. A farmer can set up these systems ahead of time to ensure that the right seeds and other resources are applied to the right field by simply using a phone app.

Technology is also capable of dividing the field into small segments and assigning information to each segment. This information can include the following types:

  • soil fertility, including nitrogen, phosphorous, potassium, and organic matter;

  • the yield of any crop previously grown; and

  • weed and plant disease history.

Figure 5 shows an example of a yield map. This map gives the farmer an indication of the yield on a segment-by-segment basis.

This type of information allows a farmer to vary the rate applications of resources. Each segment can be given the optimum levels of resources that the soil can support, and the plants can utilize.

Tillage. Tillage consists of a tillage implement being pulled by a tractor driven by an operator. The tractor uses GPS, which allows for auto-guidance. Auto-guidance, used with the addition of the implement width, improves operating efficiency by controlling implement overlap from adjacent passes.

Auto-guidance, available since around 2000, automates the steering while the tractor is working in the field, but not when turning around at the end of the field. Recently, however, the turning function has become partially automated. New technology is also allowing full autonomy with no operator.

This tractor utilizes a vision system, artificial intelligence (both machine learning and rule based), sensors, and ultra-fast GPU processors to safely drive the tractor through the field. A farmer can not only monitor field activity but start a tractor in the field and supervise it with a cell phone or from the home office.

Planting. Planting involves a tractor pulling a planter. The tractor can use auto-guidance, just as used for tillage.

The planter is another complex smart machine, consisting of 24 to 60 electrically powered row units. Each row unit is controlled independently and can select one seed at a time and position each seed in a row at a precise distance from other seeds while traveling up to 15 km/hour.

Independent control allows for row units to stop planting in areas that have already been planted, as illustrated in Figure 6 . The planter can also apply fertilizer, herbicide and insecticide, all at variable rates.

Application. Application involves spraying a water and chemical solution on a field to eliminate plants that compete with the seeded crop for nutrient and water resources. Application is performed by a machine called a sprayer. The sprayer base unit is similar to that of a tractor, but it also contains a sprayer attachment with a foldable boom that can be up to 36 m in width. There are multiple nozzles positioned along the boom, and each nozzle can be controlled independently.

Today's smart machines also have cameras mounted on the boom. These smart machines use vision systems and artificial intelligence to identify plants that don't belong in the field and can spray an herbicide on that plant (and that plant only). The machine also can record the type of plant that was sprayed as well as the location of the plant in the field. This process is illustrated in Figure 7.

Again, the use of GPS machine positioning and knowing the boom width enables coverage of the field to be tracked. Individual nozzles can be shut off to prevent applying the solution to the same area twice.

Harvesting. Harvesting is performed by a combine, a self-propelled machine that cuts and gathers grain and crop material from the field, as shown in Figure 8 . The machine then separates the grain from the crop material and temporarily stores the grain prior to unloading.
This type of machine has many adjustments that historically were made by the operator once or twice a day as harvesting conditions changed. These adjustments were made while the machine was not operating. The adjustments are made either in the cab or in different areas of the machine itself. With a smart combine, these adjustments are made in real time as the machine harvests the field. They are made without any input from the operator and are displayed as shown in Figure 9 .

Grain condition and grain cleanliness, along with other harvesting parameters, are continuously monitored using vision systems and sensors mounted inside the machine. Machine learning programs are used to analyze the grain moving through the machine and can calculate and implement the harvesting adjustments needed to be made.

In addition, combines utilize GPS and automated steering to guide the machine through the field. Yield data can also be continuously recorded and assigned to the position in the field where the yield was recorded, producing a yield map.

Today and continuing into the future, standards development and application are occurring in the following areas of agriculture: functional safety, data connectivity and security, robotics and automation, artificial intelligence, image processing and perception systems, sustainability, and high voltage electrification.

Participants in standards development and application include John Deere and other agricultural equipment manufacturers, academic institutions, trade associations, and regulatory bodies. As food demand increases, agriculture will continue to seek and apply new technologies to meet that demand, thereby driving the need for additional standards.

Bruce Hawkins is a staff standards engineer at John Deere. He participates in developing standards applicable to agricultural equipment and provides guidance to U.S. national standards programs related to agricultural machinery.

Bruce Hawkins is a staff standards engineer at John Deere. He participates in developing standards applicable to agricultural equipment and provides guidance to U.S. national standards programs related to agricultural machinery.

Close modal