Summary:Automated weeders are capable of selectively removing weeds from the uncultivated band (3-5 inches wide) left around the seedline by standard cultivation. A camera detects the image, a computer processes the image and then activates a kill mechanism (e.g. a split blade). Twelve evaluations of autoweeders were conducted in 2020-21. Autoweeders removed from 31.7 to 98.7% of the weeds (average = 69.5%). The percent of weeds removed by the autoweeders was affected by the width of the uncultivated band and by the use of transplants; autoweeders removed fewer weeds if the uncultivated band was narrower (e.g. 3 inches vs 4 inches); in addition, automated weeders worked more efficiently with transplanted lettuce because the crop and weeds were smaller when weeded. Autoweeders did not reduce the lettuce stand or mean head weight in any of these evaluations. Autoweeded fields generally require follow up hand weeding to remove double lettuce plants (in direct seeded lettuce) and any remaining weeds. The question that comes up for growers is, does the reduction in follow-up hand weeding pay for the cost of running the autoweeder the field? We were not able to provide a simple answer to this question, however, we did see greater reduction in the time to subsequently hand weed fields where an autoweeder was used when the initial weed population was higher. However, given the labor situation, autoweeders may be justified regardless, if hand labor is simply not available to weed fields.
Introduction: Automated weeder technology has evolved significantly over the past decade. The technology used by auto weeders is similar to that used by the auto thinners: cameras detect plants, a computer processes the image and makes decisions about which plants to keep and which to remove and then activates the kill mechanism. Automated weeders remove weeds from inside the uncultivated band (3-5 inches wide) left around the seedline and unreachable by standard cultivation. The kill mechanism used by the currently available machines is either a split blade that opens around keeper plants (e.g. Robovator and Stout) or a spinning blade that avoids the keeper plants by placing them in a notch in the blade (e.g. Garford Robocrop). Auto weeders do not remove all the weeds in the seedline because they cannot remove weeds that are too close to the crop plants without risking damaging them. In addition, automated weeders are currently not capable of removing double lettuce plants in direct seeded lettuce fields, and as a result, it is still necessary to have a crew pass through the field following the passage of the auto weeder to remove to remove double lettuce plants and any missed weeds. Therefore, there are two costs when weeding with an autoweeder: the cost of the automated weeder and subsequent hand weeding/double lettuce plant removal. If the auto weeders can reduce the amount of subsequent hand weeding to cover the cost of running the autoweeder, then it is a net gain for a grower. In these evaluations we examined the initial weed population and the reduction in subsequent hand weeding following the use of an autoweeder in order to better understand the impact of the use of autoweeders on weed control in lettuce production.
Methods: Twelve trials were conducted in 2020 and 2021. Table 1 shows the details about each trial: machine used, planting configuration, lettuce types and dates of operations. The FarmWise and Stout autoweeders used a split-knife kill mechanism and the Naio machine used finger weeders. Autoweeding was carried out after thinning (except Dino Trial No. 2 was cultivated prior to thinning) and were compared with standard cultivation which leaves a 4-5 inch wide band around the seedline. In 2020, pre and post cultivation weed and stand counts were made of a 6-inch wide band around the seedline to determine the efficacy of standard and auto cultivation, but in 2021, pre and post cultivation weed counts were made following the passing of the standard cultivation. Weeding time measurements were made of the time it took a commercial hand weeding crew to pass through the treatment rows which was then converted to hours per acre. Stand counts and harvest evaluations were conducted to determine if the auto weeders caused damage to the stand or to crop plants.
Results: The number of weeds in the seedlines varied from as low a 1.6 to as high 41.5 plants/m2 (Table 2). Autoweeders removed from 31.7 to 98.7% and averaged 69.5%. The percent of weeds removed by the autoweeders was affected by the width of the uncultivated band. For instance, in first 2021 FarmWise evaluation 69.0% of the weeds were removed; however, in the second FarmWise evaluation only 31.7% of the weeds were removed. We think the difference between these two trials is that the first evaluation had a 5-inch wide uncultivated band which include many weeds that were easier for the autoweeder to remove a large portion. However, in the second FarmWise evaluation the uncultivated band was 3-inches wide and many of the easy to remove weeds were already gone, thereby reducing the number of weeds available for the autoweeder to remove. In the first 2021 Stout evaluation 97.7% of the weeds were removed. This field was a transplanted field established with PlantTape. The lettuce plants and weeds were smaller at the time of weeding and the machine was able to operate extremely efficiently. Autoweeders were did not damage the lettuce stand or mean head weight in any of these evaluations (Table 3). The percent reduction in the amount of time to weed the field varied from 2.5 to 60.0% with the use of the autoweeders in comparison with standard cultivation. Autoweeders significantly reduced subsequent hand weeding in 2021 (Table 3). Figure 1 correlates initial weed populations with the amount of reduction in subsequent hand weeding. The correlation indicates that there is a greater impact on subsequent hand weeding with greater weed populations. As mentioned above, this correlation may be impacted by the width of the uncultivated band and by the use of transplants. In spite of these influences, it appears that automated weeders may have a greater economic impact on total weeding costs when there are higher weed populations.
