Targeted spraying application technologies have the capacity to drastically reduce herbicide inputs, but to be successful, the performance of both machine vision–based weed detection and actuator efficiency needs to be optimized. This study assessed (1) the performance of spotted spurge recognition in ‘Latitude 36’ bermudagrass turf canopy using the You Only Look Once (YOLOv3) real-time multiobject detection algorithm and (2) the impact of various nozzle densities on model efficiency and projected herbicide reduction under simulated conditions. The YOLOv3 model was trained and validated with a data set of 1,191 images. The simulation design consisted of four grid matrix regimes (3 × 3, 6 × 6, 12 × 12, and 24 × 24), which would then correspond to 3, 6, 12, and 24 nonoverlapping nozzles, respectively, covering a 50-cm-wide band. Simulated efficiency testing was conducted using 50 images containing predictions (labels) generated with the trained YOLO model and by applying each of the grid matrixes to individual images. The model resulted in prediction accuracy of an F1 score of 0.62, precision of 0.65, and a recall value of 0.60. Increased nozzle density (from 3 to 12) improved actuator precision and predicted herbicide-use efficiency with a reduction in the false hits ratio from ∼30% to 5%. The area required to ensure herbicide deposition to all spotted spurge detected within images was reduced to 18%, resulting in ∼80% herbicide savings compared to broadcast application. Slightly greater precision was predicted with 24 nozzles but was not statistically different from the 12-nozzle scenario. Using this turf/weed model as a basis, optimal actuator efficacy and herbicide savings would occur by increasing nozzle density from 1 to 12 nozzles within the context of a single band.

Control of broadleaf weeds in caladium is difficult due in part to a lack of selective POST herbicides. Cultivation is not an option due to the dense canopy and potential for tuber injury. As a result, growers currently rely on preemergence (PRE) herbicide and hand-weeding. The objective of this research was to evaluate the control of four common broadleaf weeds of field grown caladium with POST applications of halosulfuron, thifensulfuron-methyl, and trifloxysulfuron, and determine the tolerance of caladium cultivars ‘Florida Fantasy’ and ‘Florida cardinal’ to POST applications of halosulfuron. At 4 weeks after treatment (WAT), thifensufluron-methyl at 28 g ai ha−1 and trifloxysulfuron at 84 g ai ha−1 provided approximately 90 and 70% common purslane control, respectively, while halosulfuron at 210 g ai ha−1 provided 55% suppression. Trifloxysulfuron controlled ≥90% spotted spurge at 42 g ha−1, whereas the highest rate of halosulfuron and thifensulfuron-methyl only achieved 60% suppression. In field experiments, the evaluated sulfonylurea (SU) herbicides were less efficacious on hairy indigo and sharppod morningglory as control never exceeded 65 and 50%, respectively. In greenhouse experiments, the evaluated halosulfuron rates ranging from 26 to 420 g ha−1 did not significantly reduce caladium tuber weight from the nontreated control. Averaged over halosulfuron rates, ‘Florida Fantasy’ damage was 5 and 6% at 2 and 4 WAT, respectively, while ‘Florida Cardinal’ damage was 11%. We conclude that none of the herbicide treatments effectively controlled all species evaluated. Sequential treatments, higher rates, or tank-mixtures may be necessary to adequately control these species. We also conclude that caladium cultivars ‘Florida Fantasy’ and ‘Florida Cardinal’ have acceptable tolerance to POST applications of halosulfuron. Further research is needed to evaluate caladium tolerance to other SU herbicides.

Flumioxazin is used in nursery production and landscape maintenance industries. In these situations, weed control provided by flumioxazin often lasts longer than that reported in soil. Our objective was to quantify flumioxazin longevity under conditions found in nursery production. Pots were filled with 6 : 1 (v/v) pine bark : sand mixture. This nonsoil media is typical of what is used for nursery crop production. Pots were treated with flumioxazin at either 0.28 or 0.42 kg ai ha−1, and subsequently sown with either hairy bittercress (two winter experiments) or spotted spurge (two summer experiments) at weekly intervals. Weed seed germination, emergence, and seedling establishment in the treated pots was compared with nontreated control and used as a proxy for herbicide activity. Flumioxazin provided approximately 7 wk of complete (100%) hairy bittercress control regardless of rate. However, a rate effect was evident in only one of the two experiments conducted with hairy bittercress. In both experiments with hairy bittercress, marginal and highly variable activity was still evident at 18 wk after treatment. Flumioxazin at 0.28 and 0.42 kg ha−1 provided 2- and 4-wk complete spotted spurge control, respectively. No spotted spurge control was evident after about 8 wk. Subjecting this less-variable data to nonlinear regression revealed that the time required for 50% reduction in flumioxazin activity was approximately 5.5 and 6.6 wk for the two rates, respectively. A column leaching study revealed that flumioxazin activity remained localized near the surface (0 to 4 cm). Therefore the dissipation observed was likely the result of in situ degradation and not displacement. The high organic matter content of the nonsoil media contributes to the observed persistence of flumioxazin activity.

Both prodiamine and flumioxazin are used in the nursery production and landscape maintenance industries in the southeastern United States for preemergence weed control. Research was conducted to determine whether a tank mixture of these two herbicides would be more effective than either component applied alone. Prodiamine alone, flumioxazin alone, and a 72 : 28 (by weight) prodiamine–flumioxazin mixture were each applied at a series of rates to containers filled with a pine bark–sand substrate that is typical for nursery production in the southeastern United States. Our intent was to have a rate range that hopefully extended from ineffective to lethal for each treatment series. Subsequent to treatment, containers were overseeded with either large crabgrass, spotted spurge, or eclipta. Percent control was determined by comparing treated weed foliage fresh weight to that of the appropriate nontreated control at 6 and 12 wk after application. ANOVA followed by nonlinear regression was used to evaluate the interaction of prodiamine and flumioxazin when combined and to determine the rate of each treatment series required for 95% control (if applicable) for each of the three weed species. Results varied with weed species. The mixture was synergistic and more cost effective than either of the components applied alone in controlling spotted spurge. With respect to large crabgrass control, the mixture was additive and slightly more cost effective than the components. Eclipta could only be controlled with flumioxazin, and this control was antagonized by the addition of prodiamine.

Weed management is a common practice in golf courses, home lawns, and sod production systems. Sulfonylurea (SU) herbicides were initially introduced in the agricultural market in 1982; however, SUs were also evaluated for control of weeds and overseeded grasses. Later, SUs were evaluated for selective control of broadleaf weeds, sedges, and kyllinga species in cool- and warm-season turfgrasses. In the 1990s, chlorsulfuron and metsulfuron were registered for selective control of broadleaf weeds, such as wild garlic, spotted spurge, and difficult-to-control grasses, such as bahiagrass in turfgrass. Now, there are several SUs registered for specific weed management in both cool- and warm-season turfgrasses. The current status of SUs, along with potential benefits and drawbacks in using these herbicides for weed management practices, are discussed. The research findings, possible recommendations in relation to the safety of turfgrass (established and overseeding stands), environmental concerns (persistence and lateral movement), and management practices in cool- and warm-season turfgrasses are discussed, including the potential evolution of weed resistance.

Metsulfuron is used for POST control of spotted spurge in many warm-season turfgrasses. A suspected resistant (R) biotype of spotted spurge was collected from turfgrass in Georgia with a history of exclusive metsulfuron use. Research was conducted to evaluate the resistance level of this biotype to metsulfuron, efficacy of other mechanisms of action for control, and the molecular basis for resistance. Compared with a susceptible (S) biotype, the R biotype required >90 and >135 times greater metsulfuron rates to reach 50% injury and reduce biomass 50% from the nontreated, respectively. The R biotype was also resistant to trifloxysulfuron but was injured equivalent to the S biotype from dicamba, glyphosate, and triclopyr. Gene sequencing of the R biotype revealed a Trp574 to Leu substitution that has conferred resistance to acetolactate synthase (ALS) inhibitors in previous research. This is the first report of ALS resistance in spotted spurge. More importantly, this is the first report of a herbicide-resistant broadleaf weed from a turfgrass system in the United States.