The past 50 yr of advances in weed recognition technologies have poised site-specific weed control (SSWC) on the cusp of requisite performance for large-scale production systems. The technology offers improved management of diverse weed morphology over highly variable background environments. SSWC enables the use of nonselective weed control options, such as lasers and electrical weeding, as feasible in-crop selective alternatives to herbicides by targeting individual weeds. This review looks at the progress made over this half-century of research and its implications for future weed recognition and control efforts; summarizing advances in computer vision techniques and the most recent deep convolutional neural network (CNN) approaches to weed recognition. The first use of CNNs for plant identification in 2015 began an era of rapid improvement in algorithm performance on larger and more diverse datasets. These performance gains and subsequent research have shown that the variability of large-scale cropping systems is best managed by deep learning for in-crop weed recognition. The benefits of deep learning and improved accessibility to open-source software and hardware tools has been evident in the adoption of these tools by weed researchers and the increased popularity of CNN-based weed recognition research. The field of machine learning holds substantial promise for weed control, especially the implementation of truly integrated weed management strategies. Whereas previous approaches sought to reduce environmental variability or manage it with advanced algorithms, research in deep learning architectures suggests that large-scale, multi-modal approaches are the future for weed recognition.

Italian ryegrass is a major weed in winter cereals in the south-central United States. Harvest weed seed control (HWSC) tactics that aim to remove weed seed from crop fields are a potential avenue to reduce Italian ryegrass seedbank inputs. To this effect, a 4-yr, large-plot field study was conducted in College Station, Texas, and Newport, Arkansas, from 2016 to 2019. The treatments were arranged in a split-plot design. The main-plot treatments were (1) no narrow-windrow burning (a HWSC strategy) + disk tillage immediately after harvest, (2) HWSC + disk tillage immediately after harvest, and (3) HWSC + disk tillage 1 mo after harvest. The subplot treatments were (1) pendimethalin (1,065 g ai ha−1; Prowl H2O®) as a delayed preemergence application (herbicide program #1), and (2) a premix of flufenacet (305 g ai ha−1) + metribuzin (76 g ai ha−1; Axiom®) mixed with pyroxasulfone (89 g ai ha−1; Zidua® WG) as an early postemergence application followed by pinoxaden (59 g ai ha−1; Axial® XL) in spring (herbicide program #2). After 4 yr, HWSC alone was significantly better than no HWSC. Herbicide program #2 was superior to herbicide program #1. Herbicide program #2 combined with HWSC was the most effective treatment. The combination of herbicide program #1 and standard harvest practice (no HWSC; check) led to an increase in fall Italian ryegrass densities from 4 plants m−2 in 2017 to 58 plants m−2 in 2019 at College Station. At wheat harvest, Italian ryegrass densities were 58 and 59 shoots m−2 in check plots at College Station and Newport, respectively, whereas the densities were near zero in plots with herbicide program #2 and HWSC at both locations. These results will be useful for developing an improved Italian ryegrass management strategy in this region.

Wild radish is the most problematic broadleaf weed in Australian grain production. The propensity of wild radish to evolve resistance to herbicides has led to high frequencies of multiple herbicide–resistant populations present in these grain production regions. The objective of this study was to evaluate the potential of mesotrione to selectively control wild radish in wheat. The initial dose response pot trials determined that at the highest mesotrione rate of 50 g ha−1 applied preemergence (PRE) was 30% more effective than when applied postemergence (POST) on wild radish. This same rate of mesotrione applied POST resulted in a 30% reduction in wheat biomass compared to 0% for the PRE application. Subsequent mesotrione PRE dose response trials identified a wheat selective rate range of >100 and <300 g ai ha−1 that provided greater than 85% wild radish control with less than 15% reduction in wheat growth. Field evaluations confirmed the efficacy of mesotrione at 100 to 150 g ai ha−1 in reducing wild radish populations by greater than 85% following PRE application and incorporation by wheat planting. Additionally, these field trials demonstrated the opportunity for season-long control of wild radish when mesotrione applied PRE was followed by bromoxynil applied POST. The sequential PRE application of mesotrione, a herbicide that inhibits p-hydroxyphenylpyruvate dioxygenase, followed by POST application of bromoxynil, a herbicide that inhibits photosystem II, has the potential to provide 100% wild radish control with no effect on wheat growth.

Chaff lining and chaff tramlining are harvest weed seed control (HWSC) systems that involve the concentration of chaff material containing weed seed into narrow (20 to 30 cm) rows between or on the harvester wheel tracks during harvest. These lines of chaff are left intact in the fields through subsequent cropping seasons in the assumption that the chaff environment is unfavorable for weed seed survival. The chaff row environment effect on weed seed survival was examined in field studies, and chaff response studies determined the influence of increasing amounts of chaff on weed seedling emergence. The objectives of these studies were to determine the influences of (1) chaff lines on the summer–autumn seed survival of selected weed species and (2) chaff type and amount on rigid ryegrass seedling emergence. There was frequently no difference (P > 0.05) in seed survival of four weed species (rigid ryegrass, wild oat, annual sowthistle, and turnip weed) when seeds were placed beneath or beside chaff lines. In one instance, wild oat seed survival was increased (P < 0.05) when seed were placed beneath compared to beside a chaff line. The pot studies determined that increasing amounts of chaff consistently resulted in decreasing numbers of rigid ryegrass seedlings emerging through chaff material. The suppression of emergence broadly followed a linear relationship in which there was approximately a 2.0% reduction in emergence with every 1,000 kg ha–1 increase in chaff material. This relationship was consistent across wheat, barley, canola, and lupin chaff types, indicating that the physical presence of the chaff was more important than chaff type. These studies suggested that chaff lines may not affect the survival over summer–autumn of the contained weed seeds but that the subsequent emergence of weed seedlings will be restricted by high amounts of chaff (>40,000 kg ha–1).

Narrow-windrow burning has been a successful form of harvest weed seed control in Australian cropping systems, but little is known about the efficacy of narrow-windrow burning on weed seeds infesting U.S. cropping systems. An experiment was conducted using a high-fire kiln that exposed various grass and broadleaf weed seeds to temperatures of 200, 300, 400, 500, and 600 C for 20, 40, 60, and 80 s to determine the temperature and time needed to kill weed seeds. Weeds evaluated included Italian ryegrass, barnyardgrass, johnsongrass, sicklepod, Palmer amaranth, prickly sida, velvetleaf, pitted morningglory, and hemp sesbania. Two field experiments were also conducted over consecutive growing seasons, with the first experiment aimed at determining the amount of heat produced during burning of narrow windrows of soybean harvest residues (chaff and straw) and the effect of this heat on weed seed mortality. The second field experiment aimed to determine the effect of wind speed on the duration and intensity of burning narrow windrows of soybean harvest residues. Following exposure to the highest temperature and longest duration in the kiln, only sicklepod showed any survival (<1% average); however, in most cases, the seeds were completely destroyed (ash). A heat index of only 22,600 was needed to kill all seeds of Palmer amaranth, barnyardgrass, and Italian ryegrass. In the field, all seeds of the evaluated weed species were completely destroyed by narrow-windrow burning of 1.08 to 1.95 kg m−2 of soybean residues. The burn duration of the soybean harvest residues declined as wind speed increased. Findings from the kiln and field experiments show that complete kill is likely for weed seeds concentrated into narrow windrows of burned soybean residues. Given the low cost of implementation of narrow-windrow burning and the seed kill efficacy on various weed species, this strategy may be an attractive option for destroying weed seed.

Australian conservation cropping systems are practiced on very large farms (approximately 3,000 ha) where herbicides are relied on for effective and timely weed control. In many fields, though, there are low weed densities (e.g., <1.0 plant 10 m−2) and whole-field herbicide treatments are wasteful. For fallow weed control, commercially available weed detection systems provide the opportunity for site-specific herbicide treatments, removing the need for whole-field treatment of fallow fields with low weed densities. Concern about the sustainability of herbicide-reliant weed management systems remain and there has not been interest in the use of weed detection systems for alternative weed control technologies, such as targeted tillage. In this paper, we discuss the use of a targeted tillage technique for site-specific weed control in large-scale crop production systems. Three small-scale prototypes were used for engineering and weed control efficacy testing across a range of species and growth stages. With confidence established in the design approach and a demonstrated 100% weed-control potential, a 6-m wide pre-commercial prototype, the “Weed Chipper,” was built incorporating commercially available weed-detection cameras for practical field-scale evaluation. This testing confirmed very high (90%) weed control efficacies and associated low levels (1.8%) of soil disturbance where the weed density was fewer than 1.0 plant 10 m−2 in a commercial fallow. These data established the suitability of this mechanical approach to weed control for conservation cropping systems. The development of targeted tillage for fallow weed control represents the introduction of site-specific, nonchemical weed control for conservation cropping systems.

Downy brome, feral rye, and jointed goatgrass are problematic winter annual grasses in central Great Plains winter wheat production. Integrated control strategies are needed to manage winter annual grasses and reduce selection pressure exerted on these weed populations by the limited herbicide options currently available. Harvest weed-seed control (HWSC) methods aim to remove or destroy weed seeds, thereby reducing seed-bank enrichment at crop harvest. An added advantage is the potential to reduce herbicide-resistant weed seeds that are more likely to be present at harvest, thereby providing a nonchemical resistance-management strategy. Our objective was to assess the potential for HWSC of winter annual grass weeds in winter wheat by measuring seed retention at harvest and destruction percentage in an impact mill. During 2015 and 2016, 40 wheat fields in eastern Colorado were sampled. Seed retention was quantified and compared per weed species by counting seed retained above the harvested fraction of the wheat upper canopy (15 cm and above), seed retained below 15 cm, and shattered seed on the soil surface at wheat harvest. A stand-mounted impact mill device was used to determine the percent seed destruction of grass weed species in processed wheat chaff. Averaged across both years, seed retention (±SE) was 75% ± 2.9%, 90% ± 1.7%, and 76% ± 4.3% for downy brome, feral rye, and jointed goatgrass, respectively. Seed retention was most variable for downy brome, because 59% of the samples had at least 75% seed retention, whereas the proportions for feral rye and jointed goatgrass samples with at least 75% seed retention were 93% and 70%, respectively. Weed seed destruction percentages were at least 98% for all three species. These results suggest HWSC could be implemented as an integrated strategy for winter annual grass management in central Great Plains winter wheat cropping systems.

The loss of herbicide options due to resistance and lack of new chemistries have delivered the realization that herbicides are a finite resource and weed control alternatives are desperately needed. In Australian conservation cropping, the only available alternatives suited to routine use are the recently introduced harvest weed seed control (HWSC) and the ever-present but undervalued crop competition. Target-neighbor design pot studies examined wheat (Triticum aestivum L.) competition effects on biomass and seed production of rigid ryegrass (Lolium rigidum Gaudin), wild radish (Raphanus raphanistrum L.), ripgut brome (Bromus diandrus Roth), and wild oat (Avena fatua L.). The influence of wheat competition on crop canopy distribution of weed biomass and seed production was also examined. At the current commercially targeted wheat density (120 plants m−2) weed biomass was reduced by 69%, 73%, 72%, and 49% and seed production by 78%, 78%, 77%, and 50% for L. rigidum, R. raphanistrum, B. diandrus, and A. fatua, respectively, when compared with no competition. These results highlighted the importance of uniform wheat crop establishment in minimizing the ongoing impact of weeds. Enhanced what competition (from 120 to 400 plants m−2) resulted in further smaller, but substantial, reductions in biomass (19%, 13%, 20%, and 39%) and seed production (12%, 13%, 17%, and 45%) for L. rigidum, R. raphanistrum, B. diandrus, and A. fatua, respectively. This enhanced competition also increased weed seed retention in the upper crop canopy (>40 cm) by 35% and 31% for L. rigidum and B. diandrus, respectively, but not for A. fatua and R. raphanistrum, for which weed seed retention was already >80% at the wheat density of 120 plants m−2. Enhanced wheat crop competition, then, has the dual effect of restricting the growth and development of L. rigidum, R. raphanistrum, B. diandrus, and A. fatua as well increasing the susceptibility of these weed species to HWSC.

The widespread use of herbicides in cropping systems has led to the evolution of resistance in major weeds. The resultant loss of herbicide efficacy is compounded by a lack of new herbicide sites of action, driving demand for alternative weed control technologies. While there are many alternative methods for control, identifying the most appropriate method to pursue for commercial development has been hampered by the inability to compare techniques in a fair and equitable manner. Given that all currently available and alternative weed control methods share an intrinsic energy consumption, the aim of this review was to compare methods based on energy consumption. Energy consumption was compared for chemical, mechanical, and thermal weed control technologies when applied as broadcast (whole-field) and site-specific treatments. Tillage systems, such as flex-tine harrow (4.2 to 5.5 MJ ha−1), sweep cultivator (13 to 14 MJ ha−1), and rotary hoe (12 to 17 MJ ha−1) consumed the least energy of broadcast weed control treatments. Thermal-based approaches, including flaming (1,008 to 4,334 MJ ha−1) and infrared (2,000 to 3,887 MJ ha−1), are more appropriate for use in conservation cropping systems; however, their energy requirements are 100- to 1,000-fold greater than those of tillage treatments. The site-specific application of weed control treatments to control 2-leaf-stage broadleaf weeds at a density of 5 plants m−2 reduced energy consumption of herbicidal, thermal, and mechanical treatments by 97%, 99%, and 97%, respectively. Significantly, this site-specific approach resulted in similar energy requirements for current and alternative technologies (e.g., electrocution [15 to 19 MJ ha−1], laser pyrolysis [15 to 249 MJ ha−1], hoeing [17 MJ ha−1], and herbicides [15 MJ ha−1]). Using similar energy sources, a standardized energy comparison provides an opportunity for estimation of weed control costs, suggesting site-specific weed management is critical in the economically realistic implementation of alternative technologies.

Harvest weed seed control (HWSC) is an Australian innovation, developed to target high proportions of weed seed retained at crop maturity by many major weed species. There is the potential, however, that a reduction in the average height of retained seed is an adaptation to the long-term use of HWSC practices. With the aim of examining the distribution of rigid ryegrass (Lolium rigidum Gaudin) seed through crop canopies, a survey of Australian wheat (Triticum aestivum L.) fields was conducted at crop maturity. Nine sites with medium to long-term HWSC use were specifically included to examine the influence of HWSC use on seed retention height. During the 2013 wheat harvest, L. rigidum and wheat plant samples were collected at five heights downward through the crop canopy (40, 30, 20, 10, and 0 cm above ground level) in 71 wheat fields. Increased crop competition resulted in higher proportions of L. rigidum seed in the upper crop canopy (>40 cm). The increase in plant height is likely a shade-intolerance response of L. rigidum plants attempting to capture more light. This plant attribute creates the opportunity to use crop competition to improve HWSC efficacy by increasing the average height of seed retention. Crop competition can, therefore, have a double impact by reducing overall L. rigidum seed production and increasing seed retention height. Examining the distribution of wheat biomass and L. rigidum seed through the crop canopy, we determined that reducing harvest height for HWSC considerably increased the collection of L. rigidum seed (25%) but to a lesser extent wheat crop biomass (14%). Comparison of + and − HWSC use at nine locations found no evidence of adaptation to this form of weed control following 5 to 10 yr of use. Although the potential for resistance to HWSC remains, these results indicate that this will not readily occur in the field.

Harvest weed seed control (HWSC) techniques have been implemented in Australian cropping systems to target and reduce the number of weed seeds entering the seedbank and thereby reduce the number of problematic weeds emerging in subsequent years to infest subsequent crops. However, the influence of HWSC on ameliorating herbicide-resistance (HR) evolution has not been investigated. This research used integrated spatial modeling to examine how the frequency and efficacy of HWSC affected the evolution of resistance to initially effective herbicides. Herbicides were, in all cases, better protected from future resistance evolution when their use was combined with annual HWSC. Outbreaks of multiple HR were very unlikely to occur and were nearly always eliminated by adding annual, efficient HWSC. The efficacy of the HWSC was important, with greater reductions in the number of resistance genes achieved with higher-efficacy HWSC. Annual HWSC was necessary to protect sequences of lower-efficacy herbicides, but HWSC could still protect herbicides if it was used less often than once per year, when the HWSC and the herbicides were highly effective. Our results highlight the potential benefits of combining HWSC with effective herbicides for controlling weed populations and reducing the future evolution of HR.

In Australia, widespread evolution of multi-resistant weed populations has driven the development and adoption of harvest weed seed control (HWSC). However, due to incompatibility of commonly used HWSC systems with highly productive conservation cropping systems, better HWSC systems are in demand. This study aimed to evaluate the efficacy of the integrated Harrington Seed Destructor (iHSD) mill on the seeds of Australia’s major crop weeds during wheat chaff processing. Also examined were the impacts of chaff type and moisture content on weed seed destruction efficacy. Initially, the iHSD mill speed of 3,000 rpm was identified as the most effective at destroying rigid ryegrass seeds present in wheat chaff. Subsequent testing determined that the iHSD mill was highly effective (>95% seed kill) on all Australian crop weeds examined. Rigid ryegrass seed kill was found to be highest for lupin chaff and lowest in barley, with wheat and canola chaff intermediate. Similarly, wheat chaff moisture reduced rigid ryegrass seed kill when moisture level exceeded 12%. The broad potential of the iHSD mill was evident, in that the reductions in efficacy due to wide-ranging differences in chaff type and moisture content were relatively small (≤10%). The results from these studies confirm the high efficacy and widespread suitability of the iHSD for use in Australian crop production systems. Additionally, as this system allows the conservation of all harvest residues, it is the best HWSC technique for conservation cropping systems.

Traditionally, personalised nutrition was delivered at an individual level. However, the concept of delivering tailored dietary advice at a group level through the identification of metabotypes or groups of metabolically similar individuals has emerged. Although this approach to personalised nutrition looks promising, further work is needed to examine this concept across a wider population group. Therefore, the objectives of this study are to: (1) identify metabotypes in a European population and (2) develop targeted dietary advice solutions for these metabotypes. Using data from the Food4Me study (n 1607), k-means cluster analysis revealed the presence of three metabolically distinct clusters based on twenty-seven metabolic markers including cholesterol, individual fatty acids and carotenoids. Cluster 2 was identified as a metabolically healthy metabotype as these individuals had the highest Omega-3 Index (6·56 (sd 1·29) %), carotenoids (2·15 (sd 0·71) µm) and lowest total saturated fat levels. On the basis of its fatty acid profile, cluster 1 was characterised as a metabolically unhealthy cluster. Targeted dietary advice solutions were developed per cluster using a decision tree approach. Testing of the approach was performed by comparison with the personalised dietary advice, delivered by nutritionists to Food4Me study participants (n 180). Excellent agreement was observed between the targeted and individualised approaches with an average match of 82 % at the level of delivery of the same dietary message. Future work should ascertain whether this proposed method could be utilised in a healthcare setting, for the rapid and efficient delivery of tailored dietary advice solutions.

Harvest weed seed control (HWSC) systems have been developed to exploit the high proportions of seed retained at maturity by the annual weeds rigid ryegrass, wild radish, bromegrass, and wild oats. To evaluate the efficacy of HWSC systems on rigid ryegrass populations, three systems, the Harrington Seed Destructor (HSD), chaff carts, and narrow-windrow burning were compared at 24 sites across the western and southern wheat production regions of Australia. HWSC treatments were established at harvest (Nov. – Dec.) in wheat crops with low to moderate rigid ryegrass densities (1 to 26 plants m−2). Rigid ryegrass counts at the commencement of the next growing season (Apr. – May) determined that HWSC treatments were similarly effective in reducing emergence. Chaff carts, narrow-windrow burning, or HSD systems act similarly on rigid ryegrass seed collected during harvest to deliver substantial reductions in subsequent rigid ryegrass populations by restricting seedbank inputs. On average, population densities were reduced by 60%, but there was considerable variation between sites (37 to 90%) as influenced by seed production and the residual seedbank. Given the observed high rigid ryegrass seed production levels at crop maturity it is clear that HWSC has a vital role in preventing seedbank inputs in Australian conservation cropping systems.

A large-plot field experiment was conducted at Keiser, AR, from fall of 2010 through fall of 2013 to understand to what extent soybean in-crop herbicide programs and postharvest fall management practices impact Palmer amaranth population density and seed production over three growing seasons. The effect of POST-only (glyphosate-only) or PRE followed by (fb) POST (glyphosate or glufosinate) + residual herbicide treatments were evaluated alone and in combination with postharvest management options of soybean residue spreading or soil incorporation, use of cover crops, windrowing with/without burning, and residue removal. Significant differences were observed between fall management practices on Palmer amaranth population density each fall. The use of cover crops and residue collection and removal fb the incorporation of crop residues into soil during the formation of beds were the most effective practices in reducing Palmer amaranth population. In contrast, the effects of fall management practices on Palmer amaranth seed production were inconsistent among years. The inclusion of a PRE herbicide application into the herbicide program significantly reduced Palmer amaranth population density and subsequent seed production each year when compared to the glyphosate-only program. Additionally, the glufosinate-containing residual program was superior to the glyphosate-containing residual program in reducing Palmer amaranth seed production. PRE fb POST herbicides resulted in significant decreases in the Palmer amaranth population density and seed production compared to POST application of glyphosate alone for all fall management practices, including the no-till practice. This study demonstrated that crop residue management such as chaff removal from the field, the use of cover crops, or seed incorporation during bed formation in combination with an effective PRE plus POST residual herbicide program is important for optimizing in-season management of Palmer amaranth and subsequently reducing the population density, which has a profound impact on lessening the risk for herbicide resistance and the consistency and effectiveness of future weed management efforts.

Seed production of annual weeds persisting through cropping phases replenishes/establishes viable seed banks from which these weeds will continue to interfere with crop production. Harvest weed seed control (HWSC) systems are now viewed as an effective means of interrupting this process by targeting mature weed seed, preventing seed bank inputs. However, the efficacy of these systems is directly related to the proportion of total seed production that the targeted weed species retains (seed retention) at crop maturity. This study determined the seed retention of the four dominant annual weeds of Australian cropping systems - annual ryegrass, wild radish, brome grass, and wild oat. Beginning at the first opportunity for wheat harvest and on a weekly basis for 28 d afterwards the proportion of total seed production retained above a 15 cm harvest cutting height was determined for these weed species present in wheat crops at nine locations across the Western Australian (WA) wheat-belt. Very high proportions of total seed production were retained at wheat crop maturity for annual ryegrass (85%), wild radish (99%), brome grass (77%), and wild oat (84%). Importantly, seed retention remained high for annual ryegrass and wild radish throughout the 28 d harvest period. At the end of this period, 63 and 79% of total seed production for annual ryegrass and wild radish respectively, was retained above harvest cutting height. However, seed retention for brome grass (41%) and wild oat (39%) was substantially lower after 28 d. High seed retention at crop maturity, as identified here, clearly indicates the potential for HWSC systems to reduce seed bank replenishment and diminish subsequent crop interference by the four most problematic species of Australian crops.