In small-plot experiments, weed scientists have traditionally estimated herbicide efficacy through visual assessments or manual counts with wooden frames—methods that are time-consuming, labor-intensive, and error-prone. This study introduces a novel mobile application (app) powered by convolutional neural networks (CNNs) to automate the evaluation of weed coverage in turfgrass. The mobile app automatically segments input images into 10 by 10 grid cells. A comparative analysis of EfficientNet, MobileNetV3, MobileOne, ResNet, ResNeXt, ShuffleNetV1, and ShuffleNetV2 was conducted to identify weed-infested grid cells and calculate weed coverage in bahiagrass (Paspalum notatum Flueggé), dormant bermudagrass [Cynodon dactylon (L.) Pers.], and perennial ryegrass (Lolium perenne L.). Results showed that EfficientNet and MobileOne outperformed other models in detecting weeds growing in bahiagrass, achieving an F1 score of 0.988. For dormant bermudagrass, ResNet performed best, with an F1 score of 0.996. Additionally, app-based coverage estimates (11%) were highly consistent with manual assessments (11%), showing no significant difference (P = 0.3560). Similarly, ResNeXt achieved the highest F1 score of 0.996 for detecting weeds growing in perennial ryegrass, with app-based and manual coverage estimates also closely aligned at 10% (P = 0.1340). High F1 scores across all turfgrass types demonstrate the models’ ability to accurately replicate manual assessments, which is essential for herbicide efficacy trials requiring precise weed coverage data. Moreover, the time for weed assessment was compared, revealing that manual counting with 10 by 10 wooden frames took an average of 39.25, 37.25, and 42.25 s per instance for bahiagrass, dormant bermudagrass, and perennial ryegrass, respectively, whereas the app-based approach reduced the assessment times to 8.23, 7.75, and 14.96 s, respectively. These results highlight the potential of deep learning–based mobile tools for fast, accurate, scalable weed coverage assessments, enabling efficient herbicide trials and offering labor and cost savings for researchers and turfgrass managers.

Furrow-irrigated rice (Oryza sativa L.) hectares are increasing in the Midsouth. The lack of sustained flooding creates a favorable environment for weed emergence and persistence, which makes Palmer amaranth (Amaranthus palmeri S. Watson) difficult to control throughout the growing season. The negative yield impacts associated with season-long A. palmeri interference in corn (Zea mays L.), cotton (Gossypium hirsutum L.), and soybean [Glycine max (L.) Merr.] have been evaluated. However, there is limited knowledge of the weed’s ability to influence rice grain yield. Research was initiated in 2022 and 2023 to determine the effect of A. palmeri time of emergence relative to rice on weed seed production and grain yield. Cotyledon-stage A. palmeri plants were marked every 7 d, beginning 1 wk before rice emergence through 4 wk after rice emergence. Amaranthus palmeri seed production decreased exponentially as emergence timing was delayed relative to rice, and seed production increased by 447 seed plant−1 for every 1-g increase in weed biomass. Without rice competition and from the earliest emergence timing, A. palmeri produced 540,000 seeds plant−1. Amaranthus palmeri that emerged 1 wk before the crop had the greatest spatial influence on rice, with grain yield loss of 5% and 50% at a distance of 1.4 m and 0.40 m from the weed, respectively. As A. palmeri emergence was delayed, the area of influence decreased. However, A. palmeri plants emerging 3.5 wk after rice emergence still negatively affected grain yield and produced sufficient seed to replenish the soil seedbank, potentially impacting long-term crop management decisions. These results show that the time of A. palmeri emergence is a crucial factor influencing rice grain yield and weed seed production, which can be used to determine the consequences of escapes in rice.

Typically, weed density is used to predict weed-induced yield loss, as it is easy and quick to quantify, even though it does not account for weed size and time of emergence relative to the crop. Weed–crop leaf area relations, while more difficult to measure, inherently account for differences in plant size, representing weed–crop interference more accurately than weed density alone. Unmanned aerial systems (UASs) may allow for efficient quantification of weed and crop leaf cover over a large scale. It was hypothesized that UAS imagery could be used to predict maize (Zea mays L.) yield loss based on weed–crop leaf cover ratios. A yield loss model for maize was evaluated for accuracy using 15- and 30-m-altitude aerial red–green–blue and four-band multispectral imagery collected at four North Carolina locations. The model consistently over- and underpredicted yield loss when observed yield loss was less than and greater than 3,000 kg ha−1, respectively. Altitude and sensor type did not influence the accuracy of the prediction. A correction for the differences between predicted and observed yield loss was incorporated into the linear model to improve overall precision. The correction resulted in r2 increasing from 0.17 to 0.97 and a reduction in root mean-square error from 705 kg ha−1 to 219 kg ha−1. The results indicated that UAS images can be used to develop predictive models for weed-induced yield loss before canopy closure, making it possible for growers to plan production and financial decisions before the end of the growing season.

Echinochloa crus-galli var. crus-galli (L.) P. Beauv. (EC), Echinochloa crus-galli var. mitis (Pursh) Petermann (ECM), and Echinochloa glabrescens Munro ex Hook. f. (EG) are all serious rice (Oryza sativa L.) weeds that are usually treated as a single species in weed management practices. To determine interspecific and intraspecific differences in seed germination responding to different temperatures among the three Echinochloa weeds, we conducted field surveys and collected 66 EC, 141 ECM, and 120 EG populations from rice fields of East China in 2022; and tested their seed germination under 28/15 C (day/night), 30/20 C, and 35/25 C regimes, simulating temperatures of rice-planting periods for double-cropping early rice, single-cropping rice, and double-cropping late rice, respectively. In EC, ECM, and EG, seed percentage germination (cumulative percentage of germinated seed) and germination index (sum of the ratio of germinated seeds to the corresponding days) increased with increasing temperatures. At 28/15 C, the average percentage germination of EC populations (67.5%) was significantly (P < 0.05) higher compared with ECM (46.4%) and EG (43.7%); GD50 (duration for 50% total germination) for EC populations (5.2 d) was significantly shorter compared with ECM (5.9 d) and EG (5.8 d). At 35/25 C, the percentage germinations of EC (90.7%), ECM (80.5%), and EG (80.3%) were all significantly the highest among the three temperature treatments, respectively, and the GD50 values for EC (2.5 d), ECM (2.6 d), and EG (2.7 d) were all significantly the lowest. At 30/20 C and 35/25 C, the average germination percentages of populations collected from transplanted rice fields were significantly higher than those of populations collected from direct-seeded rice fields. Moreover, among EG populations, the longitudes and latitudes of collection locations were significantly correlated with seed percentage germination and germination indices. According to the interspecific differences and intraspecific variations of Echinochloa species, weed management strategies should also be customized according to the species and population characteristics in seed germination.

Integrating cover crops (CCs) in dryland crop rotations could help in controlling herbicide-resistant weeds. Field experiments were conducted at Kansas State University Agricultural Research Center near Hays, KS, from 2020 to 2023 to determine the effect of fall-planted CCs on weed suppression in grain sorghum [Sorghum bicolor (L.) Moench], crop yield, and net returns in no-till dryland winter wheat (Triticum aestivum L.)–grain sorghum–fallow (W-S-F) rotation. The field site had a natural seedbank of glyphosate-resistant (GR) kochia [Bassia scoparia (L.) A. J. Scott] and Palmer amaranth (Amaranthus palmeri S. Watson). A CC mixture [winter triticale (×Triticosecale Wittm. ex A. Camus [Secale × Triticum])–winter peas (Pisum sativum L.)–canola (Brassica napus L.)–radish (Raphanus sativus L.)] was planted after wheat harvest and terminated at triticale heading stage before sorghum planting. Treatments included nontreated control, chemical fallow, CC terminated with glyphosate (GLY), and CC terminated with GLY+ acetochlor/atrazine (ACR/ATZ). Across 3 yr, CC terminated with GLY+ACR/ATZ reduced total weed density by 34% to 81% and total weed biomass by 45% to 73% compared with chemical fallow during the sorghum growing season. Average grain sorghum yield was 786 to 1,432 kg ha−1 and did not differ between chemical fallow and CC terminated with GLY+ACR/ATZ. However, net returns were lower with both CC treatments (−US$275 to US$66) in all 3 yr compared with chemical fallow (−US$111 to US$120). These results suggest that fallow replacement with fall-planted CCs in the W-S-F rotation can help suppress GR B. scoparia and A. palmeri in the subsequent grain sorghum. However, the cost of integrating CCs exceeded the benefits of improved weed control, and lower net returns were recorded in all 3 yr compared with chemical fallow.

The rapid and efficient removal of weeds is currently a research hotspot. With the integration of robotics and automation technology into agricultural production, intelligent field-weeding robots have emerged. An overview of the development status of weeding robots based on bibliometric and scientific mapping methods is presented. Two key technologies of weeding robots are summarized, and the research progress of precision-spraying weeding robots, mechanical weeding robots, and thermal weeding robots with laser devices, categorized by weeding method, is reviewed. Finally, a summary and an outlook on the future development trends of intelligent field-weeding robots are provided, aiming to offer a reference for further promoting the development of weeding robots.

Kochia [Bassia scoparia (L.) A.J. Scott] is an invasive tumbleweed in the North American Great Plains that is difficult to manage in croplands and ruderal areas due to widespread resistance to up to four herbicide sites of action, including auxin mimics (Herbicide Resistance Action Committee [HRAC] Group 4) and inhibitors of acetolactate synthase (HRAC Group 2), photosystem II (HRAC Group 5), and 5-enolpyruvylshikimate-3-phosphate synthase (HRAC Group 9). Poor B. scoparia control with protoporphyrinogen oxidase (PPO)-inhibiting (HRAC Group 14) herbicides was noted in a brown mustard [Brassica juncea (L.) Czern.] field near Kindersley, SK, Canada, in 2021. Similar observations were made in a sunflower (Helianthus annuus L.) field near Mandan, ND, USA, and in research plots near Minot, ND, USA, in 2022. Whole-plant dose–response experiments were conducted to determine whether these B. scoparia accessions were resistant to the PPO-inhibiting herbicides saflufenacil and carfentrazone and the level of resistance observed. All three B. scoparia accessions were highly resistant to foliar-applied saflufenacil and carfentrazone compared with two locally relevant susceptible accessions. The Kindersley accession exhibited 57- to 87-fold resistance to saflufenacil and 97- to 121-fold resistance to carfentrazone based on biomass dry weight at 21 d after treatment (DAT). Similarly, the Mandan accession exhibited 204- to 321-fold resistance to saflufenacil and 111- to 330-fold resistance to carfentrazone, while the Minot accession exhibited 45- to 71-fold resistance to saflufenacil and 88- to 264-fold resistance to carfentrazone. Substantial differences in visible control at 7 and 21/28 DAT were also observed between the putative-resistant and susceptible accessions. This study represents the first confirmations of PPO inhibitor–resistant B. scoparia globally and the fifth herbicide site of action to which B. scoparia has evolved resistance. It also documents this issue present at three locations in the Northern Great Plains region that occur up to 790 km apart and on both sides of the Canada/U.S. border.

Herbicide-resistant weeds threaten modern agriculture production. In Michigan, horseweed [Erigeron canadensis L.; syn.: Conyza canadensis (L.) Cronq.] is among the most troublesome weeds, and glyphosate was widely used to control E. canadensis. Due to extreme selection pressure imposed by heavy glyphosate usage, glyphosate-resistant E. canadensis is widespread. New technologies to control resistant E. canadensis are being introduced in the form of multiple herbicide resistance traits integrated into glyphosate-resistant soybean [Glycine max (L.) Merr.] (e.g., dicamba or 2,4-D choline). These new soybean varieties will likely increase the use of 2,4-D and dicamba, thus increasing the resistance selection pressure in E. canadensis. Predicting agronomic factors that drive herbicide-resistance evolution can serve as an effective proactive tool to advise practitioners to modify management strategies. Therefore, the objectives of this study are: (1) conduct dose–response assays to assess the current resistance spectrum of E. canadensis collected in Michigan and (2) predict and determine the main factors in row-crop production that contribute to resistance evolution in these accessions. Dose–response assays were conducted to evaluate the herbicide sensitivity spectrum to glyphosate, dicamba, and 2,4-D in 20 E. canadensis accessions collected from eight Michigan counties. Out of the 20 accessions, 60% were resistant to glyphosate, 35% to 2,4-D, and 20% to dicamba. Pearson’s correlation coefficient of dose–response values was positive in all comparisons (2,4-D-dicamba, r = 0.35; dicamba-glyphosate, r = 0.15; 2,4-D-glyphosate, r = 0.21). Dose–response data were integrated in odds ratio analyses to access the influence that previous management history had on the occurrence of resistance. Out of the significant pairwise comparisons, 44% were related to crop rotation frequency, 33% to previous herbicide-resistance status, and 22% to location where collected. Results highlight that growers have the ability to proactively manage herbicide-resistance evolution progression of E. canadensis in Michigan by adopting integrated weed management techniques to slow successive selection events that occur in low-diversity management systems.

Weed-suppression benefits of cover crops (CCs) have long been recognized; however, the specific ability of CCs to suppress highly epidemic Amaranthus spp. (Palmer amaranth (Amaranthus palmeri S. Watson), redroot pigweed (Amaranthus retroflexus L.), smooth pigweed (Amaranthus hybridus L.), and waterhemp [Amaranthus tuberculatus (Moq.) Sauer]) has not been widely discussed. The objective of this meta-analysis was to evaluate the implications of CC management decisions (CC type, planting and termination methods, residue fate after termination, and in-season weed management plan) on Amaranthus spp. weed density (ASWD) and Amaranthus spp. weed biomass (ASWB) compared with no CC (NCC) in temperate regions, including the United States and Canada. We found 41 studies conducted across the United States and Canada and extracted 595 paired observations. The results indicate that CCs reduced the ASWD by 58% in the early season (0 to 4 wk after crop planting [WAP]), by 48% in the midseason (5 to 8 WAP), and by 44% in the late season (>8 WAP). Similarly, CCs reduced ASWB by 59%, 55%, and 37% in the early, mid-, and late season, respectively. Meta-regression analysis showed CCs terminated within 2.5 wk of crop planting reduced ASWD by ≥50%. CC biomass required to reduce ASWD and ASWB by 50% was 4,079 kg ha−1 for ASWD and 5,352 kg ha−1 for ASWB. Among CC types, grasses and mixtures reduced ASWD by 60% and 77% in early season, 53% and 59% in midseason, and 44% and 47% in late season. Legume CCs were effective only during the early season (47% ASWD reduction), while brassicas did not affect ASWD. CC residues remaining on the soil surface were more effective for reducing ASWD than incorporation. CCs did not affect ASWD or ASWB compared with NCC when herbicides were used for in-season weed management. In general, CCs were found to reduce ASWD and ASWB and therefore can be used as an effective tool for integrated management of Amaranthus spp.

Yellow nutsedge (Cyperus esculentus L.) is one of the most problematic weeds in turfgrass due to its fast growth rate and high tuber production. Effective long-term control relies on translocation of systemic herbicides to underground tubers. Two identical trials were conducted simultaneously in separate greenhouses to evaluate the effect of several acetolactate synthase (ALS)- and protoporphyrinogen oxidase (PPO)-inhibiting postemergence herbicides on C. esculentus tuber production and viability. Seven tubers were planted into 1-L pots, and plants were allowed to mature for 6 wk before trial initiation. Treatments included pyrimisulfan at 73 g ai ha−1 once or 49 g ai ha−1 twice, imazosulfuron at 736 g ai ha−1 once or 420 g ai ha−1 twice, carfentrazone-ethyl + sulfentrazone at 22 + 198 g ai ha−1 once or 14 + 127 g ai ha−1 twice, halosulfuron at 70 g ai ha−1 once or 35 g ai ha−1 twice, and a nontreated control. Sequential applications were made 3 wk after initial treatment (WAIT) for both trials. Both single and sequential applications of carfentrazone-ethyl + sulfentrazone exhibited the quickest control (80% to 83% 4 WAIT). Two applications of imazosulfuron resulted in the greatest reduction in tuber number (81%) and tuber dry biomass (85%), while one application of carfentrazone-ethyl + sulfentrazone resulted in the greatest reduction in shoot biomass (71%). The viability of tubers that were recovered from each pot was reduced 48% to 70%, with the greatest reduction in response to carfentrazone-ethyl + sulfentrazone. Although two applications of pyrimisulfan only resulted in tuber number and shoot biomass reductions of 66% and 38%, respectively, tuber dry biomass reduction was 80%. Therefore, pyrimisulfan, imazosulfuron, halosulfuron, and carfentrazone-ethyl + sulfentrazone are all viable options for long-term C. esculentus control in turfgrass.

Trifludimoxazin is a protoporphyrinogen oxidase (PPO)-inhibiting herbicide currently under development for preplant burndown and soil-residual weed control in soybean [Glycine max (L.) Merr.] and other crops. Greenhouse dose–response experiments with foliar applications of trifludimoxazin, fomesafen, and saflufenacil were conducted on susceptible and PPO inhibitor–resistant (PPO-R) waterhemp [Amaranthus tuberculatus (Moq.) Sauer] and Palmer amaranth (Amaranthus palmeri S. Watson) biotypes. These PPO-R biotypes contained the PPO2 target-site (TS) mutations ΔG210 (A. tuberculatus and A. palmeri), R128G (A. tuberculatus), and V361A (A. palmeri). The resistant/susceptible (R/S) ratios for fomesafen and saflufenacil ranged from 2.0 to 9.2 across all PPO-R biotypes. In contrast, the response of known PPO inhibitor–susceptible and PPO-R biotypes to trifludimoxazin did not differ within each Amaranthus species. In 2017 and 2018, experiments at the Meigs and Davis Purdue Agriculture Centers were conducted in fields with native A. tuberculatus populations composed of 3% and 30% PPO-R plants (ΔG210 mutation), respectively. At Meigs in 2018, A. tuberculatus control following foliar applications of fomesafen, lactofen, saflufenacil, and trifludimoxazin was greater than 95%. When averaged across the other 3 site-years, applications of 25 g ai ha−1 trifludimoxazin resulted in 95% control of A. tuberculatus at 28 DAA, while applications of fomesafen (343 g ai ha−1), lactofen (219 g ai ha−1), or saflufenacil (25.0 or 50 g ai ha−1), resulted in 80% to 88% control. Thus, at these relative application rates, the foliar efficacy of trifludimoxazin was comparable or greater on A. tuberculatus when compared with other commercial PPO inhibitors, even in populations where low frequencies of PPO-R plants exist. The lack of cross-resistance for common PPO2 TS mutations to trifludimoxazin and the level of foliar field efficacy observed on populations containing PPO-R individuals suggest that trifludimoxazin may be a valuable herbicide in an integrated approach for managing herbicide-resistant Amaranthus weeds.

Johnsongrass [Sorghum halepense (L.) Pers.], an invasive tallgrass, actively inhabits grassland ecosystems of North America. The grasslands ecoregions of the Southern Great Plains are particularly susceptible to S. halepense invasion and dominance because of its preferential growth in continental climate zones coupled with its ability to readily colonize recent disturbances associated with declining livestock grazing and anthropogenic energy and housing development. Controlling S. halepense via chemical or mechanical inputs can reduce this plant species’ abundance temporarily, but are typically followed by S. halepense reestablishment. Sorghum halepense does, however, provide high-quality forage and appears to withstand the frequent drought and flooding events associated with climate change in Southern Great Plains ecosystems. In this review, the benefits and drawbacks of S. halepense in Southern Great Plains grassland ecosystems are discussed and areas where research on this species could be expanded are identified.

Foliar-applied postemergence applications of glufosinate are often applied to glufosinate-resistant crops to provide nonselective weed control without significant crop injury. Rainfall, air temperature, solar radiation, and relative humidity near the time of application have been reported to affect glufosinate efficacy. However, previous research may have not captured the full range of weather variability to which glufosinate may be exposed before or following application. Additionally, climate models suggest more extreme weather will become the norm, further expanding the weather range to which glufosinate can be exposed. The objective of this research was to quantify the probability of successful weed control (efficacy ≥85%) with glufosinate applied to some key weed species across a broad range of weather conditions. A database of >10,000 North American herbicide evaluation trials was used in this study. The database was filtered to include treatments with a single postemergence application of glufosinate applied to waterhemp [Amaranthus tuberculatus (Moq.) Sauer], morningglory species (Ipomoea spp.), and/or giant foxtail (Setaria faberi Herrm.) <15 cm in height. These species were chosen because they are well represented in the database and listed as common and troublesome weed species in both corn (Zea mays L.) and soybean [Glycine max (L.) Merr.] (Van Wychen 2020, 2022). Individual random forest models were created. Low rainfall (≤20 mm) over the 5 d before glufosinate application was detrimental to the probability of successful control of A. tuberculatus and S. faberi. Lower relative humidity (≤70%) and solar radiation (≤23 MJ m−1 d−1) on the day of application reduced the probability of successful weed control in most cases. Additionally, the probability of successful control decreased for all species when average air temperature over the first 5 d after application was ≤25 C. As climate continues to change and become more variable, the risk of unacceptable control of several common species with glufosinate is likely to increase.

Established hedgerows of native plants on the borders of crop fields provide a variety of ecosystem service benefits in agricultural landscapes. However, their influence on weed communities is not well understood, and there are concerns that hedgerows could contribute to weed infestations on farms. To address this research gap, we examined the role of established hedgerows of native California plants on weed abundance (weed numbers and cover) and weed species richness in field borders, and in adjacent crops, in large-scale, monocropping systems compared with conventionally managed field borders (i.e., no hedgerows). Across 20 farm sites in California’s Central Valley, hedgerows on orchard crop borders reduced weed numbers by 66%, weed species richness by 59%, and weed cover by 74%. On annual field crop borders, hedgerows reduced weed numbers by 71%, weed species richness by 60%, and weed cover by 70%. In orchards, hedgerows also reduced weed intrusion into the adjacent crop interior, with significantly lower weed cover to the first tree row (area directly underneath the trees), weed species richness to the 10-m tree row, and weed numbers to the 10-m avenue (area between the tree rows). Yearly management practices and associated costs for weed control in established hedgerows were significantly less than for conventionally managed field borders. This study highlights the effectiveness of native hedgerows as a sustainable nature-based solution for reducing weed pressure and management inputs on farms.

Barnyardgrass [Echinochloa crus-galli (L.) P. Beauv.] is a dominant weed species occurring in rice (Oryza sativa L.) fields across China. Metamifop, a common herbicide, is frequently applied to control E. crus-galli and other grassy weeds in rice fields. Herein, HS01, an E. crus-galli population suspected to be resistant (R) to metamifop, was collected from Hanshan County in Anhui Province, China. Whole-plant dose–response testing revealed that, compared with the susceptible (S) population FD03, HS01 had developed high-level resistance to metamifop with a resistance index (RI) of 11.76 and showed cross-resistance to cyhalofop-butyl (RI = 9.33), fenoxaprop-P-ethyl (RI = 5.80) and clethodim (RI = 3.24). Gene sequencing revealed a Cys-2088-Arg mutation in the ACCase 1,5 allele of all the R plants, while ACCase gene overexpression was not involved in the resistance. Molecular docking indicated that the less-negative binding energies might be the main reason for the resistance of HS01 to acetyl-CoA carboxylase (ACCase)-inhibiting herbicides. A derived cleaved amplified polymorphic sequence (dCAPS) method was developed for the rapid identification of the Cys-to-Arg mutation in the ACCase gene at codon position 2088 in E. crus-galli. Additionally, pretreatment with the cytochrome P450 inhibitor piperonyl butoxide or the glutathione S-transferase inhibitor 4-chloro-7-nitrobenzoxadiazole had no significant effects (P > 0.05) on the resistance of HS01 to metamifop. To our knowledge, this is the first report of a Cys-2088-Arg mutation in E. crus-galli ACCase that confers cross-resistance to ACCase-inhibiting herbicides.

Weed infestations have been identified as a major cause of yield reductions in canola (Brassica napus L.), a vital oil crop that has gained significant prominence in Iran, especially within Fars Province. Weed management using machine learning algorithms has become a crucial approach within the framework of precision agriculture for enhancing the efficacy and efficiency of weed control strategies. The evolution of habitat suitability models for weeds represents a significant advancement in agricultural technology, offering the capability to predict weed occurrence and proliferation accurately and reliably. This study focuses on the issue of dominant weed infestation in canola cultivation, particularly emphasizing the prevalence and impact of wild oat (Avena fatua L.) as the dominant weed species in canola farming in 2023. We collected data on 12 environmental variables related to topography, climate, and soil properties to develop habitat suitability models. Three machine learning techniques, including random forest (RF), support vector machine (SVM), and boosted regression tree (BRT), were estimated based on the receiver operating characteristic (ROC) and area under the curve (AUC) to model the distribution of A. fatua. Model performance was quantified using the ROC curve and AUC metrics to identify the best predictive algorithm. The findings indicated that RF, BRT, and SVM models exhibited accuracies of 99%, 97%, and 96% for the habitat suitability of A. fatua, respectively. The Boruta feature selection method identified the slope variable as significantly influential in A. fatua habitat suitability modeling, followed by plan curvature, clay, temperature, and silt. This study serves as a case study that highlights the utility of machine learning for habitat suitability predictions when information on multiple environmental variables is available. This approach supports effective weed management strategies, potentially enhancing canola productivity and mitigating the ecological impacts associated with weed infestation.

Interseeding alfalfa (Medicago sativa L.) into corn (Zea mays L.) is a novel approach that increases the production of high-quality forage and reduces the risk of nutrient and soil loss from cropland. Annual grass weeds like yellow foxtail [Setaria pumila (Poir.) Roem. & Schult.] can reduce the success of alfalfa establishment and are difficult to manage in the interseeding system. This study evaluated ground cover, fall biomass, and fall plant density of interseeded alfalfa in response to varying populations of S. pumila. Our goal was to identify a threshold for initiating control of annual grasses to ensure good establishment of alfalfa in this intercropping system. Ground cover of interseeded alfalfa growing under corn declined as S. pumila density increased from 0 to 125 plants m−2 in July, August, and October with the sharpest decline in August (up to a 70% reduction in alfalfa cover). This reduction in ground cover was associated with a decline in postestablishment shoot and root mass and a reduction in alfalfa plant density from 246 to 146 plants m−2 in October. Results suggest that June S. pumila populations should be kept to less than 50 plants m−2 to obtain recommended fall alfalfa densities of 200 plants m−2 that are needed to maximize alfalfa yield the following year. This research provides crucial information to practitioners on when annual grass management is needed to ensure successful alfalfa establishment in this interseeded system.

Efficient chemical weed management considers precise application of herbicides, maximizing herbicide retention and absorption, reducing the impact of abiotic factors, and mitigating off-target movement in order to optimize herbicide efficacy. Hence, this study assessed the employability and cost-efficiency of an unmanned aerial vehicle (UAV) for preplanting application and postemergence selective weed control of grasses infesting legume cover crops (LCCs) in an immature oil palm (Elaeis guineensis Jacq.) plantation. Field experiments were conducted in 2020 and 2021 at a research center and an oil palm replanting area in Jerantut, Pahang, Malaysia. Droplet deposition and distribution analyses revealed that the pressure at 0.25 MPa yielded better spray coverage and increased droplet counts compared with 0.15 MPa. For preplanting application, both the UAV and mist blower resulted in total weed control. Meanwhile for selective grass control in the LCCs, conventional knapsack sprayer (CKS) application provided slightly better weed control than the UAV over the 12-wk observation. However, a cost-efficiency analysis revealed that UAV spraying yielded economically favorable results for areas greater than 3,000 ha, with potential savings ranging from 4% to 28%. Furthermore, UAV spraying demonstrated superior operational efficiency and reduced working hours by 37%, water consumption by 91%, and human labor expenses by 81% compared with both conventional methods. These findings underscore the potential of UAV-based spraying for large-scale weed control in oil palm plantations and highlight its efficiency, comparable effectiveness, and cost-saving benefits.

Herbaceous perennials must annually rebuild the aboveground photosynthetic architecture from carbohydrates stored in crowns, rhizomes, and roots. Knowledge of carbohydrate utilization and storage can inform management decisions and improve control outcomes for invasive perennials. We monitored the nonstructural carbohydrates in a population of the hybrid Bohemian knotweed [Polygonum ×bohemicum (J. Chrtek & Chrtková) Zika & Jacobson [cuspidatum × sachalinense]; syn.: Fallopia ×bohemica (Chrtek and Chrtková) J.P. Bailey] and in Japanese knotweed [Polygonum cuspidatum Siebold & Zucc.; syn.: Fallopia japonica (Houtt.) Ronse Decr.]. Carbohydrate storage in crowns followed seasonal patterns typical of perennial herbaceous dicots corresponding to key phenological events. Starch was consistently the highest nonstructural carbohydrate present. Sucrose levels did not show a consistent inverse relationship with starch levels. Lateral distribution of starch in rhizomes and, more broadly, total nonstructural carbohydrates sampled before dormancy break showed higher levels in rhizomes compared with crowns. Total nonstructural carbohydrate levels in crowns reached seasonal lows at an estimated 22.6% of crown dry weight after accumulating 1,453.8 growing degree days (GDD) by the end of June, mainly due to depleted levels of stored starch, with the estimated minimum of 12.3% reached by 1,220.3 GDD accumulated by mid-June. Depletion corresponded to rapid development of vegetative canopy before entering the reproductive phase in August. Maximum starch accumulation in crowns followed complete senescence of aboveground tissues by mid- to late October. Removal of aboveground shoot biomass in late June to early July with removal of vegetation regrowth in early September before senescence would optimize the use of time and labor to deplete carbohydrate reserves. Additionally, foliar-applied systemic herbicide translocation to belowground tissue should be maximized with applications in late August through early fall to optimize downward translocation with assimilate movement to rebuild underground storage reserves. Fall applications should be made before loss of healthy leaf tissue, with the window for control typically ending by late September in Minnesota.

The commercialization of a three-way transgenic sugar beet cultivar, engineered for resistance to glyphosate, glufosinate, and dicamba (hereafter referred to as “triple-stacked”) is anticipated by the mid-2020s. While offering potential benefits for growers facing glyphosate resistance, two of three herbicides (dicamba and glyphosate) to be utilized with triple-stacked sugar beet (Beta vulgaris L.) have previously been used on major weeds in western U.S. cropping systems, raising concerns about preexisting resistance to these active ingredients. We conducted a field survey in sugar beet–growing counties of southeast Montana and northwest Wyoming in fall 2021, before the sugar beet harvest. We collected kochia [Bassia scoparia (L.) A.J. Scott], redroot pigweed (Amaranthus retroflexus L.), and common lambsquarters (Chenopodium album L.) populations and screened them for glyphosate, glufosinate, and dicamba resistance in greenhouse conditions. Our results showed two-way resistance (glyphosate and dicamba) in 32% of B. scoparia populations and reduced susceptibility to glyphosate in 78% of C. album populations. Additionally, we conducted a greenhouse experiment to assess the emergence patterns of collected populations. Phylogenetically closely related B. scoparia and C. album showed higher resemblance in emergence pattern than the distant relative A. retroflexus. While the majority of B. scoparia and C. album populations emerged in <20 d (time required to reach 90% emergence [E90] < 20 d], A. retroflexus populations required >30 d to reach E90. Widespread glyphosate and dicamba resistance in B. scoparia populations raises concerns about the long-term feasibility of a triple-stacked sugar beet cultivar. Furthermore, the delayed emergence of A. retroflexus may enable it to evade early-season weed management.