Herbicide-resistant weeds are fast becoming a substantial global problem, causing significant crop losses and food insecurity. Late detection of resistant weeds leads to increasing economic losses. Traditionally, genetic sequencing and herbicide dose-response studies are used to detect herbicide-resistant weeds, but these are expensive and slow processes. To address this problem, an artificial intelligence (AI)-based herbicide-resistant weed identifier program (HRIP) was developed to quickly and accurately distinguish common chickweed plants that are resistant to acetolactate synthase (ALS) inhibitor herbicides and those that are susceptible to ALS inhibitors. A regular camera was converted to capture light wavelengths from 300 to 1,100 nm. Full-spectrum images from a 2-yr experiment were used to develop a hyperparameter-tuned convolutional neural network model using a “train from scratch” approach. This novel approach exploits the subtle differences in the spectral signature of ALS inhibitor-resistant and ALS inhibitor-susceptible common chickweed plants as they react differently to the ALS-inhibiting herbicide treatments. The HRIP was able to identify ALS-inhibitor–resistant common chickweed as early as 72 h after treatment at an accuracy of 88%. It has broad applicability due to its ability to distinguish common chickweed plants that are resistant to ALS-inhibitor herbicides from those that are susceptible to becoming resistant to them regardless of the type of ALS herbicide or dose used. Using tools such as the HRIP will allow farmers to make timely interventions to prevent the herbicide-escape plants from completing their life cycle and adding to the weed seedbank.

Redweed is a tropical, erect branched herb, and one of the predominant broadleaf weeds affecting upland crops in the Onattukara Sandy Plains of Kerala, India. Experiments were conducted in a screenhouse in Thiruvananthapuram, Kerala, India, to determine the effects of seed burial depth and seed scarification on emergence indices and growth attributes of redweed. Scarification stimulated emergence and resulted in greater values for emergence indices and seedling parameters. The seedling emergence of redweed was influenced by seed burial depth. Shallow seed burial (2 cm) of scarified and non-scarified seeds resulted in greater seedling length (70 cm and 58 cm, respectively), seedling biomass (0.72 g and 0.48 g, respectively), emergence percentage (60% and 32%, respectively), and greater values for other emergence indices. As the depth of seed burial increased from 2 cm, emergence and seedling biomass decreased, exhibiting lower values for the emergence indices. Correlation and regression studies revealed that seed burial depth of scarified and non-scarified seeds greater than 2 cm had a negative effect on seedling emergence and biomass of redweed. Weed biology studies indicated that redweed displayed notable consistency in its phenological traits, regardless of the location where the seeds were collected, as little ecotype variability was observed. Emergence occurred in 6 d, 50% flowering in 44 d, capsule formation in 56 d, and maturity in 76 d. On average, a single plant produced 277 seeds and had a 100-seed weight of 0.31 g. A stale seedbed with shallow tillage or deep plowing to a depth of 10 cm before sowing can be adopted to reduce the infestation of redweed.

Cotton producers need residual herbicides that can safely and practically be applied postemergence. Herbicide-coated fertilizers could allow for simultaneous application of residual herbicides and a bulk fertilizer blend. Therefore, a study was conducted in 2022 and 2023 in Fayetteville, AR, to evaluate cotton tolerance to 12 herbicide treatments coated onto a fertilizer blend and applied over cotton. Herbicides and rates evaluated included diuron at 840 g ai ha−1, florpyrauxifen-benzyl at 29 g ai ha−1, flumioxazin at 105 g ai ha−1, flumioxazin + pyroxasulfone at 70 + 90 g ai ha−1, fluridone at 168 g ai ha−1, fluometuron at 840 g ai ha−1, fomesafen at 280 g ai ha−1, pyroxasulfone at 128 g ai ha−1, saflufenacil at 66 g ai ha−1, saflufenacil + dimethenamid-P at 25 + 219 g ai ha−1, saflufenacil + pyroxasulfone at 44 + 91 g ai ha−1, and S-metolachlor at 1,388 g ai ha−1. In both years, fluridone, fluometuron, diuron, and S-metolachlor caused less than 10% injury at 7 d after treatment (DAT). Higher injury levels were observed in 2022 (19% to 30%) compared with 2023 (4% to 12%) for flumioxazin, fomesafen, saflufenacil, saflufenacil plus dimethenamid-P, and saflufenacil + pyroxasulfone. The elevated injury in one of two years was attributed to the presence of dew when the herbicide-coated fertilizer was applied. The initial injury was transient, as the cotton generally had recovered by 28 DAT for all herbicides. No differences in seed cotton yield or groundcover among the herbicide treatments occurred either year. These results highlight the potential of using several postemergence-applied, residual herbicides coated onto fertilizer that are not currently registered for over-the-top use in cotton.