Weed management represents a critical challenge in agriculture, significantly impacting crop yields and requiring substantial resources for control. Effective weed monitoring and analysis strategies are crucial for implementing sustainable agricultural practices and site-specific management approaches. We introduce WeedSense, a novel multi-task learning architecture for comprehensive weed analysis that jointly performs semantic segmentation, height estimation, and growth stage classification. We present a unique dataset capturing 16 weed species over an 11-week growth cycle with pixel-level annotations, height measurements, and temporal labels. WeedSense leverages a dual-path encoder incorporating Universal Inverted Bottleneck blocks and a Multi-Task Bifurcated Decoder with transformer-based feature fusion to generate multi-scale features and enable simultaneous prediction across multiple tasks. WeedSense outperforms other state-of-the-art models on our comprehensive evaluation. On our multi-task dataset, WeedSense achieves mIoU of 89.78% for segmentation, 1.67cm MAE for height estimation, and 99.99% accuracy for growth stage classification while maintaining real-time inference at 160 FPS. Our multitask approach achieves 3$\times$ faster inference than sequential single-task execution and uses 32.4% fewer parameters. Please see our project page at weedsense.github.io.

Waterhemp (Amaranthus tuberculatus (Moq.) J. D. Sauer) is one of the most competitive and herbicide-resistant weed species in soybean cropping systems across North America. While its competitive and adaptive traits are well-documented, its role as an alternative host for plant pathogens remains underexplored. This review synthesizes current knowledge on fungal, bacterial, viral, and nematode pathogens that infect waterhemp and examines the ecological and management implications of these interactions. We discuss how waterhemp may serve as a reservoir for inoculum, potentially influencing disease dynamics in soybean under changing climate conditions. Furthermore, we assess the potential of host-specific pathogens as biological control agents within the integrated weed management (IWM) approach. Despite promising experimental results, several barriers limit large-scale adoption of bioherbicides, including environmental sensitivity, narrow host specificity, challenges in mass production, and regulatory constraints. Understanding weed–pathogen interactions could inform dual-purpose strategies that reduce both weed pressure and disease risk in soybean systems. Further research is needed to optimize biocontrol scalability, assess climate-driven epidemiological shifts, and develop robust integrated weed and disease management approaches.

Glufosinate-ammonium (GA) has been widely used in U.S. Midwest fields, and in recent years a growing number of failures to control waterhemp [ Amaranthus tuberculatus (Moq.) Sauer] have raised concerns about the evolution of resistance. The goal of this study was to investigate four cases of suspected resistance to GA in A. tuberculatus from Illinois using greenhouse, field, and transcriptomics studies. Greenhouse dose–response experiments revealed resistance ratios ranging from 2.2-to 3.4-fold based on survival and 1.3-to 2.8-fold based on biomass relative to a susceptible population. A subsequent field study where one of the populations originated confirmed that 20% of treated plants survived the labeled GA field recommended rate. Screening with other herbicide site-of-action groups revealed that most populations showed reduced sensitivity to atrazine, glyphosate, and imazethapyr, surviving up to 3× the field recommended rates, and to a lesser extent, lactofen and fomesafen. Transcriptomic analysis of plants surviving GA revealed no resistance-associated mutations or differential transcript abundance in the plastidic and cytosolic isoforms of glutamine synthetase. Among the four suspected resistant populations, there were 182 genes differentially expressed relative to two susceptible populations. Different sets of genes were differentially expressed among the populations studied, with only one gene (upregulated relative to two susceptible populations) shared among all four. Many of the differentially expressed genes, including cytochrome P450s, glutathione S -transferases, glycosyltransferases, transporters, and transcriptional regulators, are commonly associated with metabolic resistance. Gene ontology enrichment analyses indicated significant overrepresentation of stress response, defense regulation, and secondary metabolism categories across the populations. Together, these findings provide evidence for the evolution of GA resistance in populations of A. tuberculatus in Illinois. While more in-depth studies are needed to fully characterize the underlying mechanisms, the consistent differential expression of metabolism-related genes and no indication of target-site mechanisms point to a potential metabolic basis for resistance.

Glufosinate-ammonium (GA) has been widely used in Midwestern fields, and in recent years a growing number of failures to control waterhemp [ Amaranthus tuberculatus (Moq.) Sauer] have raised concerns about the potential evolution of resistance. The goal of this study was to investigate four independent cases of suspected resistance to GA in A. tuberculatus from Illinois using greenhouse, field, and transcriptomics studies. Greenhouse dose-response experiments revealed resistance ratios ranging from 2.2- to 3.4-fold based on survival and from 1.3- to 2.8-fold based on dry biomass relative to a susceptible population. A subsequent field study where one of the populations originated confirmed that twenty percent of treated plants survived the labeled GA field-recommended rate. Screening for other herbicide sites of action revealed that most populations showed reduced sensitivity to atrazine, glyphosate, and imazethapyr, surviving up to three times the field-recommended rates, and to a lesser extent, lactofen and fomesafen. Transcriptomic analysis of plants surviving GA revealed no resistance-associated mutations or differential transcript abundance in the plastidic and cytosolic isoforms of glutamine synthetase. Among the four suspected resistant populations, there were 182 genes differentially expressed relative to two susceptible populations. Different sets of genes were differentially expressed among the populations studied, with only one gene (upregulated relative to two susceptible populations) shared among all four. Many of the differentially expressed genes, including cytochrome P450s, glutathione S -transferases, glycosyltransferases, transporters, and transcriptional regulators, are commonly associated with metabolic resistance. Gene ontology enrichment analyses indicated significant overrepresentation of stress response, defense regulation, and secondary metabolism categories across the populations. Together, these findings provide evidence for the evolution of GA resistance in populations of A. tuberculatus in Illinois. While more in-depth studies are needed to fully characterize the underlying mechanisms, the consistent differential expression of metabolism-related genes and no indication of target-site mechanisms points to a potential metabolic basis for resistance.