Tall fleabane [Conyza sumatrensis (Retz.) E. Walker] is commonly invasive in agricultural fields, reducing yield in various infested crops. The current study investigates the genetic diversity within and between a significant number of invasive C. sumatrensis biotypes in soybean fields in southern, southeastern, and midwestern Brazil, using microsatellites as molecular markers. High and low observed and expected heterozygosity estimated in microsatellite loci supported our hypothesis that different levels of genetic diversity may be detected within biotypes from different invaded fields. Analysis of a significant number of biotypes in several fields showed high and low genetic diversity not associated with geographic distribution, bottleneck effect, or susceptibility to glyphosate. A deficit of heterozygous plants, high genetic divergence, and moderate allelic transference were also observed. Allelic fixation was different in the different biotypes. The bottleneck effect was seen in biotypes with reduced genetic diversity and in biotypes with the highest genetic diversity. Data on genetic diversity, bottleneck effect, and glyphosate resistance showed contrasts in biotypes from nearby invaded fields. Our study showed different genetic diversity levels in biotypes from invaded areas under the same climatic conditions.

The current study was conducted in 2013 to identify the seeds of three species of Amaranthus, Amaranthus viridis L., Amaranthus retroflexus L. and Amaranthus albus L., by using the artificial neural network (ANN) and canonical discriminant analysis (CDA) methods. To begin with, photographs were taken of the seeds and 13 morphological characteristics of each seed extracted as predictor variables. Backward regression was used to find the most influential variables and seven variables were derived. Thus, predictor variables were divided into two sets of 13 and seven morphological characteristics. The results showed that the recognition accuracy of the ANN made using 13 and seven predictor variables was 81.1 and 80.3%, respectively. Meanwhile, recognition accuracy of the CDA using the seven and 13 predictor variables was 74.0 and 75.7%, respectively. Therefore, in comparison to CDA, ANN showed higher identification accuracy; however, the difference was not statistically significant. Identification accuracy for A. retroflexus was higher using the CDA method than ANN, while the ANN method had higher recognition accuracy for A. viridis than CDA. In addition, use of 13 predictor variables yielded a greater identification accuracy than seven. The results of the current study showed that using seed morphological characteristics extracted by computer vision could be effective for reliable identification of the similar seeds of Amaranthus species.

Common ragweed is a plant species causing allergic and asthmatic symptoms in humans. To control its propagation, an early identification system is needed. However, due to its similar appearance with mugwort, proper differentiation between these two weed species is important. Therefore, we propose a method to discriminate common ragweed and mugwort leaves based on digital images using bag of visual words (BoVW). BoVW is an object-based image classification that has gained acceptance in many areas of science. We compared speeded-up robust features (SURF) and grid sampling for keypoint selection. The image vocabulary was built using K-means clustering. The image classifier was trained using support vector machines. To check the robustness of the classifier, specific model runs were conducted with and without damaged leaves in the trainings dataset. The results showed that the BoVW model allows the discrimination between common ragweed and mugwort leaves with high accuracy. Based on SURF keypoints with 50% of 788 images in total as training data, we achieved a 100% correct recognition of the two plant species. The grid sampling resulted in slightly less recognition accuracy (98 to 99%). In addition, the classification based on SURF was up to 31 times faster.

Restoration of abandoned agricultural lands to create resilient ecosystems in arid and semi-arid ecosystems typically requires seeding or transplanting native species, improving plant–soil–water relations, and controlling invasive species. We asked if improving water relations via irrigation or surface mulch would result in negative tradeoffs between native species establishment and invasive species competition. We examined the effects of sprinkler irrigation and straw mulch on native seed mixtures planted in two consecutive years in an abandoned agricultural field in a cold desert shrubland in southwestern Nevada, USA. Restoration effects differed among years because of contingency effects of growing season conditions. Precipitation was low during the first year and seeded plant density and biomass increased in response to irrigation. Precipitation was relatively high during the second year, seeded plant densities and biomass were generally high, and irrigation had inconsistent effects. Mulch increased native plant cover in the absence of irrigation during the dry year. Invasive plant biomass and cover also were influenced by year, but irrigation increased invasive plants regardless of precipitation. Positive effects of irrigation on seeded plant density, cover, and biomass outweighed negative tradeoffs of increases in invasive plants. In ecosystems with highly variable precipitation, the most effective restoration strategies will most likely be adaptive ones, requiring determination of timing and amount of irrigation based on precipitation, native plant establishment, and invasive species composition and abundance.