The increasing public concern about food security and the stricter rules applied worldwide concerning herbicide use in the agri-food chain, reduce consumer acceptance of chemical plant protection. Site-Specific Weed Management can be achieved by applying a treatment only on the weed patches. Crop plants and weeds identification is a necessary component for various aspects of precision farming in order to perform on the spot herbicide spraying or robotic weeding and precision mechanical weed control. During the last years, a lot of different methods have been proposed, yet more improvements need to be made on this problem, concerning speed, robustness, and accuracy of the algorithms and the recognition systems. Digital cameras and Artificial Neural Networks (ANNs) have been rapidly developed in the past few years, providing new methods and tools also in agriculture and weed management. In the current work, images gathered by an RGB camera of Zea mays, Helianthus annuus, Solanum tuberosum, Alopecurus myosuroides, Amaranthus retroflexus, Avena fatua, Chenopodium album, Lamium purpureum, Matricaria chamomila, Setaria spp., Solanum nigrum and Stellaria media were provided to train Convolutional Neural Networks (CNNs). Three different CNNs, namely VGG16, ResNet–50, and Xception, were adapted and trained on a pool of 93,000 images. The training images consisted of images with plant material with only one species per image. A Top-1 accuracy between 77% and 98% was obtained in plant detection and weed species discrimination, on the testing of the images.

Cannabis is one of the oldest cultivated plants, but plant breeding and cultivation are restricted by country specific regulations. Plant growth, morphology and metabolism can be manipulated by changing light quality and intensity. Three morphologically different strains were grown under three different light spectra with three real light repetitions. Light dispersion was included into the statistical evaluation. The light spectra considered had an influence on the morphology of the plant, especially the height. Here, the shade avoidance induced by the lower R:FR ratio under the ceramic metal halide lamp (CHD) was of particular interest. The sugar leaves seemed to be of elementary importance in the last growth phase for yield composition. Furthermore, the last four weeks of flowering were crucial to influence the yield composition of Cannabis sativa L. through light spectra. The dry flower yield was significantly higher under both LED treatments compared to the conventional CHD light source. Our results indicate that the plant morphology can be artificially manipulated by the choice of light treatment to create shorter plants with more lateral branches which seem to be beneficial for yield development. Furthermore, the choice of cultivar has to be taken into account when interpreting results of light studies, as Cannabis sativa L. subspecies and thus bred strains highly differ in their phenotypic characteristics.

Cannabis is one of the oldest cultivated plants, but plant breeding and cultivation are restricted by country-specific regulations. The plant has gained interest due to its medically important secondary metabolites, cannabinoids and terpenes. Besides biotic and abiotic stress factors, secondary metabolism can be manipulated by changing light quality and intensity. In this study, three morphologically different cannabis strains were grown in a greenhouse experiment under three different light spectra with three real light repetitions. The chosen light sources were as follows: a CHD Agro 400 ceramic metal-halide lamp with a sun-like broad spectrum and an R:FR ratio of 2.8, and two LED lamps, a Solray (SOL) and an AP67, with R:FR ratios of 13.49 and 4, respectively. The results of the study indicated that the considered light spectra significantly influenced CBDA and terpene concentrations in the plants. In addition to the different light spectra, the distributions of secondary metabolites were influenced by flower positions. The distributions varied between strains and indicated interactions between morphology and the chosen light spectra. Thus, the results demonstrate that secondary metabolism can be artificially manipulated by the choice of light spectrum, illuminant and intensity. Furthermore, the data imply that, besides the cannabis strain selected, flower position can have an impact on the medicinal potencies and concentrations of secondary metabolites.