Broomrape is a root parasitic plant causing yield losses in sunflower production. Since sunflower is an important oil crop, the development of broomrape-resistant hybrids is the prime breeding objective. Using conventional plant breeding methods, breeders have identified resistant genes and developed a number of hybrids resistant to broomrape, adapted to different growing regions worldwide. However, the spread of broomrape into new countries and the development of new and more virulent races have been noted intensively. Recent advances in sunflower genomics provide additional tools for plant breeders to improve resistance and find durable solutions for broomrape spread and virulence. This review describes the structure and distribution of new, virulent physiological broomrape races, sources of resistance for introduction into susceptible cultivated sunflower, qualitative and quantitative resistance genes along with gene pyramiding and marker assisted selection (MAS) strategies applied in the process of increasing sunflower resistance. In addition, it presents an overview of underutilized biotechnological tools, such as phenotyping, -omics, and genome editing techniques, which need to be introduced in the study of sunflower resistance to broomrape in order to achieve durable resistance.

Drought stress significantly threatens crop productivity worldwide, requiring a comprehensive understanding of plant adaptations to alleviate its adverse effects. Sunflower, as an important source of edible oil, is greatly affected by drought in different developmental stages. This review investigates the morphological aspects and phenological adaptations of sunflower under drought conditions. Through a detailed description of morphological and phenological changes in sunflower, induced by drought, we aim to unravel the plant’s strategies for coping with water scarcity. In addition, the study describes genetic background of drought tolerance in sunflower, as well as insight about valuable genetic resources. Finally, we have described drought mitigation mechanisms known in sunflower, through morpho-physiological adaptations and agricultural practices which can alleviate the effect of drought. As a future strategy this research emphasizes the importance of genetic diversity in cultivating drought-resilient sunflower, using modern breeding techniques through genomic selection and omic’s technologies as a promising strategy in the face of escalating water limitations and development of drought tolerant and tenacious sunflower.

Sunflower (Helianthus annuus L.) is one of the most important crops grown in the world, but it can be attacked by more than 30 different pathogens. The areal of Macrophomina phaseolina (Tassi) Goid., one of the sunflower pathogens nowadays often found in temperate regions, has been spreading over the last few years due to climate change. The most effective eco-friendly method for controlling charcoal rot caused by M. phaseolina is growing resistant sunflower cultivars. Due to that, 24 commercially available hybrids and 70 inbred lines were tested for M. phaseolina tolerance in a two-year trial. Under the field conditions, two different inoculation methods were used - the Unwounded Stem Base Inoculation (USBI) and Toothpick (TP) method. This study identified five highly tolerant hybrids and 12 inbred lines that can be used in breeding programs for improvement of future genotypes. Sunflower genotype screening tests for Macrophomina tolerance indicated that both inoculation methods should be applied together to provide reliable results, and that stem lesion length is a reliable trait for disease severity assessments.

This study aimed to investigate the Diaporthe species associated with Phomopsis stem canker of sunflower (Helianthus annuus L.) in Serbia. The significant increase in sunflower and soybean (Glycine max [L.] Merr.) cultivation may have created the bridge favorable conditions for the distribution of Diaporthe species in this region. The present study identified five Diaporthe species on sunflower: D. gulyae, D. helianthi, D. pseudolongicolla, D. stewartii, and the newly identified D. riccionae based on morphological, molecular, and pathogenic characteristics. The research emphasizes the importance of effective inoculation methods and evaluates the aggressiveness of isolates. Sunflower plants were inoculated using the stem wound method, while seeds of sunflower and soybean were inoculated using the standard seed method. Most of the tested isolates demonstrated high aggressiveness, resulting in more than 80% premature wilting of sunflower plants. Additionally, this research examined the aggressiveness of Diaporthe species on sunflower seeds, highlighting D. stewartii and D. pseudolongicolla as common pathogens of both sunflower and soybean. The most aggressive species on seeds was D. stewartii, causing seed decay of up to 100% in sunflower and 97% in soybean. The findings suggest the development of resilient sunflower genotypes through breeding programs and the implementation of strategies to manage cross-contamination risks between sunflower and soybean crops. Furthermore, this study provides insights into the interactions between Diaporthe species and the seeds of sunflower and soybean. Future research will enhance our understanding of the impact of Diaporthe species on sunflower and soybean.

Efficient water supply and timely detection of drought stress in crops to increase yields is an important task considering that agriculture is the primary consumer of water globally. This is particularly significant for plants such as sunflowers, which are an important source of quality edible oils, essential for human nutrition. Traditional detection methods are labor-intensive, time-consuming, and rely on advanced sensor technologies. We introduce an innovative approach based on neural networks and transfer learning for drought stress detection using a novel dataset including 209 non-invasive rhizotron images and 385 images of manually cleaned sections of sunflowers, subjected to normal watering or water stress. We used five neural network models: VGG16, VGG19, InceptionV3, DenseNet, and MobileNet, pre-trained on the ImageNet dataset, whose performance was compared to select the most efficient architecture. Accordingly, the most efficient model, MobileNet, was further refined using different data augmentation mechanisms. The introduction of targeted data augmentation and the use of grayscale images proved to be effective, demonstrating improved results, with an F1 score and an accuracy of 0.95. This approach encourages advances in water stress detection, highlighting the value of artificial intelligence in improving crop health monitoring and management for more resilient agricultural practices.