Search

Machine learning is a widespread technology that plays a crucial role in digitalisation and aims to explore rules and patterns in large datasets to autonomously solve non-linear problems, taking advantage of multiple source data. Due to its versatility, machine learning can be applied to agriculture. Better crop management, plant health assessment, and early disease detection are some of the main challenges facing the agricultural sector. Plant phenotyping can play a key role in addressing these challenges, especially when combined with machine learning techniques. Therefore, this study reviews available scientific literature on the applications of machine learning algorithms in plant phenotyping with a specific focus on sunflowers. The most common algorithms in the agricultural field are described to emphasise possible uses. Subsequently, the overview highlights machine learning application on phenotyping in three primaries areas: crop management (i.e., yield prediction, biomass estimation, and growth stage monitoring), plant health (i.e., nutritional status and water stress), and disease detection. Finally, we focus on the adoption of machine learning techniques in sunflower phenotyping. The role of machine learning in plant phenotyping has been thoroughly investigated. Artificial neural networks and stacked models seems to be the best way to analyse data. [ABSTRACT FROM AUTHOR]

Sunflower is one of the most important oilseed crops cultivated in the world for different purposes. In Italy, the production is mostly located in the central area, representing 70% of Italian production. The market demand for sunflower oil is higher than the national production. There is an increasing request for cold pressed sunflower oil for food application. The success of this activity is linked to a correct setting up and management of the production and supply chain with a valorization of products and by-products. To this aim, information is needed, and this paper is focused on the cultivation of sunflower in central Italy using suitable hybrids, as well as on the study of the cold extraction performance of the sunflower seed produced and the quality of by-products and residues. Results indicate that, on average, a range of about 1.0–1.5 t ha−1 of cold pressed oil and different amounts of by-products can be obtained. According to a proposed scenario, 30 ha cultivated with sunflower are needed to create a complete supply chain within the farm, avoiding many additional passages and maintaining all the value for the farmer. It is important to use suitable hybrids for obtaining good yield, but also the cold extraction performances are important because they also affect the quality of by-products and residues that can be valorized themselves to improve sustainability. [ABSTRACT FROM AUTHOR]