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 an important oilseed crop affected by environmental and geopolitical threats. • Sunflower can be managed with advanced agriculture techniques thanks to its high mechanizability. • Remote sensing is widespread in the agricultural sector, but it is not so for sunflowers. • Most of the studies on the application of remote sensing do not involve the world's major producers. • The evaluated topics are: vegetation indices, forecasting and growth models, abiotic stresses. Sunflower is an annual species of the Asteraceae family, and it occupies a relevant position in the world market business as one of the most important oilseed crops. Given the current geopolitical situation and climate change, the agri-food supply chain of sunflower is in crisis. In this context, precision agriculture, especially remote sensing, can address demands for more production and greater sustainability. The aim of the present systematic review is to evaluate the available scientific literature on precision agriculture applied to sunflower crop, specifically the use of hyperspectral data to calculate vegetation indices or create crop growth models. The systematic review follows specific guidelines and a well-described review protocol. A total of 104 studies were included in the review, starting from raw search in different data sources (Scopus, Web of Science, Springer Link, and Science Direct) and following with the application of inclusion criteria. Results focused on the following main topics: crop management (i.e., management zones, yield prediction, vegetation indices correlations), sunflower crop growth monitoring (i.e., identify different growth stages and vegetation parameters), weed management, and industrial applications. The role of hyperspectral sensors has been thoroughly investigated to help choose ideal wavelengths related to vegetation indices. Future research should prioritise water stress management, time-saving evaluation of new sunflower hybrids, and crop growth models. [ABSTRACT FROM AUTHOR]