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.

In the context of climate change and the increasing demand for innovative solutions in agriculture and energy, agrivoltaic systems (AVSs) have emerged as promising technologies. These systems integrate photovoltaic panels with agricultural practices, optimizing both food and energy production. This study provides a comprehensive review focused on monitoring techniques applicable to AVS, including fixed sensors and remote monitoring tools. Bibliographic analysis revealed a significant increase in scientific interest in AVSs since 2019, with most publications focusing on technological, agronomic, and environmental aspects. Key findings highlight environmental benefits such as reduced greenhouse gas emissions, improved water efficiency, and enhanced soil quality. Otherwise, challenges including high initial costs and the persistence of technical complexities. Innovative configurations such as semi-transparent or vertically bifacial panels enable resource optimization and improved agricultural yields if combined with advanced monitoring systems. This study highlights the importance of incentive policies and further research to maximize the potential of AVSs in promoting sustainable land management.

Grapevines are one of the most intensely treated crops with a high potential risk to health and biodiversity. Thus, the distribution control of agrochemicals is crucial to obtain a high quality and sustainable product for intensive viticulture. Although the search for systems to reduce the waste of chemical products is consistent in some countries, such as Italy, the machinery used are obsolete. The development of an upgrading system for sprayers can be a good compromise to achieve the pollution reduction without requiring huge investments. Field tests were conducted using a LIDAR-based prototype coupled to a commercial sprayer. This study tested the distribution performance using water-sensitive papers and evaluated the infections of grapevine downy and powdery mildews. The results showed a distribution in the vegetation gaps with a higher frequency in the coverage classes >20% in the standard treatment and 10–15% in the LIDAR treatment. Treatments performed with LiDAR reduced the incidence of downy mildew and severity of powdery mildew. The innovative sprayer reduces the distribution of agrochemicals thanks to the on/off control of the nozzles in the voids of vegetation and, meanwhile, controls vineyard fungal disease, so it can be a good way to meet the sustainability and quality of the production.

The integration of precision agriculture technologies, such as remote sensing through drones and satellites, has significantly enhanced real-time crop monitoring. This study is among the first to combine multispectral data from both a drone equipped with Altum-PT camera and PlanetScope satellite imagery to predict fresh biomass in sweet basil grown in an open field, demonstrating the added value of integrating different spatial scales. A dataset of 40 sampling points was built by combining remote sensing data with field measurements, and seven vegetation indices were calculated for each point. Feature selection was performed using three different methods (F-score, Recursive Feature Elimination, and model-based selection), and the most informative features were then processed through Principal Component Analysis. Eight regression models were trained and evaluated using leave-one-out cross-validation. The best-performing models were Random Forest (R² = 0.96 in training, R² = 0.65 in testing) and k-Nearest Neighbours (R² = 0.74 in training, R² = 0.94 in testing), with kNN demonstrating superior generalization capability on unseen data. These findings highlight the potential of combining drone and satellite imagery for modelling basil agronomic traits, offering valuable insights for optimizing crop management strategies.