Leandro Almeida Rodrigues

Abstract
In 2023, global kiwifruit production reached over 4.4 million tonnes, highlighting the crop's significant economic importance. However, achieving high yields depends on adequate pollination. In Actinidia species, pollen is transferred by insects from male to female flowers on separate plants. Natural pollination faces increasing challenges due to the decline in pollinator populations and climate variability, driving the adoption of assisted pollination methods. This study examines the Portuguese kiwifruit sector, one of the world's top 12 producers, using a novel mixed-methods approach that integrates both qualitative and quantitative analyses to assess the feasibility of robotic pollination. The qualitative study identifies the benefits and challenges of current methods and explores how robotic pollination could address these challenges. The quantitative analysis explores the cost-effectiveness and practicality of implementing robotic pollination as a product and service. Findings indicate that most farmers use handheld pollination devices but face pollen wastage and application timing challenges. Economic analysis establishes a break-even point of €685 per hectare for an annual single application, with a first robotic pollination of €17 146 becoming cost-effective for orchards of at least 3.5 hectares and a second robotic solution of €34 293 becoming cost-effective for orchards up to 7 hectares. A robotic pollination service priced at €685 per hectare per application presents a low-risk and a viable alternative for growers. This study provides robust economic insights supporting the adoption of robotic pollination technologies. This study is crucial to make informed decisions to enhance kiwifruit production's productivity and sustainability through precise robotic-assisted pollination. © 2025 Elsevier B.V., All rights reserved.

Abstract
This study demonstrates the application of a tomography-like (TL) method to monitor grape maturation dynamics over two growing seasons (2021-2022) in the Douro Wine Region. Using a Vis-NIR point-of-measurement sensor, which employs visible and near-infrared light to penetrate grape tissues non-destructively and provide spectral data to predict internal composition, this approach captures non-destructive measurements of key physicochemical properties, including soluble solids content (SSC), weight-to-volume ratio, chlorophyll and anthocyanin levels across internal grape tissues-skin, pulp, and seeds-over six post-veraison stages. The collected data were used to generate detailed metabolic maps of maturation, integrating topographical factors such as altitude and NDVI-based (normalised difference vegetation index) vigour assessments, which revealed significant (p < 0.05) variations in SSC, chlorophyll, and anthocyanin levels across vineyard zones. The metabolic maps generated from the TL method enable high-throughput data to reveal the impact of environmental variability on grape maturation across distinct vineyard areas. Predictive models using random forest (RF) and self-learning artificial intelligence (SL-AI) algorithms showed RF's robustness, achieving stable predictions with R-2 >= 0.86 and MAPE <= 33.83 %. To illustrate the TL method's practical value, three hypothetical decision models were developed for targeted winemaking objectives based on SSC, chlorophyll in the pulp, and anthocyanin in the skin and seeds. These models underscore the TL method's ability to support site-specific management (SSM) by providing actionable agricultural practices (e.g. harvest) into vineyard management, guiding winemakers to implement tailored interventions based on metabolic profiles rather than only cultivar characteristics. This precision viticulture (PV) approach enhances wine quality and production efficiency by aligning vineyard practices with specific wine quality goals.

Abstract
This study investigates how grapevines (Vitis vinifera L.) respond to shading induced by artificial nets, focusing on physiological and metabolic changes. Through a multidisciplinary approach, grapevines' adaptations to shading are presented via biochemical analyses and hyperspectral data that are then combined with systems biology techniques. In the study, conducted in a 'Moscatel Galego Branco' vineyard in Portugal's Douro Wine Region during post-veraison, shading was applied and predawn leaf water potential (Psi pd) was then measured to assess water stress. Biochemical analyses and hyperspectral data were integrated to explore adaptations to shading, revealing higher chlorophyll levels (chlorophyll a-b 117.39% higher) and increased Reactive Oxygen Species (ROS) levels in unshaded vines (52.10% higher). Using a self-learning artificial intelligence algorithm (SL-AI), simulations highlighted ROS's role in stress response and accurately predicted chlorophyll a (R2: 0.92, MAPE: 24.39%), chlorophyll b (R2: 0.96, MAPE: 17.61%), and ROS levels (R2: 0.76, MAPE: 52.17%). In silico simulations employing flux balance analysis (FBA) elucidated distinct metabolic phenotypes between shaded and unshaded vines across cellular compartments. Integrating these findings provides a systems biology approach for understanding grapevine responses to environmental stressors. The leveraging of advanced omics technologies and precise metabolic models holds immense potential for untangling grapevine metabolism and optimizing viticultural practices for enhanced productivity and quality.

Abstract
Several thousand grapevine varieties exist, with even more naming identifiers. Adequate specialized labor is not available for proper classification or identification of grapevines, making the value of commercial vines uncertain. Traditional methods, such as genetic analysis or ampelometry, are time-consuming, expensive, and often require expert skills that are even rarer. New vision-based systems benefit from advanced and innovative technology and can be used by nonexperts in ampelometry. To this end, deep learning (DL) and machine learning (ML) approaches have been successfully applied for classification purposes. This work extends the state of the art by applying digital ampelometry techniques to larger grapevine varieties. We benchmarked MobileNet v2, ResNet-34, and VGG-11-BN DL classifiers to assess their ability for digital ampelography. In our experiment, all the models could identify the vines' varieties through the leaf with a weighted F1 score higher than 92%.

Abstract
The efficiency of agricultural practices depends on the timing of their execution. Environmental conditions, such as rainfall, and crop-related traits, such as plant phenology, determine the success of practices such as irrigation. Moreover, plant phenology, the seasonal timing of biological events (e.g., cotyledon emergence), is strongly influenced by genetic, environmental, and management conditions. Therefore, assessing the timing the of crops' phenological events and their spatiotemporal variability can improve decision making, allowing the thorough planning and timely execution of agricultural operations. Conventional techniques for crop phenology monitoring, such as field observations, can be prone to error, labour-intensive, and inefficient, particularly for crops with rapid growth and not very defined phenophases, such as vegetable crops. Thus, developing an accurate phenology monitoring system for vegetable crops is an important step towards sustainable practices. This paper evaluates the ability of computer vision (CV) techniques coupled with deep learning (DL) (CV_DL) as tools for the dynamic phenological classification of multiple vegetable crops at the subfield level, i.e., within the plot. Three DL models from the Single Shot Multibox Detector (SSD) architecture (SSD Inception v2, SSD MobileNet v2, and SSD ResNet 50) and one from You Only Look Once (YOLO) architecture (YOLO v4) were benchmarked through a custom dataset containing images of eight vegetable crops between emergence and harvest. The proposed benchmark includes the individual pairing of each model with the images of each crop. On average, YOLO v4 performed better than the SSD models, reaching an F1-Score of 85.5%, a mean average precision of 79.9%, and a balanced accuracy of 87.0%. In addition, YOLO v4 was tested with all available data approaching a real mixed cropping system. Hence, the same model can classify multiple vegetable crops across the growing season, allowing the accurate mapping of phenological dynamics. This study is the first to evaluate the potential of CV_DL for vegetable crops' phenological research, a pivotal step towards automating decision support systems for precision horticulture.