Mário Cunha

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
Wildfire disturbances can profoundly impact many aspects of both ecosystem functioning and resilience. This study proposes a satellite-based approach to assess ecosystem resilience to wildfires based on post-fire trajec-tories of four key functional dimensions of ecosystems related to carbon, water, and energy exchanges: (i) vegetation primary production; (ii) vegetation and soil water content; (iii) land surface albedo; and (iv) land surface sensible heat. For each dimension, several metrics extracted from satellite image time-series, at the short, medium and long-term, describe both resistance (the ability to withstand environmental disturbances) and re-covery (the ability to pull back towards equilibrium). We used MODIS data for 2000-2018 to analyze trajectories after the 2005 wildfires in NW Iberian Peninsula. Primary production exhibited low resistance, with abrupt breaks immediately after the fire, but rapid recoveries, starting within six months after the fire and reaching stable pre-fire levels two years after. Loss of water content after the fire showed slightly higher resistance but slower and more gradual recoveries than primary production. On the other hand, albedo exhibited varying levels of resistance and recovery, with post-fire breaks often followed by increases to levels above pre-fire within the first two years, but sometimes with effects that persisted for many years. Finally, wildfire effects on sensible heat were generally more transient, with effects starting to dissipate after one year and overall rapid recoveries. Our approach was able to successfully depict key features of post-fire processes of ecosystem functioning at different timeframes. The added value of our multi-indicator approach for analyzing ecosystem resilience to wildfires was highlighted by the independence and complementarity among the proposed indicators targeting four dimensions of ecosystem functioning. We argue that such approaches can provide an enhanced characterization of ecosystem resilience to disturbances, ultimately upholding promising implications for post-fire ecosystem management and targeting different dimensions of ecosystem functioning.

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.

Abstract
Currently, copper is approved as an active substance among plant protection products and is considered effective against more than 50 different diseases in different crops, conventional and organic. Tomato has been cultivated for centuries, but many fungal diseases still affect it, making it necessary to control them through antifungal agents, such as copper, making it the primary form of fungal control in organic farming systems (OFS). The objective of this work was to determine whether exogenous copper applications can affect AOX mechanisms and nitrogen use efficiency in tomato plant grown in OFS. For this purpose, plants were sprayed with 'Bordeaux' mixture (SP). In addition, two sets of plants were each treated with 8 mg/L copper in the root substrate (S). Subsequently, one of these groups was also sprayed with a solution of 'Bordeaux' mixture (SSP). Leaves and roots were used to determine NR, GS and GDH activities, as well as proline, H2O2 and AsA levels. The data gathered show that even small amounts of copper in the rhizosphere and copper spraying can lead to stress responses in tomato, with increases in total ascorbate of up to 70% and a decrease in GS activity down to 49%, suggesting that excess copper application could be potentially harmful in horticultural production by OFS.

Abstract
The world wine sector is a multi-billion dollar industry with a wide range of economic activities. Therefore, it becomes crucial to monitor the grapevine because it allows a more accurate estimation of the yield and ensures a high-quality end product. The most common way of monitoring the grapevine is through the leaves (preventive way) since the leaves first manifest biophysical lesions. However, this does not exclude the possibility of biophysical lesions manifesting in the grape berries. Thus, this work presents three pre-trained YOLO models (YOLOv5x6, YOLOv7-E6E, and YOLOR-CSP-X) to detect and classify grape bunches as healthy or damaged by the number of berries with biophysical lesions. Two datasets were created and made publicly available with original images and manual annotations to identify the complexity between detection (bunches) and classification (healthy or damaged) tasks. The datasets use the same 10,010 images with different classes. The Grapevine Bunch Detection Dataset uses the Bunch class, and The Grapevine Bunch Condition Detection Dataset uses the OptimalBunch and DamagedBunch classes. Regarding the three models trained for grape bunches detection, they obtained promising results, highlighting YOLOv7 with 77% of mAP and 94% of the F1-score. In the case of the task of detection and identification of the state of grape bunches, the three models obtained similar results, with YOLOv5 achieving the best ones with an mAP of 72% and an F1-score of 92%.