A Large-Scale Dataset and Deep Learning Model for Detecting and Counting Olive Trees in Satellite Imagery

Since the Pre-Roman era, olive trees have a significant economic and cultural value. In 2019, the Al-Jouf region, in the north of the Kingdom of Saudi Arabia, gained a global presence by entering the Guinness World Records, with the largest number of olive trees in the world. Olive tree detecting and counting from a given satellite image are a significant and difficult computer vision problem. Because olive farms are spread out over a large area, manually counting the trees is impossible. Moreover, accurate automatic detection and counting of olive trees in satellite images have many challenges such as scale variations, weather changes, perspective distortions, and orientation changes. Another problem is the lack of a standard database of olive trees available for deep learning applications. To address these problems, we first build a large-scale olive dataset dedicated to deep learning research and applications. The dataset consists of 230 RGB images collected over the territory of Al-Jouf, KSA. We then propose an efficient deep learning model (SwinTUnet) for detecting and counting olive trees from satellite imagery. The proposed SwinTUnet is a Unet-like network which consists of an encoder, a decoder, and skip connections. Swin Transformer block is the fundamental unit of SwinTUnet to learn local and global semantic information. The results of an experimental study on the proposed dataset show that the SwinTUnet model outperforms the related studies in terms of overall detection with a 0.94% estimation error.

Xylella fastidiosa and Drought Stress in Olive Trees: A Complex Relationship Mediated by Soluble Sugars

Xylella fastidiosa (Xf) subsp. pauca “De Donno” is the etiological agent of “Olive Quick Decline Syndrome” (OQDS) on olive trees (Olea europaea L.); the presence of the bacterium causes xylem vessel occlusions inducing a drought stress and the development of leaf scorch symptoms, which may be worsened by water shortage in summer. In order to evaluate how the two stress factors overlap each other, the carbohydrate content and the expression patterns of genes related to carbohydrate metabolism have been evaluated in two olive cvs trees (Cellina di Nardò, susceptible to Xf, and Leccino, resistant to Xf) reporting transcriptional dynamics elicited by Xf infection, drought, or combined stress (drought/Xf). In the Xf-susceptible Cellina di Nardò plants, Xf and its combination with drought significantly decrease total sugars compared to control (−27.0% and −25.7%, respectively). In contrast, the Xf-resistant Leccino plants show a more limited reduction in sugar content in Xf-positive conditions (−20.1%) and combined stresses (−11.1%). Furthermore, while the amount of glucose decreases significantly in stressed Cellina di Nardò plants (≈18%), an increase was observed in Leccino plants under drought/Xf combined stresses (+11.2%). An opposite behavior among cvs was also observed for sucrose, as an accumulation of the disaccharide was recorded in stressed Leccino plants (≈37%). The different response to combined stress by Xf-resistant plants was confirmed considering genes coding for the sucrose or monosaccharide transporter (OeSUT1, OeMST2), the cell wall or vacuolar invertase (OeINV-CW, OeINV-V), the granule-bound starch synthase I (OeGBSSI) and sucrose synthase (OeSUSY), with a higher expression than at least one single stress (e.g., ≈1-fold higher or more than Xf for OeMST2, OeINV-CW, OeINV-V, OeGBSSI). It is probable that the pathways involved in drought stress response induce positive effects useful for pathogen resistance in cv Leccino, confirming the importance of investigating the mechanisms of cross-talk of biotic and abiotic responses.

Neofusicoccum mediterraneum Is Involved in a Twig and Branch Dieback of Olive Trees Observed in Salento (Apulia, Italy)

Olive trees are infected and damaged by Botryosphaeriaceae fungi in various countries. The botryosphaeriaceous fungus Neofusicoccum mediterraneum is highly aggressive and is a major concern for olive groves in Spain and California (USA), where it causes ‘branch and twig dieback’ characterized by wood discoloration, bark canker, and canopy blight. During surveys of olive groves in Apulia (southern Italy), we noticed that—in some areas—trees were heavily affected by severe branch and twig dieback. In addition, chlorosis and the appearance of red-bronze patches on the leaf preceded the wilting of the foliage, with necrotic leaves persisting on the twigs. Given the severity of the manifestation in zones also subject to olive quick decline syndrome (OQDS) caused by Xylella fastidiosa subsp. pauca, we investigated the etiology and provide indications for differentiating the symptoms from OQDS. Isolation from diseased wood samples revealed a mycete, which was morphologically and molecularly identified as N. mediterraneum. The pathogenicity tests clearly showed that this fungus is able to cause the natural symptoms. Therefore, also considering the low number of tested samples, N. mediterraneum is a potential causal agent of the observed disease. Specifically, inoculation of the twigs caused complete wilting in two to three weeks, while inoculation at the base of the stem caused severe girdling wedge-shaped cankers. The growth rate of the fungus in in vitro tests was progressively higher from 10 to 30 °C, failing to grow at higher temperatures, but keeping its viability even after prolonged exposure at 50 °C. The capacity of the isolate to produce catenulate chlamydospores, which is novel for the species, highlights the possibility of a new morphological strain within N. mediterraneum. Further investigations are ongoing to verify whether additional fungal species are involved in this symptomatology.

Estimating Productivity, Detecting Biotic Disturbances and Assessing the Health State of Traditional Olive Groves, Using Nondestructive Phenotypic Techniques

Conservation of traditional olive groves through effective monitoring of their health state is crucial both at a tree and at a population level. In this study, we introduce a comprehensive methodological framework for estimating the traditional olive grove health state, by considering the fundamental phenotypic, spectral, and thermal traits of the olive trees. We obtained phenotypic information from olive trees on the Greek island of Lesvos by combining this with in situ measurement of spectral reflectance and thermal indices to investigate the effect of the olive tree traits on productivity, the presence of the olive leaf spot disease (OLS), and olive tree classification based on their health state. In this context, we identified a suite of important features, derived from linear and logistic regression models, which can explain productivity and accurately evaluate infected and noninfected trees. The results indicated that either specific traits or combinations of them are statistically significant predictors of productivity, while the occurrence of OLS symptoms can be identified by both the olives’ vitality traits and by the thermal variables. Finally, the classification of olive trees into different health states possibly offers significant information to explain traditional olive grove dynamics for their sustainable management.

Doenças associadas à Xylella fastidiosa no Brasil

Based on genomic information, the Xylella fastidiosa bacterium is classified into three main subspecies: fastidiosa, multiplex and pauca. These different subspecies are naturally transmitted through vector insects, known as sharpshooters, which feed on the sap of xylem vessels of plants, where the bacteria colonize. Mainly due to the obstruction in the transport of water and mineral salts in these conducting vessels, the X. fastidiosa bacterium causes serious diseases in different cultures of economic interest. In Brazil, this phytopathogen was detected for the first time in plum trees, a crop in which the multiplex subspecies is responsible for the disease known as plum leaf scald. Subsequently, the pauca subspecie was associated with citrus variegated chlorosis in sweet orange orchards in São Paulo State. In the same state, the pauca subspecie was also found in coffee plants causing atrophy of the coffee tree branches, a disease whose damage has not been quantified yet. Recently, the pauca subspecie has also been found in olive trees, causing the olive quick decline syndrome, reported in the southeast region, especially in the Serra da Mantiqueira region. In this review, specific aspects of these diseases were focused, as well as measures that can be adopted as management.

The Sustainability of Irrigation Strategies in Traditional Olive Orchards

Olive trees are one of the few alternative crops available for farmers in arid environments. In many of these regions, surface irrigation is increasing. The aim of this study was to estimate the pattern of water soil reserves through the season considering different climatic scenarios, limitations in irrigation scheduling, and irrigation systems. Modeling was performed with the most common type of soil, and a tree density of 10 × 10 m was used. Three different climatic scenarios were estimated using eighteen agroclimatic stations along the zone (Jaén, Spain). In these climatic scenarios, different irrigation strategies were considered. First, the percentages of maximum flow available (100%, 50%, and 33%) were used. In each of these flows, the days available for irrigation were considered: daily irrigation (IDD), 20 days per month (ID20), and no irrigation, during August (RDI). The results suggest that a 33% flow strategy, the most common in the surveyed area, would produce the greatest water-stress period in the most sensitive phenological stage. However, 100%, in all scenarios, and 50% (only IDD and RDI) would obtain the best water status. According to the estimated water applied, 50% was the most advisable strategy. However, in a minimum rainfall scenario, water needs could be excessive.