A geostatistical fusion approach using UAV data for probabilistic estimation of Xylella fastidiosa subsp. pauca infection in olive trees

Assessing the driving role of the anthropogenic landscape on the distribution of the Xylella fastidiosa-driven "olive quick decline syndrome" in Apulia (Italy)

The plant pathogen Xylella fastidiosa (Xf) is a significant threat to various economically important tree cash crops. Although previously found only in the Americas, the bacterium responsible for olive quick decline syndrome was detected in Apulia, Italy, in 2013. Since then, it has spread to approximately 54,000 ha of olive trees in the region, causing dramatic concern throughout the Mediterranean basin. As a result, it is crucial to comprehend its distribution and forecast its potential diffusion. The effect of the anthropogenic component of the landscape on the distribution of Xf remains little explored. The present study used an ecological niche model to identify how different land uses, used as proxies of different levels of human pressure across the Apulia territory, impacted the distribution of the Xf-infected olive trees in 2015-2021. Results demonstrated that the anthropogenic component significantly contributed to the epidemic, with the road system representing the main driver of diffusion and natural/seminatural areas hampering Xf spread at the landscape scale. This evidence highlighted the importance of explicitly considering the effects of the anthropogenic landscape when modelling Xf distribution and support the design of landscape-informed monitoring strategies to prevent Xf spread in Apulia and other Mediterranean countries.

1H-NMR Metabolomics Study after Foliar and Endo-Therapy Treatments of Xylella fastidiosa subsp. pauca Infected Olive Trees: Medium Time Monitoring of Field Experiments

Here we report the medium-term effects of foliar spray and endo-therapy treatments with different doses of a Cu/Zn citric acid biocomplex (Dentamet®) in Xylella fastidiosa infected olive trees of Salento, Apulia region (South-east Italy). Leaf extract samples from field-treated 150 years old olive trees cvs Ogliarola salentina and Cellina di Nardò were studied by 1H NMR-based metabolomics. The result of different applications of Dentamet® endo-therapy after 60, 120 and 180 days in comparison with traditional foliar spray treatment and water injection as a control have been investigated. The metabolic profile analyses, performed by 1H NMR-based metabolomic approach, indicated plant metabolites variations connected to the disease progression such as mannitol, quinic acid, and oleuropein related compounds. The best results, in terms of discrimination of the metabolic profiles with respect to water injection, were found for monthly endo-therapy treatments. Dentamet® foliar application demonstrated more specific time related progressive effectiveness with respect to intravascular treatments. Therefore, besides a possible more effective performance of endo-therapy with respect to foliar treatments, the need of further doses/frequencies trimming to obtain long-term results was also assessed. The present field studies confirmed the indication of Dentamet® effectiveness in metabolic variation induction, potentially linked with reducing the X. fastidiosa subspecies pauca related Olive Quick Decline Syndrome (OQDS) symptoms development.

Estimation of tomato water status with photochemical reflectance index and machine learning: Assessment from proximal sensors and UAV imagery

Tracking plant water status is a critical step towards the adaptive precision irrigation management of processing tomatoes, one of the most important specialty crops in California. The photochemical reflectance index (PRI) from proximal sensors and the high-resolution unmanned aerial vehicle (UAV) imagery provide an opportunity to monitor the crop water status efficiently. Based on data from an experimental tomato field with intensive aerial and plant-based measurements, we developed random forest machine learning regression models to estimate tomato stem water potential (ψ _stem), (using observations from proximal sensors and 12-band UAV imagery, respectively, along with weather data. The proximal sensor-based model estimation agreed well with the plant ψ _stem with R ² of 0.74 and mean absolute error (MAE) of 0.63 bars. The model included PRI, normalized difference vegetation index, vapor pressure deficit, and air temperature and tracked well with the seasonal dynamics of ψ _stem across different plots. A separate model, built with multiple vegetation indices (VIs) from UAV imagery and weather variables, had an R ² of 0.81 and MAE of 0.67 bars. The plant-level ψ _stem maps generated from UAV imagery closely represented the water status differences of plots under different irrigation treatments and also tracked well the temporal change among flights. PRI was found to be the most important VI in both the proximal sensor- and the UAV-based models, providing critical information on tomato plant water status. This study demonstrated that machine learning models can accurately estimate the water status by integrating PRI, other VIs, and weather data, and thus facilitate data-driven irrigation management for processing tomatoes.

Automatic Detection of Olive Tree Canopies for Groves with Thick Plant Cover on the Ground

Marking the tree canopies is an unavoidable step in any study working with high-resolution aerial images taken by a UAV in any fruit tree crop, such as olive trees, as the extraction of pixel features from these canopies is the first step to build the models whose predictions are compared with the ground truth obtained by measurements made with other types of sensors. Marking these canopies manually is an arduous and tedious process that is replaced by automatic methods that rarely work well for groves with a thick plant cover on the ground. This paper develops a standard method for the detection of olive tree canopies from high-resolution aerial images taken by a multispectral camera, regardless of the plant cover density between canopies. The method is based on the relative spatial information between canopies.The planting pattern used by the grower is computed and extrapolated using Delaunay triangulation in order to fuse this knowledge with that previously obtained from spectral information. It is shown that the minimisation of a certain function provides an optimal fit of the parameters that define the marking of the trees, yielding promising results of 77.5% recall and 70.9% precision.

Landscape and Vegetation Patterns Zoning Is a Methodological Tool for Management Costs Implications Due to Xylella fastidiosa Invasion

Philaenus spumarius (Linnaeus 1758, hereafter Ps) is considered one of the main insect vectors responsible for the spread of an alien biota, Xylella fastidiosa (Wells 1987, hereafter Xf), in the Salento area, Apulia region (Southern Italy). Effective management of this biological invader depends on the continuous surveillance and monitoring of its insect vector. As such, this research elicits the invasion drivers (i.e., landscape and vegetation indicators) that influence the abundance and the dynamics of this vector and, consequently, the spatial spread of this bacterium in this Italian region. For this purpose, a spatial pattern clustering methodological approach is considered. The results reveal that spatial variation and territorial differentiation may differ from zone to zone in the same invaded area, for which effective management and monitoring planning should be addressed. Further, six agro-ecosystems zones have been identified with respect to five indicators: (i) vegetation index, (ii) intensity of cultivation, (iii) cultural diversity, (iv) density of agricultural landscape elements, and (v) altitude. This paper has public implications and contributes to an understanding of how zoning of an infected area, by an alien biota, into homogenous zones may impact its effective management costs. This approach could also be applied in other countries affected or potentially affected by the phenomenon of Xf invasion.

Unmanned Aerial Vehicles (UAV) in Precision Agriculture: Applications and Challenges

Agriculture is the primary source of income in developing countries like India. Agriculture accounts for 17 percent of India’s total GDP, with almost 60 percent of the people directly or indirectly employed. While researchers and planters focus on a variety of elements to boost productivity, crop loss due to disease is one of the most serious issues they confront. Crop growth monitoring and early detection of pest infestations are still a problem. With the expansion of cultivation to wider fields, manual intervention to monitor and diagnose insect and pest infestations is becoming increasingly difficult. Failure to apply on time fertilizers and pesticides results in more crop loss and so lower output. Farmers are putting in greater effort to conserve crops, but they are failing most of the time because they are unable to adequately monitor the crops when they are infected by pests and insects. Pest infestation is also difficult to predict because it is not evenly distributed. In the recent past, modern equipment, tools, and approaches have been used to replace manual involvement. Unmanned aerial vehicles serve a critical role in crop disease surveillance and early detection in this setting. This research attempts to give a review of the most successful techniques to have precision-based crop monitoring and pest management in agriculture fields utilizing unmanned aerial vehicles (UAVs) or unmanned aircraft. The researchers’ reports on the various types of UAVs and their applications to early detection of agricultural diseases are rigorously assessed and compared. This paper also discusses the deployment of aerial, satellite, and other remote sensing technologies for disease detection, as well as their Quality of Service (QoS).

The potential direct economic impact and private management costs of an invasive alien species: Xylella fastidiosa on Lebanese wine grapes

Since its outbreak in 2013 in Italy, the harmful bacterium Xylella fastidiosa has continued to spread throughout the Euro-Mediterranean basin and, more recently, in the Middle East region. Xylella fastidiosa subsp. fastidiosa is the causal agent of Pierce’s disease on grapevines. At present, this alien subspecies has not been reported in Lebanon but if this biological invader was to spread with no cost-effective and sustainable management, it would put Lebanese vineyards at a certain level of risk. In the absence of an Xylella fastidiosa subsp. fastidiosa outbreak, the gross revenue generated by Lebanese wine growers is estimated as close to US$22 million/year for an average period of 5 years (2015–2019). The potential quantitative economic impacts of an Xylella fastidiosa subsp. fastidiosa outbreak and particularly, the private control costs have not been assessed yet for this country as well as for others which Xylella fastidiosa may invade. Here, we have aimed to estimate the potential direct economic impact on growers’ livelihoods and provide the first estimate of the private management costs that a theoretical Xylella fastidiosa subsp. fastidiosa outbreak in Lebanon would involve. For this purpose, we used a Partial Budget approach at the farm gate. For the country as a whole, we estimated that a hypothetical full spread of Xylella fastidiosa subsp. fastidiosa on Lebanese wine grapes would lead to maximum potential gross revenue losses of almost US$ 11 million for an average recovery period of 4 years, to around US$ 82.44 million for an average grapevine life span period of 30 years in which infected plants are not replaced at all. The first yearly estimated additional management cost is US$853 per potentially infected hectare. For a recovery period of 4 years, the aggregate estimated additional cost would reach US$2374/ha, while the aggregate net change in profit would be US$-4046/ha. Furthermore, additional work will be needed to estimate the public costs of an Xylella fastidiosa subsp. fastidiosa outbreak in Lebanon. The observed costs in this study support the concerned policy makers and stakeholders to implement a set of reduction management options against Xylella fastidiosa subsp. fastidiosa at both national and wine growers’ levels. This re-emerging alien biota should not be neglected in this country. This understanding of the potential direct economic impact of Xylella fastidiosa subsp. fastidiosa and the private management costs can also benefit further larger-scale studies covering other potential infection areas and plant hosts.

Spatially variable pesticide application in olive groves: Evaluation of potential pesticide-savings through stochastic spatial simulation algorithms

Site-specific management using spatial crown volume characterization can greatly reduce the amount of pesticides applied in agricultural treatments performed with air-assisted sprayers, while helping farmers achieve the European legislation on safe use of pesticides. Nevertheless, variable rate treatments in olive groves have received little attention. Thus, field research was conducted in a 20.6-ha traditional olive grove. Two attributes of the trees - tree crown volume (V) and tree projected area - were determined, using 67 samples for V and all trees of the field (1433) for tree projected area. Spatial continuity of both attributes was modelled with exponential variograms. To gain a measure of local uncertainty, stochastic simulation algorithms were applied. One hundred simulated images were obtained for tree projected area using direct sequential simulation. Tree projected area simulations were used to improve spatial prediction of V, more difficult and more expensive to obtain, taking advantage of the high linear correlation between both variables (r_xy = 0.72,p < 0.001). Thus, direct sequential cosimulation was employed to predict the spatial distribution of V, obtaining 100 geostatistical realizations of V. In order to estimate the potential reduction of pesticide use in the farm with variable rate treatments, two cut-off values of V were considered (50 and 100 m³_{crown volume}). Local uncertainty, understood as the probability of each tree belonging to a given crown volume interval was determined. Probability maps were further transformed to morphological maps and finally to variable prescription maps. Two scenarios with 2 and 3 management zones (MZs) were obtained. In comparison with a conventional phytosanitary application, the variable rate treatments could reduce the pesticide amounts by 21.3% with 2 MZs, and by 38% with 3 MZs. The joint use of V and tree projected area in stochastic sequential simulation algorithms has shown to be useful to determine MZs in olive groves.

Semi-Automatic Method for Early Detection of Xylella fastidiosa in Olive Trees Using UAV Multispectral Imagery and Geostatistical-Discriminant Analysis

Xylella fastidiosa subsp. pauca (Xfp) is one of the most dangerous plant pathogens in the world. Identified in 2013 in olive trees in south–eastern Italy, it is spreading to the Mediterranean countries. The bacterium is transmitted by insects that feed on sap, and causes rapid wilting in olive trees. The paper explores the use of Unmanned Aerial Vehicle (UAV) in combination with a multispectral radiometer for early detection of infection. The study was carried out in three olive groves in the Apulia region (Italy) and involved four drone flights from 2017 to 2019. To classify Xfp severity level in olive trees at an early stage, a combined method of geostatistics and discriminant analysis was implemented. The results of cross-validation for the non-parametric classification method were of overall accuracy = 0.69, mean error rate = 0.31, and for the early detection class of accuracy 0.77 and misclassification probability 0.23. The results are promising and encourage the application of UAV technology for the early detection of Xfp infection.