Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images.

In the present study, the detection and mapping of Silybum marianum (L.) Gaertn. weed using novelty detection classifiers is reported. A multispectral camera (green-red-NIR) on board a fixed wing unmanned aerial vehicle (UAV) was employed for obtaining high-resolution images. Four novelty detection classifiers were used to identify S. marianum between other vegetation in a field. The classifiers were One Class Support Vector Machine (OC-SVM), One Class Self-Organizing Maps (OC-SOM), Autoencoders and One Class Principal Component Analysis (OC-PCA). As input features to the novelty detection classifiers, the three spectral bands and texture were used. The S. marianum identification accuracy using OC-SVM reached an overall accuracy of 96%. The results show the feasibility of effective S. marianum mapping by means of novelty detection classifiers acting on multispectral UAV imagery.

Application of Multilayer Perceptron with Automatic Relevance Determination on Weed Mapping Using UAV Multispectral Imagery.

Remote sensing techniques are routinely used in plant species discrimination and of weed mapping. In the presented work, successful Silybum marianum detection and mapping using multilayer neural networks is demonstrated. A multispectral camera (green-red-near infrared) attached on a fixed wing unmanned aerial vehicle (UAV) was utilized for the acquisition of high-resolution images (0.1 m resolution). The Multilayer Perceptron with Automatic Relevance Determination (MLP-ARD) was used to identify the S. marianum among other vegetation, mostly Avena sterilis L. The three spectral bands of Red, Green, Near Infrared (NIR) and the texture layer resulting from local variance were used as input. The S. marianum identification rates using MLP-ARD reached an accuracy of 99.54%. Τhe study had an one year duration, meaning that the results are specific, although the accuracy shows the interesting potential of S. marianum mapping with MLP-ARD on multispectral UAV imagery.

Nontarget effects of aerial mosquito adulticiding with water-based unsynergized pyrethroids on honey bees and other beneficial insects in an agricultural ecosystem of north Greece.

We assessed the nontarget effects of ultra-low-volume (ULV) aerial adulticiding with two new water-based, unsynergized pyrethroid formulations, Aqua-K-Othrine (FFAST antievaporant technology, 2% deltamethrin) and Pesguard S102 (10% d-phenothrin). A helicopter with GPS navigation technology was used. One application rate was tested per formulation that corresponded to 1.00 g (AI)/ha of deltamethrin and 7.50 g (AI)/ha of d-phenothrin. Three beneficial nontarget organisms were used: honey bees (domesticated hives), family Apidae (Apis mellifera L.); mealybug destroyers, family Coccinellidae (Cryptolaemus montrouzieri Mulsant); and green lacewings, family Chrysopidae (Chrysoperla carnea (Stephens)). No significant nontarget mortalities were observed. No bees exhibited signs of sublethal exposure to insecticides. Beehives exposed to the insecticidal applications remained healthy and productive, performed as well as the control hives and increased in weight (25-30%), in adult bee population (14-18%), and in brood population (15-19%).

Field Assessment of the Host Range of Aculus mosoniensis (Acari: Eriophyidae), a Biological Control Agent of the Tree of Heaven (Ailanthus altissima).

Tree of heaven (Ailanthus altissima) is a fast-growing deciduous tree native to China, considered a serious invasive species worldwide, with several socio-economic and ecological impacts attributed to it. Chemical and mechanical methods have limited efficacy in its management, and biological controls may offer a suitable and sustainable option. Aculus mosoniensis (Ripka) is an eriophyid mite that has been recorded to attack tree of heaven in 13 European countries. This study aims to explore the host range of this mite by exposing 13 plant species, selected either for their phylogenetic and ecological similarity to the target weed or their economic importance. Shortly after inoculation with the mite, we recorded a quick decrease in mite number on all nontarget species and no sign of mite reproduction. Whereas, after just one month, the population of mites on tree of heaven numbered in the thousands, irrespective of the starting population, and included both adults and juveniles. Significantly, we observed evidence of damage due to the mite only on target plants. Due to the specificity, strong impact on the target, and the ability to increase its population to high levels in a relatively short amount of time, we find A. mosoniensis to be a very promising candidate for the biological control of tree of heaven.

Ground ultra low volume (ULV) space spray applications for the control of wild sand fly populations (Psychodidae: Phlebotominae) in Europe.

The Phlebotomus sand flies are considered an important vector of both canine and human leishmaniasis. Current measures for sand fly control include mostly indoor interventions, such as residual spraying of dwellings (IRS) to target endophilic sand fly species with very limited number of vector control tools for outdoor interventions against exophilic sand flies. In this study we investigated the efficacy of ground ultra low volume (ULV) space spray applications of a deltamethrin based product against field populations of P. perfiliewi, a major nuisance and pathogen-transmitting sand fly species of the Mediterranean Basin. Sand fly flight activity patterns and flight height preference within candidate treatment sites (kennels) were determined prior to treatments in order to optimize the timing and application parameters of the spray applications. On average there was a distinct activity peak between 20.00-22.00 h for both male and female P. perfiliewi with more than 45% and 30% of the population sampled occurring between 20.00-21.00 h and 21.00-22.00 h, respectively. No significant difference was observed in sand fly numbers from sticky traps placed at 0.5 up to 1.5 m height. However, there was a significant decrease in sand fly numbers at 2 m indicating a preference of sand flies to fly below 2 m. The low and high application rate of deltamethrin resulted in mean sand fly population decrease of 18 and 66%, respectively between pre-and post-treatment trap nights. The percent mean population change in the untreated control area was a positive number (30%) indicating that there was an increase in numbers of sand flies trapped between pre- and post-treatment nights. The results of this study provide strong evidence that ground ULV space spray applications when applied properly can result in significant sand fly control levels, even in a heavily infested sand fly environment such as the kennel sites used in this study.

Detection and early warning of West Nile Virus circulation in Central Macedonia, Greece, using sentinel chickens and mosquitoes.

Following the West Nile Virus (WNV) epidemic in 2010 in Central Macedonia, Greece, which resulted in 197 human neuroinvasive disease cases, we determined the seasonal appearance and prevalence of the virus in 2011 by testing weekly for WNV genomic RNA in mosquitoes collected in carbon dioxide-baited traps, and for anti-WNV antibodies in sentinel chickens. Preliminary findings of the surveillance program regarding the circulation of "Nea Santa-Greece-2010" in sentinel chickens were rapidly communicated to public health authorities. In the present article, the full 2011 data produced by this surveillance program are presented. We detected enzootic circulation of WNV in chickens 1 month prior to the onset of the first human cases in 2011. Culex pipiens and Cx. modestus were abundant throughout the sampling period and at all sites of increased transmission. Molecular identification and phylogenetic analysis of WNV isolates from two chickens and one Cx. pipiens mosquito pool suggested that: (1) the virulent "Nea Santa-Greece-2010" WNV lineage 2 strain responsible for the 2010 epidemic was actively circulating in 2011, and (2) all Greek isolates belong to a distinct recent evolutionary clade. In Europe, where numerous strains of different virulence coexist, sequencing information for WNV is important for phylogeography and identification of virulent strains for human health risk assessment.