InsectSound1000 An insect sound dataset for deep learning based acoustic insect recognition.

InsectSound1000 is a dataset comprising more than 169000 labelled sound samples of 12 insects. The insect sound level spans from very loud (Bombus terrestris) to inaudible to human ears (Aphidoletes aphidimyza). The samples were extracted from more than 1000 h of recordings made in an anechoic box with a four-channel low-noise measurement microphone array. Each sample is a four-channel wave-file of 2500 kHz length, at 16 kHz sample rate and 32 bit resolution. Acoustic insect recognition holds great potential to form the basis of a digital insect sensor. Such sensors are desperately needed to automate pest monitoring and ecological monitoring. With its significant size and high-quality recordings, InsectSound1000 can be used to train data-hungry deep learning models. Used to pretrain models, it can also be leveraged to enable the development of acoustic insect recognition systems on different hardware or for different insects. Further, the methodology employed to create the dataset is presented in detail to allow for the extension of the published dataset.

Rapid and low-cost insect detection for analysing species trapped on yellow sticky traps.

While insect monitoring is a prerequisite for precise decision-making regarding integrated pest management (IPM), it is time- and cost-intensive. Low-cost, time-saving and easy-to-operate tools for automated monitoring will therefore play a key role in increased acceptance and application of IPM in practice. In this study, we tested the differentiation of two whitefly species and their natural enemies trapped on yellow sticky traps (YSTs) via image processing approaches under practical conditions. Using the bag of visual words (BoVW) algorithm, accurate differentiation between both natural enemies and the Trialeurodes vaporariorum and Bemisia tabaci species was possible, whereas the procedure for B. tabaci could not be used to differentiate this species from T. vaporariorum. The decay of species was considered using fresh and aged catches of all the species on the YSTs, and different pooling scenarios were applied to enhance model performance. The best performance was reached when fresh and aged individuals were used together and the whitefly species were pooled into one category for model training. With an independent dataset consisting of photos from the YSTs that were placed in greenhouses and consequently with a naturally occurring species mixture as the background, a differentiation rate of more than 85% was reached for natural enemies and whiteflies.

Mitespotting: approaches for Aculops lycopersici monitoring in tomato cultivation.

Aculops lycopersici is a major pest in tomato cultivation worldwide, and lately its relevance in German tomato cultivation has increased markedly. Aculops lycopersici causes damage to tomato plants by feeding on the surface of leaves, stem and fruits and can lead to the loss of whole plants. Given the small size of the pest, A. lycopersici infestation may go unnoticed for quite a length of time. When discovered symptoms can be easily confused with those of diseases. In addition to these issues A. lycopersici has a very high reproduction rate. In this study, fluorescence measurements were performed on the stem of A. lycopersici-inoculated potted tomato plants and these were compared with a visual bare eye assessment and a sticky tape imprint method for classification of these plants as either infested or healthy. The best correct classification rate was achieved with sticky tape, but this method is time intensive, which makes it unsuitable for large-scale monitoring in practice. Classification based on a ridge regression performed on stem fluorescence measurements was at least as good as the classification based on the visual assessment, and detection was robust against symptoms of drought stress. In a second trial the specificity of stem fluorescence measurements for A. lycopersici against Trialeurodes vaporariorum was tested successfully. The fluorescence method is promising as this method allows for high automation and thereby has the potential to increase monitoring efficacy in practice considerably. The relevance of the tested monitoring methods for practical tomato cultivation and the next steps to be taken are discussed.

Bait spray for control of European cherry fruit fly: an appraisal based on semi-field and field studies.

BACKGROUND: The European cherry fruit fly, Rhagoletis cerasi, is the major insect pest of sweet and tart cherries. Its management is becoming increasingly difficult in many countries as formerly effective but broad-spectrum insecticides are removed from the market. With the objective of identifying suitable and environmentally safe alternatives, we investigated bait sprays containing two families of plant-derived insecticides: azadirachtins (NeemAzal-T(®) and NeemAzal-T/S(®) ) and pyrethrins (Spruzit Neu(®) ). RESULTS: In 12 semi-field trials conducted within cages, weekly applications of 0.0001 or 0.0005% neem in a bait formulation effectively reduced fruit infestation. However, addition of 0.000125-0.001% pyrethrins did not improve the efficacy of the neem formulations, and when used alone pyrethrins were less effective than neem alone. Two years of field trials were also conducted within orchards wherein an insecticidal barrier of treated trees excluded immigration of fertile R. cerasi from elsewhere. In blocks treated with 0.0005% neem in a bait formulation, we observed 94% (2011) or 86% (2012) reduction of fruit infestation over control blocks. CONCLUSION: Bait sprays containing neem are a promising alternative for the management of R. cerasi, especially where the risk of immigration of fertilized females is low, as in isolated orchards or as part of area-wide treatments.

The preimaginal phases and development of Pachycrepoideus vindemmiae (Hymenoptera, Pteromalidae) on Mediterranean fruit fly, Ceratitis capitata (Diptera, Tephritidae).

The development and morphology of the immature phases of Pachycrepoideus vindemmiae (Rondani, 1875) (Hymenoptera, Pteromalidae) are described from a laboratory rearing culture maintained on Ceratitis capitata (Wiedemann, 1824) (Diptera, Tephritidae) using microscopic techniques, including light and scanning electron microscopy. The surface of the chorion of the egg is granulated, and the micropyle occurs at the anterior end. The labrum of the first instar larva does not have sensilla, and the second to fourth instar larvae have setae on the head. The mature larva is characterized by the position and number of the integumental differentiations (sensilla and setae). On completion of larval development, an adecticous and exarate pupa is produced. As for the adult, the mandibles of the pupae are toothed. Five larval instars are recorded, based on statistical analyses of the sizes of the larval mandibles in combination with characters such as the number of exuviae and excretion of the meconium. Developmental time from egg to adult emergence was 18-20 days for males and 21-23 days for females at 21-26 degrees C, 55-85 relative humidity, and a 16L:8D photoperiod. The results show that the eggs and different larval instars of this parasitoid can be unambiguously identified only by scanning electron microscope.

The preimaginal stages and development of Spalangia cameroni Perkins (Hymenoptera: Pteromalidae) on Ceratitis capitata (Wiedemann) (Diptera: Tephritidae).

The development and morphology of the immature phases of Spalangia cameroni Perkins, 1910 (Hymenoptera, Pteromalidae) are described from a laboratory rearing culture maintained on Ceratitis capitata (Wiedemann, 1824) (Diptera, Tephritidae), using microscopic techniques, including light and scanning electron microscopy. The surface of the chorion of the egg is smooth and the micropyle occurs at the anterior end. The immature larvae are similar to the mature larva, differing mainly in the size of the head capsule and mandibles. The mature larva displays tubercules on the body segments as well as a pleurostoma and superior and inferior mandibular processes. On completion of its larval development, an adecticous and exarate pupa is produced. The mandibles of the pupa, as for the adult, are toothed. Three larval instars are recorded based on statistical analyses of the sizes of the larval mandibles and head capsules, in combination with such characters as the number of exuviae and excretion of the meconium. There are significant positive correlations between mandible length and width of larval head capsule with the number of instars, thus indicating that the mandible length and width of larval capsule are good predictors of the number of instars in this parasitoid. Developmental time from egg to adult emergence was approximately 33-34 days for females and approximately 28-29 days for males at 21-26 degrees C, 55-85 RH and a L16:D8 photoperiod. Our results show that the eggs and different instars of S. cameroni can be unambiguously identified only by SEM. Therefore, characterization of the immature stages of Spalangia species using SEM should be done before subsequent routine identifications using a binocular microscope or stereomicroscope.