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.

Comparison of the drift potential of two application methods for the control of oak processionary moths with biocidal products in an oak avenue.

The control of oak processionary moths (OPM; Thaumetopoea processionea) with biocidal products has become more important to protect humans from its urticating hairs. Two important application methods are cannon sprayers and helicopters. However, drift of insecticides to non-target areas might occur during the treatment resulting in potential risks for non-target organisms. Until now, information about the direct drift resulting from the applications are missing because equipment for the application of biocidal products is not tested or regulated within Europe. The aim of this work is to measure the direct drift in up to 100 m distance resulting from the application of biocidal products using a cannon sprayer and helicopter in an oak avenue. Furthermore, two different nozzles were tested for the helicopter application. The results show high drift potential with decreasing concentrations in relation to the distance to the treated area. Considering the 50th percentile of the results, the cannon sprayer produced generally more drift than the helicopter. Considering the 90th percentile at near distance, the helicopter equipped with ID-120-05 POM nozzles showed a significantly lower drift than both other tested techniques, the helicopter equipped with the Airmix 110 05 nozzles and the cannon sprayer. Hundred m away from the treated area, both nozzles installed at the helicopter showed a lower drift than the cannon sprayer. For the first time, this study shows the drift potential of applications of biocidal products and shows the possibilities to reduce drift into non-target areas by choosing appropriate equipment. This leads to a reduction of risks for non-target organisms in the vicinity of treated avenues.