Insect populations are declining globally, making systematic monitoring essential for conservation. Most classical methods involve death traps and counter insect conservation. This paper presents a multisensor approach that uses AI-based data fusion for insect classification. The system is designed as low-cost setup and consists of a camera module and an optical wing beat sensor as well as environmental sensors to measure temperature, irradiance or daytime as prior information.
The system has been tested in the laboratory and in the field. First tests on a small very unbalanced data set with 7 species show promising results for species classification.
The multisensor system will support biodiversity and agriculture studies. Insects play a crucial role in various ecological and economic interactions with their environment, e. They also play an important part in composting for soil fertility and in cleaning water. However, the number of insect species and individuals is in sharp decline worldwide. The reasons for this decline are manifold. Systematic monitoring of population, occurrence and distribution is therefore of great importance.
Conventional insect monitoring systems usually use death traps to measure the absolute biomass of dried insects. Only a few species are classified at the species level. In this paper, a live monitoring system is presented that can complement and extend conventional long-term monitoring. Especially by including citizen scientists, a data set can be obtained that is important for systematic correlation studies.
That way, blind spots on the monitoring map can be prevented. We developed a standardized multisensor system that is easy to use, combined with a Web application for data collection and community networking. To bring monitoring to the public, an automated system based on AI algorithms is used, multiplying the valuable and necessary expert knowledge that is essential for serious statistics in scientific studies.
