Information about the DiversityScanner technology and associated pipelines.

DiversityScanner is novel technology developed by Rudolf Meier (Museum fur Naturkunde) and Lorenz Wührl and Christian Pylatiuk (Karlsruher Institut für Technologie) that combines robotics, machine learning and high-throughput genomic sequencing to scan, classify and quantify invertebrate taxa from bulk environmental samples, at a price and scale not possible with current methods.

A robot, the “DiversityScanner,  detects, images, and measures individual specimens and moves them into the wells of a 96-well microplate. The images are used to train convolutional neural networks (CNNs) to assign specimens to common insect families. To obtain biomass information, the images are also used to measure specimen length and estimate body volume. In order to obtain DNA barcodes, robust and cost-effective barcoding techniques involving ONT sequencers and bioinformatics tools have been develped that allow for approximate species-level sorting.


 

 

References and further reading