Understanding how biological communities respond to environmental changes is\na key challenge in ecology and ecosystem management. The apparent decline of\ninsect populations necessitates more biomonitoring but the time-consuming\nsorting and identification of taxa pose strong limitations on how many insect\nsamples can be processed. In turn, this affects the scale of efforts to map\ninvertebrate diversity altogether. Given recent advances in computer vision, we\npropose to replace the standard manual approach of human expert-based sorting\nand identification with an automatic image-based technology. We describe a\nrobot-enabled image-based identification machine, which can automate the\nprocess of invertebrate identification, biomass estimation and sample sorting.\nWe use the imaging device to generate a comprehensive image database of\nterrestrial arthropod species. We use this database to test the classification\naccuracy i.e. how well the species identity of a specimen can be predicted from\nimages taken by the machine. We also test sensitivity of the classification\naccuracy to the camera settings (aperture and exposure time) in order to move\nforward with the best possible image quality. We use state-of-the-art Resnet-50\nand InceptionV3 CNNs for the classification task. The results for the initial\ndataset are very promising ($\\overline{ACC}=0.980$). The system is general and\ncan easily be used for other groups of invertebrates as well. As such, our\nresults pave the way for generating more data on spatial and temporal variation\nin invertebrate abundance, diversity and biomass.\n