Recent advances in artificial intelligence and machine learning, such as the use of convolutional neural networks (CNNs) for image recognition, have emerged as a promising modality with the capability to visually differentiate between mosquito species. Here we present the first performance metrics of IDX, Vectech’s system for AI mosquito identification, as part of Maryland’s mosquito control program in the USA. Specimens were collected over fourteen weeks from twelve CDC gravid trap collection sites, identified morphologically by an entomologist, and imaged using the IDX system. By comparing entomologist identification to the algorithm output by IDX, we are able to calculate the accuracy of the system across species. Over the study period, 2,591 specimens were collected and imaged representing 14 species, 10 of which were available in the identification algorithm on the device during the study period. The micro average accuracy was 94.9%. Of these 10 species, 7 species consisted of less than 30 samples. The macro average accuracy when including these species was 79%, while the macro average when excluding these species was 93%. In the next iteration of this technology, Vectech is translating the vector identification capabilities of IDX into systems capable of processing greater numbers of specimens at large public health facilities, and remote sensing systems that will allow public health organizations to monitor vector abundance and diversity from the office. These advances demonstrate the utility of artificial intelligence in entomology and its potential to support vector surveillance and control programs around the world.

In this study, we isolated and identified an aggregation-sex pheromone from Monochamus saltuarius, the major insectvector of the pine wood nematode in Korea. Adult male of M. saltuarius produces 2-undecyloxy-1-ethanol, which is knownto be an aggregation-sex pheromone in other Monochamus species. We performed field experiments to determine the attractivenessof the pheromone and other synergists. More M. saltuarius adult beetles were attracted to traps baited with the pheromonethan to unbaited traps. Ethanol and (-)-α-pinene interacted synergistically with the pheromone. Traps baited with pheromone+(-)-α-pinene+ethanol were more attractive to M. saltuarius adults than traps baited with pheromone, (-)-α-pinene, or ethanol alone.Ipsenol, ipsdienol, and limonene were also identified as synergists of the aggregation-sex pheromone for M. saltuarius adults.

Trombiculid mites are known to be the vector of tsutsugamushi disease by transmitting Orientia tsutsugamushi to human. Although the classification of trombiculid mites is necessary for vector surveillance, their classification by morphological observation is only possible at the larval stage and not easy because of similar shapes as well as tiny body sizes. Further the classification need the specimen production process, it takes much time and the accuracy of classification is changed according to the technology of the researcher. The internal transcribed spacers (ITS) regions of 8 trombiculid mite species were analyzed by amplification using tick common ITS primer sets. We designed molecular marker sets for the identification of five Leptotrombidium species, the lengths of marker L. orientale (1078 bp), L. pallidum (820 bp), L. palpale (1202 bp), L. scutellare (447 bp) and for L. zetum (621 bp) and three Neotrombicula species, the lengths of marker N. gardellai (264 bp), N. japonica (460 bp) and N. kwangneungensis (309 bp) based on alignment of ITS sequences. The markers will be helpful for exact classification of trombiculid mites. This study is the first report on molecular marker of ITS regions of trombiculid mites.