Mosquito-borne diseases remain one of the greatest threats to global health worldwide. Despite countless efforts to control, suppress or eradicate mosquitoes by thousands of institutions worldwide, the scope of the mosquito problem continues to grow too large to be addressed solely by dedicated professionals. To fill this gap, a growing number of citizen science projects focused on mosquitoes have sprung up around the world. To test the general utility of a citizen science platform known as iNaturalist (iNat) for motivating mosquito citizen science and mosquito control directly by lay-persons, I started the “Mosquitoes in Hawai'i” project in 2015 prior to a widely publicized Dengue outbreak. This project has now grown to over 1000 observations collected by a group of dedicated volunteers who curate the data, promote mosquito awareness and personally respond to calls for vector control in their communities. I will explain how the growing database of curated mosquito images is used to train a machine-learning algorithm allowing photographic identification of mosquitoes. I will do a live demonstration of the machine learning algorithm and show how this tool can help amplify the expertise vector professionals and help them engage their local communities. I will briefly summarize how our lab is using iNat data to model mosquito distributions. As the Hawai'i project has grown, so has the use of iNat to document mosquitoes in different regions and worldwide. I will conclude by focusing on how the iNaturalist efforts fit into global efforts to build mosquito citizen science tools and engage communities to tackle the problem of controlling and ultimately eliminating the threat of vector-borne disease worldwide.

Click Here to Register