Most of Earth’s mosquito-borne illnesses are transmitted by mosquitoes in one of three genera: Anopheles, Aedes, and Culex. Mosquitos of such genera are located in all continents but Antarctica and infect millions of humans with parasitic viruses yearly. However, a special concern is reserved for Anopheles mosquitoes for their unique ability to carry and transmit Malaria, a disease that, according to WHO, infects more than 200 million and kills over 500,000 humans annually (Malaria, 2022). While it is most prevalent in Africa, Southeast Asia, and Central America, Malaria could soon spread to northern and southern latitudes with a changing global climate. Therefore, it is crucial to track the extent of the Anopheles range and identify any changes that could have detrimental consequences on public health. One way this can be done is using the NASA GLOBE Observer Mosquito Habitat Mapper (MHM) tool, which allows global users free access to photograph mosquito larvae, attempt to identify their genus, and upload said images to a worldwide database that records the location at which they were taken. While citizen science data is extremely helpful for mosquito research, it can be difficult for citizens with minimal training to classify the genus of their discovered larva correctly. A large portion of mosquito photos uploaded to the GLOBE MHM database are either unidentified or misidentified. Therefore, this research paper aims to devise and assess how the MHM database can be appropriately classified to create an accurate dataset with all Anopheles larvae photos classified by their proper genus.Besides being a vector of Malaria, another unique characteristic of theAnopheles mosquito is the absence of a siphon, so by scanning for this trait among MHM larvae photographs and noting positive matches, researchers created a dataset of mosquito larvae that could become vectors of Malaria as adults (Image Reference #1). This data set could then be used to train AImodels utilizing Convolutional Neural Networks (CNN) or VisionTransformers (ViT) to classify the MHM database autonomously in the near future.