Researchers at the University of South Florida (USF) have reported what could be the first identification of Anopheles stephensi, an invasive mosquito species known for spreading malaria, in Madagascar. The study, led by USF scientists Ryan Carney and Sriram Chellappan, used artificial intelligence (AI) and contributions from local citizens to reach this finding.
Anopheles stephensi is a concern in Africa due to its ability to breed in urban areas using artificial containers such as tires and buckets. This differs from native mosquitoes that typically breed in natural puddles. Its expansion across the continent could increase malaria risk for an estimated 126 million people.
The research was published in “Insects” and shows how combining mobile technology with machine learning can address gaps in tracking disease-carrying insects. The discovery began with a photo taken by residents of Antananarivo using NASA’s GLOBE Observer app. AI algorithms analyzed the image, identifying the mosquito larva as Anopheles stephensi with more than 99% certainty. Additional larvae were found nearby on the same day.
During that year, Madagascar saw malaria cases and deaths double.
Globally, mosquitoes are responsible for infecting over 700 million people each year with various pathogens. Malaria continues to be particularly deadly, causing nearly half a million deaths among children under five annually.
The researchers noted that vigilance against malaria vectors is increasingly important beyond Africa as well. In 2023, local outbreaks of malaria occurred in the United States for the first time in two decades. Florida reported more cases than any other state.
Ryan Carney stated: “Thanks to citizen science apps, we can crowd-source photos of mosquitoes and then analyze this imagery using AI to scale up detection of those disease-spreading needles in the haystack.”
He added: “While mosquitoes can be thought of as tiny flying hypodermic needles, only 3% of species are known to transmit diseases to humans,” Carney said. “Thanks to citizen science apps, we can crowd-source photos of mosquitoes and then analyze this imagery using AI to scale up detection of those disease-spreading needles in the haystack.”
To improve early detection efforts—often missed by traditional surveillance—the team developed new AI tools capable of identifying mosquito larvae and adults from smartphone images using facial recognition-like methods. These algorithms were trained on thousands of verified images representing both Anopheles stephensi and other species.
This project brought together faculty from multiple USF colleges: Arts and Sciences; Bellini College of Artificial Intelligence, Cybersecurity and Computing; and Public Health. Funding came from grants provided by the National Institutes of Health and National Science Foundation. It follows earlier work published by the team that won “Insects” journal’s Best Paper Award for 2022.
Looking ahead, USF researchers aim to create hardware based on their software—a smart trap powered by AI—to remotely identify adult Anopheles stephensi mosquitoes as well as other vector species within Florida and elsewhere.
Sriram Chellappan commented: “AI is increasingly being used in many aspects of public health, and mosquito surveillance is an area of significant importance globally, and to Florida,” Chellappan said. “We believe we are pioneering next-generation surveillance systems for public health, geared towards combating mosquito-borne diseases.”
