Machine learning approach to tracking how yellow fever mosquitoes move through the environment

Yellow fever mosquito (Aedes aegypti) is a major vector of deadly diseases such as dengue fever, chikungunya, and the Zika virus, which leads to hundreds of thousands of deaths worldwide each year. because of Ae. aegypti they prefer to bite people and there are no vaccines for many of these diseases they carry, it is vital that methods are developed to control these pests in order to control disease.

In a study recently published in Proceedings of the National Academy of Sciences, a Yale-led research team developed a new way to track how Ae. aegypti move through the environment. Combining genetic data from the mosquitoes and environmental data from satellites, the authors mapped a “landscape link” – defined as how landscape enables the movements of organisms and their genes across on large areas. In particular, the researchers developed a new workflow that more effectively models how Ae. aegypti moving through the environment in the southern US

“Connectivity maps allow managers to make informed decisions based on how mosquitoes tend to move through a landscape,” says Evlyn Pless, a graduate researcher at the University of California, Davis and a PhD graduate in Department of Ecology and Evolutionary Biology of Yale. ”Our results suggest that in the southern U.S., Ae. aegypti traveling with a combination of natural dispersal and human support, taking advantage of warmer and flatter regions, as well as human transport networks. “

Plessco wrote the paper by Giuseppe Amatulli, a research scientist with the Center for Research Computing and the Yale School of the Environment; Norah Saarman, associate professor of biology at Utah State University; and Jeffrey Powell and Adalgisa Caccone from Yale’s Department of Ecology and Evolutionary Biology.

Now, the most common way to control invasive species is disease behavior Ae. aegypti is by the use of poisons, which are not friendly. “We now know that some toxins cause environmental damage, including harm to humans,” Saarman said. “At the same time, mosquitoes are increasingly resistant to the toxins we have found to be safe for the environment.

“This creates a challenge that can only be solved with more information on where mosquitoes live and how they get around.”

One advanced control method is to release genetically modified mosquitoes into their populations, in an effort to stop the reproduction and spread of the disease. The authors state that they expect link maps like the ones they created to be useful in plotting more strategic distributions of modified mosquitoes.

“By integrating machine learning with an optimization process, our approach overcomes the limitations of previous methods and should be helpful for a more detailed design of vector control functions,” says Amatulli.

The authors also believe that this novel progression could have broader applications, including the conservation and protection of the environment.

“Connectivity maps can also be essential for the protection of endangered native species,” says Pless, “for example, in designing corridors to link scattered numbers.”