Home Others Can the AI ​​defeat the dreaded tsetse fly?

Can the AI ​​defeat the dreaded tsetse fly?

Science & technology By David J. Craig |Winter 2018-19

Geoffrey M. Attardo, PhD

It may look like an ordinary housefly, but the African tsetse fly is one of the most dangerous insects in the world. The tsetse fly is the sole vector of the infectious disease known as sleeping sickness, which kills thousands of people and millions of farm animals in sub-Saharan Africa every year. The tsetse fly has made large areas of the continent uninhabitable.

In recent years, the Senegalese government, working with international aid organizations, has come up with an ingenious way to control the deadly pest by breeding the flies in captivity, sterilizing the males with radiation syringes, and then releasing them into the wild. This has disrupted the mating patterns of the tsetse flies and caused many colonies to collapse. While the strategy is effective, it is time consuming and expensive as it requires a large number of nimble laboratory workers to carefully sort male and female flies by hand.

Zelda Moran ’17PH, a research fellow at Columbia’s Earth Institute, believes she has found a way to streamline this process. Her innovation goes back to a discovery she made in 2015 while working in Vienna for the International Atomic Energy Agency (IAEA), who oversees international scientists working on the Senegalese project. To study the early stages of the tsetse fly's physical development, Moran invented a near-infrared imaging technique that allowed scientists to look inside the opaque doll housing for the first time. This led her and her colleagues to observe that male and female pupae develop on slightly different schedules, with the females sprouting wings a day or two before the males.

We knew that if you could sort the flies during the pupal phase, you wouldn't have to be as delicate with them, says Moran. We could even automate the task.

Moran has since teamed up with Columbia physicist Szabolcs Marka to develop an artificial intelligence program that can instantly determine whether tsetse dolls contain male or female flies. The next step is to develop a robotic mechanism that when it identifies a male pupa moving past on a conveyor belt, it will blow a puff of air to separate it from the females.

Moran says she is currently in discussions with IAEA scientists about building a prototype system that could be integrated into the tsetse breeding facility in Senegal. She hopes that if her technology proves effective, it will allow the IAEA to expand its tsetse sterilization project and eventually take it to other African countries.

Read more from David J. Craig
similar posts
  • Science & technology From code to healing

Interesting Articles