Researchers from the UK and Africa have developed a fast and inexpensive way to determine age.
They improved the use of infraredspectroscopy to determine the age of mosquitoes. This method provides information on the chemical composition of the protective exoskeleton of an insect, which varies depending on the species and age. Adding to this AI-based algorithms, they were able to determine the species and age of three malaria-carrying mosquitoes. They reported the results in the journal Nature Communications.
The researchers used data from more than 40thousand female mosquitoes of different ages of three species. The insects belonged to different genetic groups and were grown both in various laboratories and in semi-wild conditions in East and West Africa.
The artificial intelligence (AI) model wastrained on mid-infrared spectroscopy data from genetically different lab-grown mosquitoes. The team then retrained it using an additional sample of mosquitoes from semi-wild populations. The resulting model was able to predict the age and species of semi-wild-raised mosquitoes from their mid-infrared signatures with over 95% accuracy.
To further test the effectiveness of thisapproach, the researchers collected wild mosquitoes in Burkina Faso and Tanzania. They then estimated the age of some of them and used them to retrain an AI model that had previously been trained on lab-grown mosquito populations.
In the future, this method can even scanflying mosquitoes. Scientists note that this is easier to do using spectroscopy in the near infrared region, and not in the middle. Now they are working on this type of device.
Read more:
After ten years of work, scientists questioned the standard model of physics
MIT builds stationary heat engine that outperforms turbines
Startup has created tiny robots that work in the human brain