Abstract
The malaria parasite, which is transmitted by several Anopheles mosquito species, requires more time to reach its human-transmissible stage than the average lifespan of a mosquito. Monitoring the species-specific age structure of mosquito populations is critical to evaluating the impact of vector control interventions on malaria risk. We developed a rapid, cost-effective surveillance method based on deep learning of mid-infrared spectra of mosquitoes’ cuticle that simultaneously identifies the species and the age of three main malaria vectors, in natural populations. Using over 40,000 ecologically and genetically diverse females, we could speciate and age grade An. gambiae, An. arabiensis, and An. coluzzii with up to 95% accuracy. Further, our model learned the age of new populations with minimal sampling effort and detected the impact of control interventions on simulated mosquito populations, measured as a shift in their age structures. We anticipate our method to be applied to other arthropod vector-borne diseases.
Competing Interest Statement
The authors have declared no competing interest.
