MIT researchers developed a technique that accelerates a privacy-preserving approach for training AI models on edge devices. Their new framework could enable more accurate, efficient, and secure AI models to be used in under-resourced settings.  

A year-long environmental DNA study of New York City’s East River involving single liter water samples revealed an unexpectedly detailed snapshot of life in and around the city, from weekly and seasonal shifts in fish species and abundance to urban wildlife activity and even New Yorkers’ diets.

The findings suggest that urban waterways anywhere could become continuous biosensors, tracking biodiversity, habitat restoration outcomes, and human impacts in real time.