How scientists in Boston are using AI to decipher the secret language of rats

A group of scientists in the Boston area are using AI and other technologies to understand how rats communicate. 

"They are doing it all night long. If we could hear them, it would be like listening to birds during the day," said Nick Jourjine, a researcher with Basis Research Institute. 

They are using microphones, thermal cameras and AI to try to decipher rats' secret language. The group places microphone boxes in strategic areas around Boston, such as dumpsters, to record the high-pitched vocalization rats make when communicating. 

"That's the start, just trying to match up what animals do with what they say," Jourjine said. 

Though the boxes sometimes pick up human chatter, all human sounds are redacted then deleted for privacy before the audio is sent through AI models. 

"Then we train those models to go do that on a scale and quantity of data we could never listen to ourselves," Jourjine said.

This data may help researchers understand what rats are saying or about to do, allowing cities to be more proactive about rat prevention. 

"When we see those black bait box traps across buildings, that means the rats are already there. The problem is already persisting, and you have already failed," says Ricky Meinke, Director of the Rat City Arts Festival. 

The Rat City Arts Festival works to educate people on rodent prevention through rat walks and mitigation education, particularly in the Allston and Brighton areas. 

"Maybe through vocalization of rats, we understand how active rats are at certain times of the day or at night, so that maybe we can place bait for rodent control at specific times," Meinke said. 

This may allow poisonous rat boxes to be on the street for less time. The poison inside can sometimes be harmful to other animals. 

"AI being so expansive as it is, we could only fathom it would just take a little bit of time to reach the rats," Meinke said.

All that is left to wonder is what the rats are saying about all of this. One day, we may actually know.