Mar 02, 2020

AI to Monitor E. Coli in Anacostia River

An environmental group and artificial intelligence company are teaming up to predict bacteria levels in the Anacostia River

water quality

Anacostia Riverkeeper, an environmental group, is trying to fill in water quality gaps by partnering with the artificial intelligence company DataRobot.

The goal is to predict bacteria levels, specifically E. Coli, in the Anacostia River, based on known current conditions and past information, according to WAMU.

“It’s kind of similar to how they do climate change models or weather forecasting,” said Robbie O’Donnell with Anacostia Riverkeeper. “There’s rain, there’s the turbidity at that moment, there’s the water level, there’s the tide, there’s the pH of the water, how sunny it is outside."

DataRobot is offering select nonprofits access to its artificial intelligence software and consulting on how to use it on a pro-bono basis, according to Paul Fornia, a data scientist at DataRobot.

The software uses machine learning to learn algorithms and make forecasts on future data.

The model for predicting water quality is still in the works, reported WAMU. O’Donnell hopes to start posting daily water quality forecasts in May or June and to expand to sites on the Potomac and Rock Creek later this year. The intent is for the forecasts to be a tool to help people understand water quality in addition to the weekly testing the group is conducting.

“This is not a yes or no to go jump in the water,” said O’Donnell. “If people have all the information, they can make the most up-to-date and accurate decision themselves."

This is the first time DataRobot has developed such a model for water quality. If it is successful, the team hopes it can be reproduced elsewhere.

“One of the things we’re most excited about is that it could potentially scale, to other urban riverkeepers in the U.S.," added O'Donnell. "Water quality is obviously a huge issue globally, in rural communities in Asia and Africa, for example.”

Read related content about water quality: 

expand_less