DataRobot Case Studies Anacostia Riverkeeper Uses DataRobot to Predict Water Quality in the Anacostia River

Edit This Case Study Record

	Anacostia Riverkeeper Uses DataRobot to Predict Water Quality in the Anacostia River DataRobot

Anacostia Riverkeeper Uses DataRobot to Predict Water Quality in the Anacostia River

DataRobot

Technology Category	Analytics & Modeling - Predictive Analytics
Applicable Industries	Cities & Municipalities
Use Cases	Predictive Quality Analytics
Services	Data Science Services
Challenge	Anacostia Riverkeeper is a nonprofit organization dedicated to protecting and restoring the Anacostia River, which runs through Washington, DC and parts of Maryland. The river is heavily polluted, and swimming has been illegal since the 1970s due to health concerns about pollution. The current methods for testing water quality take days to return results, creating a delay between when the water is tested and when the results are shared with the public. Moreover, water quality can rapidly change with weather conditions, such as rain, making test results outdated before they’re even returned. Anacostia Riverkeeper needed a more efficient and timely way to monitor and predict water quality in the Anacostia River. Read More
About Customer	Anacostia Riverkeeper is a nonprofit organization based in Washington, DC. Their mission is to protect and restore the Anacostia River for all who live, work, and play in its watershed, and to advocate for a clean river for all its communities. The Anacostia River runs through the heart of Washington, DC and parts of Maryland. Like many urban waterways, it is heavily polluted, and swimming has been illegal since the 1970s due to health concerns about pollution. Read More
Solution	Through DataRobot’s AI for Good program, Anacostia Riverkeeper partnered with DataRobot to develop a system to predict if E. coli levels are above safe levels. The team collected data about the discharge, gauge height, temperature, and more from 28 sensors at different locations in the Anacostia River from the United States Geological Survey (USGS). These features were aggregated over the preceding 12 and 24 hours to capture a historical sense of the river’s conditions. The team used DataRobot to build and train dozens of binary classification models, and then selected and deployed the best model. The solution engineers then built a script that pulls the USGS sensor data, aggregates it, and sends it to DataRobot for scoring. The results are stored in a database and visualized using Tableau. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Predictive Analytics

Applicable Industries

Cities & Municipalities

Use Cases

Predictive Quality Analytics

Services

Data Science Services

Challenge

Anacostia Riverkeeper is a nonprofit organization dedicated to protecting and restoring the Anacostia River, which runs through Washington, DC and parts of Maryland. The river is heavily polluted, and swimming has been illegal since the 1970s due to health concerns about pollution. The current methods for testing water quality take days to return results, creating a delay between when the water is tested and when the results are shared with the public. Moreover, water quality can rapidly change with weather conditions, such as rain, making test results outdated before they’re even returned. Anacostia Riverkeeper needed a more efficient and timely way to monitor and predict water quality in the Anacostia River.

About Customer

Anacostia Riverkeeper is a nonprofit organization based in Washington, DC. Their mission is to protect and restore the Anacostia River for all who live, work, and play in its watershed, and to advocate for a clean river for all its communities. The Anacostia River runs through the heart of Washington, DC and parts of Maryland. Like many urban waterways, it is heavily polluted, and swimming has been illegal since the 1970s due to health concerns about pollution.

Solution

Through DataRobot’s AI for Good program, Anacostia Riverkeeper partnered with DataRobot to develop a system to predict if E. coli levels are above safe levels. The team collected data about the discharge, gauge height, temperature, and more from 28 sensors at different locations in the Anacostia River from the United States Geological Survey (USGS). These features were aggregated over the preceding 12 and 24 hours to capture a historical sense of the river’s conditions. The team used DataRobot to build and train dozens of binary classification models, and then selected and deployed the best model. The solution engineers then built a script that pulls the USGS sensor data, aggregates it, and sends it to DataRobot for scoring. The results are stored in a database and visualized using Tableau.

Impact #1	The team was able to build and train dozens of binary classification models using DataRobot.
Impact #2	The best model was selected and deployed for use.
Impact #3	A script was built that pulls the USGS sensor data, aggregates it, and sends it to DataRobot for scoring.

Impact #1

The team was able to build and train dozens of binary classification models using DataRobot.

Impact #2

The best model was selected and deployed for use.

Impact #3

A script was built that pulls the USGS sensor data, aggregates it, and sends it to DataRobot for scoring.

Download PDF Version

Overview

Anacostia Riverkeeper Uses DataRobot to Predict Water Quality in the Anacostia River

Operational Impact