Skip To Content
City using new technology to detect potholes
City utilizing new technology to detect potholes and blight
Posted on 07/31/2019
The City of Memphis is utilizing new technology to help detect potholes and blight in the community. By collaborating with Google and SpringML, this technology is expected to significantly reduce claim costs for pothole damage, and create safer streets and neighborhoods. 

For decades, the City of Memphis Division of Public Works relied on their own street maintenance crews to locate and fill potholes. With more than 6,800 miles of public streets, it has been a challenging task for crews to reliably survey and fix damaged streets.  Similarly, Public Works has experimented with using approximately 200 volunteers to survey and photograph blighted property conditions. This effort took four months to complete and the results were insufficient in identifying all of the affected properties. 

One of the measures of an effective city government is its ability to proactively tackle challenging problems such as vacant properties and deteriorating roads. Mayor Jim Strickland and City of Memphis CIO Mike Rodriguez, began investigating ways technology could offer a solution.  A conversation with Google led to the recommendation to use a machine learning proof-of-concept (POC) with SpringML, a Google Cloud partner.

“We want to do everything we can to keep our citizens happy," Rodriguez said. "Working with Google and SpringML to reduce potholes and urban blight using machine learning and artificial intelligence was an easy decision."

In the past, residents reported potholes and vacant properties by calling 311 or using the Memphis 311 app.  However, these efforts on the part of citizens identified only 20 percent of the problems, Robert Knecht, Public Works Director said. “A lot can change quickly regarding blighted property conditions in such a large city. Now with the assistance of the Google Cloud Platform and SpringML, Memphis will be able to make a significant difference in the efforts to proactively identify and manage blighted and substandard properties.”

In order to evaluate this technology, cameras were set up on city buses and code enforcement vehicles to collect video. The video was then analyzed along with data from 311 reports. Information on potholes, paving, and geolocation data was then imported into BigQuery, a Google service which helps analyze data, so the City could better understand street conditions and predict where neighborhoods were becoming vulnerable to blight. 

With help from Google and SpringML, the City expects the number of potholes will be greatly reduced. This means money saved in city claims for vehicle damage and a safer driving experience.  

Similarly, the technology used to identify blighted and vacant properties has been over 97.5 percent accurate. The use of this tool in turn, can help the City recognize and support homeowners experiencing physical or financial challenges that make it difficult for them to maintain their properties adequately.
"Our goal is to become a smart city, and technologies such as Google Cloud Platform and SpringML put us ahead of the game.” Mayor Strickland said. “Google understands data, and there isn't a better company to help us analyze our data resources for actionable insights."
City of Memphis | All Rights Reserved | Powered by CivicLive | © 2020 Intrado Corporation.