“We didn’t know about the leak until our water bill spiked over $100.”
Mark Kovscek, CEO at Conservation Labs
There are more than 3 trillion gallons of unwanted water use each year in the U.S. costing more than $70 billion. Now, machine learning is enabling a SaaS company to directly address this critical issue. Conservation Labs, an Amazon Alexa Fund portfolio company founded by mathematician Mark Kovscek, has developed easy to install products that track the unique sound signature of water as it flows through a plumbing system.
For 25 years, Kovscek consulted with corporations analyzing their data to increase efficiencies, discover new opportunities and better target their spending.
“I was doing really quite well with it, working with large brands. Then I had a leak in my house,” Kovscek said.
This event set Kovscek on a new path beginning with understanding the impact that wasted or mis-used water has on individuals, communities, and the planet. His journey led to the creation of Conservation Labs, an IoT and AI company that provides access to water usage data and custom conservation recommendations to its clients through its proprietary H2know technology.
H2know “attaches where the main pipe enters a property and requires less than 10 minutes to install,” he explains. “No plumber is required. No special tools are required. For about $100, one H2know can protect and monitor an entire house, restaurant, apartment, or similar property. A mobile and desktop app provide water flow estimates, leak alerts, water insights and conservation recommendations.”
Conservation Labs’ H2Know technology collects a range of sound data every second and translates the data to water usage patterns. To harness the abundance of data collected, they needed to apply machine learning techniques to accurately predict water flow and identify leaks. In addition, they needed a deployment-capable analytics platform to quickly and efficiently onboard new team members and partners using the technology.
Working together, Lityx and Conservation Labs analyzed sound frequency data collected from the company’s H2know sensors to build initial water flow prediction models and test them in-market. LityxIQ’s automated machine learning and deployment capabilities made testing a wide variety of algorithms and approaches easy and efficient. The platform also provided comprehensive data enhancement functionality, allowing hundreds of features to be computed from the raw data and serve as machine learning inputs. An automated process was created to import data on a near-real-time basis and process it for analytics, clustering, and water flow prediction.
Today, the H2Know technology is being deployed across the U.S. and internationally. “My passion is mathematics and using advanced analytics to address real-world problems. Our vision at Conservation Labs is to improve our planet for future generations,” Kovscek says.
For more information on Conservation Labs.
To learn more about the LityxIQ AutoML platform.
If you need help operationalizing an idea that can leverage AI to solve a real-world problem, contact Gary Robinson, COO, Lityx, at grobinson@lityx.com
Read about other ways that LityxIQ is helping companies solve important issues through machine learning and AI.
