Hrishikesh, a data science student at IIT-Madras, wanted to get to the root of the problem. He shared his concerns with four friends he had met at an Atal Tinkering Labs event. One of them, Satyam Prakash, is also his teammate at IIT-Madras. Then there’s Manikanta Chavvakula, a business analysis student at Flame University, Jay Aherkar, a pre-university student, and Sanket Marathe, who is studying data science in Goa.
Together, they reflected. They found that nearly 50% of the world’s population still depends on groundwater, and a third still lack access to safe drinking water. “We also realized that there is no mechanism to continuously check the quality of groundwater. We wanted to find a solution that would keep all stakeholders informed about the quality of the water, ”says Hrishikesh.
It was around this time that IBM organized its global Call for Code program, one of the largest “tech for good” initiatives. The five friends immediately jumped in. Over the next seven months, they built an AI-IoT platform called Saaf Water, which won the top prize in the $ 200,000 competition.
The team has developed a complete product suite consisting of a cellular hardware component and a software platform that primarily runs on IBM Cloud and IBM Watson IoT services. While Hrishikesh is responsible for the overall management of the project and software work, Satyam takes care of the hardware component.
The hardware is a plug-and-play device equipped with sensors that check parameters such as the pH value of the water, total dissolved salts (TDS), turbidity and temperature. “Any local plumber can install it at the water source. It just needs a power supply, ”explains Satyam. The microcontroller in the box relays the data from the sensors to the cloud and the Watson IoT service, where it is processed. The box is designed to work even on 2G bandwidth.
“Behind the scenes, our algorithms check past data from that particular water source, other groundwater datasets, and then look for patterns. For example, the algorithms will look for TDS, electrical conductivity, temperature and other derived parameters, and can predict whether there is a presence of heavy metals, ”Hrishikesh explains.
The solution does not replace testing. The device may periodically update the local administration, so that it knows which water source to test.
A visual indicator is also integrated into the hardware. If the water quality is very poor, the device will display a red signal. “This even allows a user without a mobile connection or without access to the Saaf Water dashboard to know the quality of the water,” explains Satyam.
The team hosted Saaf Water on the open source platform GitHub and are looking to build a community around it.