Meet This Year’s IBM Call for Code Global Challenge Winner: Saaf Water

Saaf Water is an accessible water quality sensor and analytics platform especially for people living in rural localities

India is a leading contributor to tech innovations, and we have added one more feather to the cap. This year’s IBM Call for Code Global Challenge is Saaf Water, an accessible water quality sensor and analytics platform, especially for people living in rural localities. The team that has built Saaf Water (Hrishikesh M. Bhandari, Jay Aherkar, Satyam Prakash, Manikanta Chavvakula and Sanket Marathe) has big plans and wants to reach locales around the globe because one-third of the world’s population does not have access to safe drinking water.

Saaf Water will receive $200,000 and support to build and improve the solution further. The Linux Foundation will also provide support to open source their application.

Analytics India Magazine interacted with the team via mail to learn more about Saaf Water and how the system will solve water contamination problems.

What is Saaf Water exactly?

Jay Aherkar explains that Saaf water is an AI-IoT platform designed to regularly monitor the groundwater and effectively communicate the information not just to the authorities but also to the community. The platform has hardware (a cellular-enabled, low-powered plug and play unit that checks for different water parameters and sends it to IBM Watson IoT Platform) and a dashboard, both connected via a backend on IBM Cloud

He adds, “This data is then analysed by our ML model and saves it in IBM Cloudant NoSQL Database. It is followed by delivering water quality and the purification methods to our user-friendly Dashboard, SMS (very resourceful for those with a feature phone or who aren’t connected to the internet) and via the onsite visual indicator. If there is any cellular disconnection, the hardware has the capability of analysing water quality offline.”

Contaminated water is a serious issue

The motivation to build this system came from a personal space. Hrishikesh’s mother fell severely ill after unknowingly consuming contaminated water from their village’s public groundwater source. The friends realised that not knowing water quality and the right purification methods is the main challenge.

Sanket Marathe explains that since approximately 50% of the world’s population is still dependent on groundwater, they felt that there exists a need for a system that regularly monitors and pre-warns about anomalies or degradations in groundwater. This led to the birth of Saaf Water. Not only does it regularly monitor groundwater but also informs the community about the degradation and the purification methods to improve it. This will lead to people around, consuming ‘Saaf’ (meaning clean in Hindi) water.”

AI and ML form the backbone

The immediate need of the hour is a system that can timely monitor groundwater and pre-warn and inform about anomalies or degradation, states Hrishikesh. Saaf water does not aim for replacing a full-fledged lab test but a system that will allow the communities to take proactive measures to improve it or seek for a lab test only when required. This gives the freedom to scale and reach every needy locale around the world, including those geographically isolated. This makes Saaf Water versatile in operations, low on maintenance and easier to deploy, he adds.

Hrishikesh explains that this comes at a cost, and this is where their custom undemanding ML model on IBM cloud steps in. The ML model, which is a combination of decision trees and other classifiers, can approximately detect the presence of physical, chemical, and biological contamination. It also allows them to track the water as a profile to make predictions of any anomalies by looking out for patterns in the sensor collected and derived parameters. It can help to integrate lab test data and weather data to make better inferences and new insight of how the water quality performs over time and changing weather. 

He adds, “Our decision tree architecture also allows our platform to inform the most appropriate domestic purification methods depending on specific water parameters derived through profiling. The hardware is also equipped with a scaled-down version of our ML model (we are testing both tinyML approach which uses Tensorflow Lite and micromlgen model which uses scikit learn) for offline analysis.”

Image: LinkedIn (The team during the IBM and DELL internship conducted by Atal Innovation Mission for Atal Tinkering Lab Marathon winners)

Open source builds trust

Satyam Prakash says that open source enables communities to build software collaboratively with contributions from the community. He feels that the trust the team has in their digital infrastructure should be proportional to how trustworthy and transparent that infrastructure is. The transparency in open source leads directly to customer trust, a stable base to build the vision of making water quality information accessible to everyone.

Exciting new features coming up

In the future, it aims at improving seasonal anomaly predictions to enable its capabilities to surface water sources like lakes and rivers. It is also working upon the detection of biological contamination without any lab test.

Saaf Water platform will also come with many other capabilities like weather data integration and translation to make it much more capable, efficient and reach a wider range of people.

More Great AIM Stories

Sreejani Bhattacharyya
I am a technology journalist at AIM. What gets me excited is deep-diving into new-age technologies and analysing how they impact us for the greater good. Reach me at sreejani.bhattacharyya@analyticsindiamag.com

More Stories

OUR UPCOMING EVENTS

8th April | In-person Conference | Hotel Radisson Blue, Bangalore

Organized by Analytics India Magazine

View Event >>

30th Apr | Virtual conference

Organized by Analytics India Magazine

View Event >>

MORE FROM AIM
Yugesh Verma
All you need to know about Graph Embeddings

Embeddings can be the subgroups of a group, similarly, in graph theory embedding of a graph can be considered as a representation of a graph on a surface, where points of that surface are made up of vertices and arcs are made up of edges

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM