According to a 2025 report from the WHO and UNICEF, approximately an entire quarter of the world’s population currently lacks consistent access to safely managed drinking water. The report also states that many people without safely managed drinking water had access to basic drinking water services. Thomas Vikström developed WaterLens as a tool intended to help users assess certain water quality indicators.

WaterLens is a compact device designed to give communities an affordable ability to monitor their local water sources. It is not a substitute for comprehensive laboratory testing and should not be used by itself to determine whether water is safe to drink. The device is designed to provide supplemental information when laboratory testing is not readily available. Its creator also designed it to be constructed and operated without advanced technical skills.

A WaterLens device can be assembled using off-the-shelf components that connect without soldering. Those components include an Arduino^® UNO Q board, a Seeed Studio Grove Base Shield, a Grove OLED screen, a Grove dual-button module, and a host of Grove sensors. Those sensors are designed to measure pH, turbidity, total dissolved solids (TDS), and oxidation-reduction potential (ORP).

Displaying measurements from each sensor may be useful, but interpreting those measurements may require relevant water quality expertise. WaterLens runs a local model, trained and deployed with Edge Impulse, that is designed to identify potential anomalies in the sensor data.

WaterLens may help identify sensor readings that warrant further investigation. A sample with no detected anomalies should not be assumed to be safe to drink, and a detected anomaly does not by itself establish that the water is unsafe. WaterLens cannot and should not replace validated water quality testing. Where laboratory testing is not readily available, the device may provide supplemental information that can help users decide whether further evaluation is appropriate. 

Arduino and UNO are trademarks or registered trademarks of Arduino S.r.l.

The post WaterLens uses AI on the edge to detect water quality issues appeared first on Arduino Blog.

While it can be straightforward to distill water to high purity, this is rarely the best method for producing water for useful purposes. Even drinking water typically needs certain minerals in it, plants may need a certain pH, and wastewater systems have a whole host of other qualities that need to be measured. Measuring water quality is a surprisingly complex endeavor as a result and often involves a wide array of sensors, much like this water quality meter from [RowlesGroupResearch].

The water quality meters that they are putting to use are typically set up in remote locations, without power, and are targeting natural bodies of water and also wastewater treatment plants. Temperature and pH are simple enough to measure and grasp, but this device also includes sensors for total dissolved solids (TDS) and turbidity which are both methods for measuring various amounts and types of particles suspended in the water. The build is based around an Arduino so that it is easy for others to replicate, and is housed in a waterproof box with a large battery, and includes data logging to an SD card in order to make it easy to deploy in remote, outdoor settings and to gather the data at a later time.

The build log for this device also goes into detail about all of the steps needed to set this up from scratch, as well as a comprehensive bill of materials. This could be useful in plenty of professional settings such as community wastewater treatment facilities but also in situations where it’s believed that industrial activity may be impacting a natural body of water. For a water quality meter more focused on drinking water, though, we’d recommend this build that is trained on its own neural network.

Millions of people all over the world don’t have access to clean drinking water, and it’s largely because of pollution by corporations and individuals. Solving this problem requires an affordable, scalable way to quickly judge water quality, package the data, and present it to an authority that can crack down on the polluters before the evidence dissipates. Ideally, the solution would be open source and easy to replicate. The more citizen scientists, the better.

[Andrei Florian]’s WaterAid flows directly from this line of thinking. Dip this small handheld device below the surface, and it quickly takes a bunch of water quality and atmospheric readings, averages them, and sends the data to a web dashboard using an Arduino MKR GSM.

WaterAid judges quality by testing the pH and the turbidity of the water, which gauges the amount of impurities. Commercial turbidity sensors work by measuring the amount of light scattered by the solids present in a liquid, so [Andrei] made a DIY version with an LED pointed at a photocell. WaterAid also reads the air temperature and humidity, and reports its location along with a timestamp.

This device can run in one of two modes, depending on the application. The enterprise mode is designed for a fleet of devices placed strategically about a body of water. In this mode, the devices sample continuously, taking readings every 15 minutes, and can send notifications that trigger on predefined thresholds. There’s also a one-and-done individual mode for hikers and campers who need to find potable water. Once WaterAid takes the readings, the NeoPixel ring provides instant color-coded judgment. Check out the demo after the break.

The HackadayPrize2020 is Sponsored by: