Divining Air Quality With A Cheap Computer Vision Device

October 5, 2025 by Lewin Day 10 Comments

There are all kinds of air quality sensors on the market that rely on all kinds of electro-physical effects to detect gases or contaminants and report them back as a value. [lucascreator] has instead been investigating a method of determining air quality that is closer to divination than measurement—using computer vision and a trained AI model.

The system relies on an Unihiker K10—a microcontroller module based around the ESP32-S3 at heart. The chip is running a lightweight convolutional neural network (CNN) trained on 12,000 images of the sky. These images were sourced from a public dataset; they were taken in India and Nepal, and tagged with the relevant Air Quality Index at the time of capture. [lucascreator] used this data to train their model to look at an image taken with a camera attached to the ESP32 and estimate the air quality index based on what it has seen in that existing dataset.

It might sound like a spurious concept, but it does have some value. [lucascreator] cites studies where video data was used for low-cost air quality estimation—not as a replacement for proper measurement, but as an additional data point that could be sourced from existing surveillance infrastructure. Performance of such models has, in some cases, been remarkably accurate.

[lucascreator] is pragmatic about the limitations of their implementation of this concept, noting that their very compact model didn’t always perform the best in terms of determining actual air quality. The concept may have some value, but implementing it on an ESP32 isn’t so easy if you’re looking for supreme accuracy. We’ve featured some other great air quality projects before, though, if you’re looking for other ways to capture this information. Video after the break.

Continue reading “Divining Air Quality With A Cheap Computer Vision Device” →

Air Quality Monitor Plays Game Of Life

October 3, 2025 by Lewin Day 8 Comments

The problem with air quality is that you can’t really tell how good or bad it is just by looking…unless it’s really bad, that is. It’s usually more helpful to have some kind of sensor that can tell you what the deal is. To that end, [Arnov Sharma] built a neat air quality monitor with a fun twist.

A Raspberry Pi Pico W acts as the heart of the build, armed with an SGP40 gas sensor. This sensor is intended for monitoring total volatile organic compounds in the air, which can be a useful measure of air quality in at least one dimension. It reports a simple air quality score from 0 to 500, based on a 1-1000 ppm ethanol equivalent reading. Based on the sensor’s output, the Pi Pico drives an LED matrix display — setting it green for good quality air, yellow for moderate, and red for poor air quality (i.e. high VOC content). The fun part is that rather than just show a simple color, the display plays Conway’s Game of Life to create an animated visual. We’d love it even more if poor air quality lead to the premature death of individual cells, making it even more interactive.

We’ve featured other air quality monitors before; often, it’s desirable to monitor CO2 levels to determine whether more ventilation is needed.

Continue reading “Air Quality Monitor Plays Game Of Life“ →

Serious Chemical Threat Sniffer On A Budget

September 16, 2025 by Heidi Ulrich 40 Comments

Chemical warfare detection was never supposed to be a hobbyist project. Yet here we are: Air Quality Guardian by [debdoot], the self-proclaimed world’s first open source chemical threat detection system, claims to pack lab-grade sensing into an ESP32-based build for less than $100. Compare that with $10,000+ black-box hardware and you see why this is worth trying at home, even if this project might not have the nut cracked just yet.

Unlike your air monitor from IKEA, the device aims to analyze raw gas sensor resistance – ohm-level data most devices throw away – combined with temporal spikes, humidity correlations, and a database of 35+ signatures. Of course, there is a lot of work to be done here on the calibration side, and we don’t have any chemical warfare agents on hand to test against, so we have no idea how well it works, and we’d expect false positives. Still, the idea of taking a more granular look at the data coming off the sensor may bear some fruit.

(Editor’s note: edited with a hefty dash of skeptical salt.)

Featured Image by Arjun Lama on Unsplash

AqMood Is An Air Quality Monitor With An Attitude

March 27, 2025 by Tom Nardi No comments

You take your air quality seriously, so shouldn’t your monitoring hardware? If you’re breathing in nasty VOCs or dust, surely a little blinking LED isn’t enough to express your displeasure with the current situation. Luckily, [Tobias Stanzel] has created the AqMood to provide us with some much-needed anthropomorphic environmental data collection.

To be fair, the AqMood still does have its fair share of LEDs. In fact, one might even say it has several device’s worth of them — the thirteen addressable LEDs that are run along the inside of the 3D printed diffuser will definitely get your attention. They’re sectioned off in such a way that each segment of the diffuser can indicate a different condition for detected levels of particulates, VOCs, and CO2.

But what really makes this project stand out is the 1.8 inch LCD mounted under the LEDs. This display is used to show various emojis that correspond with the current conditions. Hopefully you’ll see a trio of smiley faces, but if you notice a bit of side-eye, it might be time to crack a window. If you’d like a bit more granular data its possible to switch this display over to a slightly more scientific mode of operation with bar graphs and exact figures…but where’s the fun in that?

[Tobias] has not only shared all the files that are necessary to build your own AqMood, he’s done a fantastic job of documenting each step of the build process. There’s even screenshots to help guide you along when it’s time to flash the firmware to the XIAO Seeed ESP32-S3 at the heart of the AqMood.

If you prefer your air quality monitoring devices be a little less ostentatious, IKEA offers up a few hackable models that might be more your speed.

Cute Face Tells You How Bad The Air Quality Is

February 13, 2025 by Lewin Day 3 Comments

You can use all kinds of numbers and rating systems to determine whether the air quality in a given room is good, bad, or somewhere in between. Or, like [Makestreme], you could go for a more human visual interface. He’s built a air quality monitor that conveys its information via facial expressions on a small screen.

Named Gus, the monitor is based around a Xiao ESP32-C3. It’s hooked up with the SeeedStudio Grove air quality sensor, which can pick up everything from carbon monoxide to a range of vaguely toxic and volatile gases. There’s also a THT22 sensor for measuring temperature and humidity. It’s all wrapped up in a cute 3D-printed robot housing that [Makestreme] created in Fusion 360. A small OLED display serves as Gus’s face.

The indications of poor air quality are simple and intuitive. As “Gus” detects poor air, his eyelids droop and he begins to look more gloomy. Of course, that doesn’t necessarily tell you what you should do to fix the air quality. If your issue is pollution from outside, you’ll probably want to shut windows or turn on an air purifier. On the other hand, if your issue is excess CO2, you’ll want to open a window and let fresh air in. It’s a limitation of this project that it can’t really detect particulates or CO2, but instead is limited to CO and volatiles instead. Still, it’s something that could be worked around with richer sensors a more expressive face. Some will simply prefer hard numbers, though, whatever the case. To that end, you can tap Gus’s head to get more direct information from what the sensors are seeing.

We’ve seen some other great air quality projects before, too, with remarkably similar ideas behind them. Video after the break.

Continue reading “Cute Face Tells You How Bad The Air Quality Is” →

Upper Room UV-C Keeps Air Cleaner

December 18, 2024 by Lewin Day 59 Comments

2020 saw the world rocked by widespread turmoil, as a virulent new pathogen started claiming lives around the globe. The COVID-19 pandemic saw a rush on masks, air filtration systems, and hand sanitizer, as terrified populations sought to stave off the deadly virus by any means possible.

Despite the fresh attention given to indoor air quality and airborne disease transmission, there remains one technology that was largely overlooked. It’s the concept of upper-room UV sterilization—a remarkably simple way of tackling biological nastiness in the air.

Continue reading “Upper Room UV-C Keeps Air Cleaner” →

A CO2 Traffic Light On An SAO

November 6, 2024 by Dave Rowntree 12 Comments

[David Bryant] clearly has an awareness of the impact of an excess concentration of CO₂ in the local environment and has designed an SAO board to add a CO₂ traffic light indicator to one of the spare slots on the official Hackaday Supercon 2024 badge.

The part used is the Sensirion SCD40 ‘true’ CO2 sensor, sitting atop an Adafruit rider board. [David] got a leg up on development by creating a simple SAO breakout board, which could have either the male and female connectors fitted, as required. Next, he successfully guessed that the badge would be based around the RP2040 running MicroPython and hooked up an Adafruit Feather RP2040 board to get started on some software to drive the thing. This made hooking up to the official badge an easy job. Since the SAO has only two GPIOs, [David] needed to decode these to drive the three LEDs. There are a few ways to avoid this, but he wanted to relive his earlier EE college years and do it the direct way using a pair of 74HC00 quad NAND gate chips.

We’ve seen a few CO₂ monitors over the years. This sleek little unit is based around the Seeeduino XIAO module and uses an LED ring as an indicator. Proper CO₂ monitors can be a little pricey, and there are fakes out there. Finally, CO₂ is not the only household pollutant; check out this project.