Data sources

Data sources

hackAIR is developing the following community-driven data sources:

  1. Image analysis: air quality information derived from mobile phone pictures of the sky;
  2. Open hardware sensors: an easy-to-build open hardware sensor module that transmits regular air quality measurements via Bluetooth; and
  3. Low-tech air quality measurement: a low-tech measurement setup involving cardboard and petroleum jelly.

Image analysis

Photos of the sky can be used to estimate air pollution for a particular location. For hackAIR, we are taking advantage of public, unfiltered, geo-tagged images posted to social media platforms such as Instagram. In addition, users of the hackAIR platform will be able to upload their own images directly to the system.

 

Open hardware sensors

 

Anyone can learn to build a functional air quality sensor, using widely available electronics components like the Arduino microcontroller. As part of its toolkit, hackAIR will provide instructions (and code) to build a sensor compatible with the hackAIR platform. In addition to Arduino, we are also supporting the PSoC controller. Sensor data can be uploaded to hackAIR using a Bluetooth low energy module.

 

Low-tech measurement setup

Air quality estimates do not necessarily require complicated electronics. Using a piece of cardboard, you can build a simple measurement setup to catch particulate matter in grease. You’ll see the difference with your naked eye. If you snap a picture of the board with your phone, the hackAIR app provides you with a more accurate air quality score.

In addition to its own sensors, hackAIR is combining data from different external sources:

  • official open official data, and
  • publicly available images posted through social media.

This multimodal air quality data will then be collected and processed into a unified air quality indicator, leveraging recent advances in web information retrieval, image analysis, open hardware, machine learning and data fusion. The resulting multimodal environmental data collection framework for integrating content from heterogeneous resources can also be applied fields beyond air quality.