The 2021 challenge focuses on air pollution measurement and prediction. Wildfires in the US West raised clouds of smoke which lingered for months. This dramatic incident only highlighted existing problems caused by decades of industrial and other pollution.
Air is life and polluted air harms us all, especially those of us with respiratory problems. Polluted air damages humans, animals and plants. Anything that we can do to reduce harm from air pollution, we should do. The first step in solving a problem is to know the problem by measuring and modeling.
The 2021 challenge asks participants to seek existing datasets and provide public access to citizen scientists in the United states. For the air quality prediction project, there are several possible data sources that teams could consider, including:
- Government air quality monitoring stations: Many governments operate air quality monitoring stations that measure various pollutants such as nitrogen dioxide, particulate matter, and ozone. Teams could use this data to build models that predict air quality in a particular region.
- Satellite imagery: Satellites can also provide valuable information on air quality, particularly for large geographic regions. Teams could use satellite data to monitor air quality and develop models that predict changes over time.
- Mobile air quality monitoring devices: There are several low-cost air quality monitoring devices that individuals can use to measure pollutants in the air. Teams could potentially distribute these devices to individuals in a particular region and use the data collected to build models that predict air quality.
Models for the challenge need not be deep learning models. This project will focus on data pipelines and applications of available models which require little training such as those in the sci-kit learn. Projects will be judged based on reproducibility and clarity of presentation.