← Back to NASA Technology Projects
CC21 NASA Air-athon: Predict Air Quality
Completed
Description
The science of using satellite data to study the health effects of trace gas and particulate pollutants is relatively new, rapidly evolving, and often relies on integration of satellite data with ground-based monitor measurements, atmospheric models, and a host of ancillary datasets. A crowdsourcing campaign has the potential to develop tools to combine existing NASA satellite data, model outputs, and ground measurements to disseminate valuable air quality data to the user community, while advancing the state of the science for future NASA projects, including MAIA, TEMPO, and the Aerosol and Cloud, Convection and Precipitation (ACCP) mission identified by the most recent Earth Science Decadal Survey.
Air pollution is one of the greatest environmental threats to human health. Currently, no single satellite provides ready-to-use, high resolution information on surface-level air pollutants. This gap in information means that millions of people may not be able to take daily action to monitor air quality and manage their exposure to protect their health. The goal of this challenge is to generate daily estimates of surface-level NO 2 and PM2.5 across 5-kilometer grid spacing across three urban areas: Los Angeles South Coast Air Basin, United States; Delhi, India; and Taipei, Taiwan. NO 2 refers to nitrogen dioxide, which lasts less than a day in the atmosphere, but can lead to respiratory and asthma issues and the formation of other harmful pollutants, such as ozone and particulate matter. PM2.5 refers to particulate matter less than 2.5 micrometers in size. It can last days to weeks in the atmosphere and penetrate deep into human lungs, resulting in major health concerns. Existing ground monitors are expensive and have large gaps in coverage. Models that make use of widely available, low-cost sensor data and satellite imagery have the potential to provide local, daily air quality information to hundreds of thousands of people. The Challenge: NASA Air-athon requires solvers to use satellite imagery, low-cost sensor data, and meteorological data to develop models for estimating daily levels of PM2.5 and NO 2 with high spatial resolution The Prize: Top ideas will share a total prize purse of $50,000 To accept the challenge, visit https://airathon.drivendata.org/
Benefits
Github repo: https://github.com/drivendataorg/nasa-airathon The top model for the PM2.5 track achieved an R-squared value of 0.81 and the top model for the NO2 track achieved an R-squared value of 0.48, representing significant improvement over baseline measures. See results blog post for more information: https://www.drivendata.co/blog/nasa-airathon-winners/
Significantly Advanced Towards a Solution
Planned for future implementation
Algorithm
Details
| Technology area | Sensors and Instruments > In Situ Instruments and Sensors |
| Program | Prizes, Challenges, and Crowdsourcing (PCC) |
| Lead organization | Marshall Space Flight Center, Huntsville, AL |
| Start date | 2021-09-16 |
| End date | 2022-06-22 |
Project contacts
Listed on TechPort itself — the most direct way to ask about this specific project.
How to get involved
This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.
None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.