Research Approach

From 2020 to 2023, the project designed and developed a set of advanced machine learning (ML)-based algorithms and models that link ground-based in situ and space-based remote sensing observations of major air quality components with the aim to (a) identify and classify patterns in urban air quality, (b) enable the deduction and forecast of air pollution events related to PM2.5 and ozone from space-based observations, and ultimately (c) identify similarities in air quality regimes between megacities around the globe for improved air pollution mitigation strategies.

Year One

• Identified ground and space-based datasets

• Developed a framework to collect and analyze data, as well as examine  historical trends and events (e.g., weather patterns, environmental trends, etc.)

• Selected data architecture and models

• Initialized computational space for data migration

• Created, deployed, and validated initial machine learning algorithms against training data

Year Two

• Identified sister cities for collaborative workshops

• Continued to identify additional datasets

• Validated models based on emergent research

• Deployed and retrained the algorithms against control and expanded data

• Develop initial open source publication (in process)

• Held regional and international workshops to socialize the models, promote the open source, and gather requirements

The PWWB team continues to analyze publicly available data from various sources:

• NASA Worldview

• NASA Atmospheric Science Data Center (ASDC)

• AQMIS - Air Quality and Meteorological Information System

• European Commission - Copernicus Climate Data Storage (CDS)

• NASA Earth Science - MODIS Data

• Bureau of Street Lighting - sourced by South Coast Air Quality Management District (SCAQMD)

• Port of Los Angeles

• OpenAQ