Hyperlocal Air Quality Prediction using Machine Learning in East Bay Area, CA

In this project, I developed machine learning models to predict air quality on a city-block basis in Oakland and San Leandro, CA, without having to rely on complex physical modeling. I used a wide variety of publicly available datasets such as previously measured pollutant concentrations, local meteorological data, emissions from local industrial sources, and traffic information.

Check out my github repo and my blog post on this work!

US County-Level Air Pollution Sequestration Dataset

I developed a county-level spatial inventory of air pollutant sequestration by grassland and shrubland vegetation in the US. The dataset was developing using the daily leaf area index of vegetation classes, the National Land Cover dataset and the i-Tree Eco model. The dataset developed in this work is currently used by

  1. California Department of Conservation and The Nature Conservancy in the TerraCount tool for land use planning.
  2. U.S. Department of Forest Service in the i-Tree Eco tool
  3. Bay Area GreenPrint Tool