Welcome to the code companion for the 2026 NASA ARSET online training “Estimating Surface PM2.5 Using Satellite Data and Other Information Sources.” This site documents the Python notebooks, utility functions, and data access workflows used throughout the training — from downloading satellite products to computing performance metrics against ground-truth monitors.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/NASAARSET/PM2.5_AQ_Online_2026/llms.txt
Use this file to discover all available pages before exploring further.
Introduction
Learn what the training covers, which datasets are used, and how the notebooks are organized.
Quickstart
Open a notebook in Google Colab and run your first PM2.5 data retrieval in minutes.
Data Sources
Understand the SatPM, MERRA-2 CNN, OpenAQ, and SINCA datasets used in the analysis.
API Reference
Full reference for the Python utility functions defined in the notebooks.
What You’ll Learn
The training focuses on two real-world case studies using openly available satellite-derived PM2.5 data products:- Case Study — Central Chile during the February 2023 megafires, comparing SatPM and MERRA-2 CNN estimates against SINCA ground monitors
- Homework — New Delhi and surrounding areas (June–August 2019), using SatPM, MERRA-2 CNN, and OpenAQ data
Case Study Notebook
Walk through the complete Chile wildfire analysis, including data access, visualization, and validation.
Homework Notebook
Apply the same workflow to New Delhi — your independent exercise region.
Analysis Workflow
Understand the end-to-end pipeline from data download to performance evaluation.
Performance Metrics
Reference for RMSE, bias, R², and spatial/temporal correlation calculations.
Getting Started
Create a NASA Earthdata account
Register at urs.earthdata.nasa.gov to access MERRA-2 CNN data through the
earthaccess Python library.Obtain an OpenAQ API key
Sign up at docs.openaq.org to query ground-based PM2.5 monitor data via the OpenAQ v3 API.
Open a notebook in Google Colab
Click the Colab badge on the Quickstart page or directly from the GitHub repository. Save a copy to your Google Drive before making changes.
All notebooks are available in both English and Español. Each has an exercise version (with gaps to fill in) and a completed reference version.