Public Lab Wiki documentation



sandbox-air-quality-data

This is a revision from November 04, 2021 21:09. View all revisions
2 | 13 | | #28017

This is a draft wiki page that will change frequently!


Understanding air quality data

Question: What are some of the first things you do with air quality monitoring data to better understand it?

Different kinds of air quality data

Becoming familiar with the kind of air quality data you have can help you on the way to figuring out what you eventually want to do with the data.

Here are some questions to consider about the data:

  • Is the data from a sensor?
    • Is the data from a stationary sensor 📍 or a portable one 🚶🏽🚴🏽 that was used at different locations?
    • Is the data collected continuously over time ⏳ 🔁 or only at certain times and dates 🕑 📆 (intermittently)?


  • Is the data for a general outdoor area 🏙️ (ambient air) or a specific emission source 🏭 (e.g., fenceline monitoring)?

  • Is the data from a lab report ⚗️📄 for an air grab sample taken at a specific place and time?

  • Did you collect the data yourself 🙋🏾‍♀️ or is it from an existing database with publicly accessible data 🔓 💻?

    • If it’s from an existing database, is the data from regulatory monitors or another monitor network (e.g., community monitors, low-cost monitor networks)


  • Considering the equipment used to collect the data, what are its detection limits and data resolution? (This could look like minimum and maximum levels for measurements ⬇️⬆️, and how small a change ↔️ the equipment can measure)

  • Is your data from indoor air 🏠 or outdoor air ☀️ (ambient)?

  • Is the data mostly not numerical (qualitative)?

    • An odor log or odor report? 👃🏽
    • An oral history? 💬
    • A visual observation? 👀 (e.g., soot, colored dust, smoke)


More about different kinds of environmental data (not specific to air quality data):


What other questions can help with understanding air quality data? Please edit this page to add more!


Illustration of people collecting various kinds of air quality data around a city, an industrial facility, and a recreational park

Image: A variety of different kinds and sources of air quality data, by @renee.



Initial analysis & visualizations to understand data

Units of measurement

Looking closely at units in data can help you understand the scale of your measurements and start thinking about how to communicate that scale so it’s meaningful to other people.

a cube representing the volume of carbon dioxide emitted from burning a gallon of gasoline appears next to the silhouette of an adult and child

Image: Illustrating the volume of carbon dioxide emitted from burning one gallon of gasoline. Carbon Visuals, CC BY


Resources on units of measurement:


Making tables of tidy data

Putting your air quality data into an organized table gets it ready for making charts, graphs, and other visualizations. Below are some resources on making tables of tidy data and on "cleaning data."

Stylized text providing an overview of Tidy Data. The top reads “Tidy data is a standard way of mapping the meaning of a dataset to its structure. - Hadley Wickham.” On the left reads “In tidy data: each variable forms a column; each observation forms a row; each cell is a single measurement.” There is an example table on the lower right with columns ‘id’, ‘name’ and ‘color’ with observations for different cats, illustrating tidy data structure.



There are two sets of anthropomorphized data tables. The top group of three tables are all rectangular and smiling, with a shared speech bubble reading “our columns are variables and our rows are observations!”. Text to the left of that group reads “The standard structure of tidy data means that “tidy datasets are all alike…” The lower group of four tables are all different shapes, look ragged and concerned, and have different speech bubbles reading (from left to right) “my column are values and my rows are variables”, “I have variables in columns AND in rows”, “I have multiple variables in a single column”, and “I don’t even KNOW what my deal is.” Next to the frazzled data tables is text “...but every messy dataset is messy in its own way. -Hadley Wickham.


Images: Illustrations from the Openscapes blog “Tidy Data for reproducibility, efficiency, and collaboration” by Julia Lowndes and Allison Horst, CC BY


An example of “tidy data” from an air quality sensor might look like this:

An example of tidy air quality data in a table. There are four columns of variables with names and units 'id', 'date (dd-mm-yy)', 'time (hh:mm:ss)', and 'PM2.5 concentration (micrograms per meter cubed)'. There are four rows of data.


Each variable forms a column: sensor ID number, date, time, and the air quality measurement of particulate matter are individual variables. Each variable gets its own column in the table. The column header at the top lists the variable name and its units of measurement.

Each observation forms a row: this sensor took an air quality measurement every minute. Each measurement gets its own row in the table.

Each cell is a single measurement: each block in the table shows one piece of data--one time, one PM measurement, etc.

More resources on organizing and cleaning data:


Making visualizations to see trends and potential problems

more to come here


Communicating with air quality data

Designing a data story

more to come here

Ways to present air quality data

more to come here

Tools for making visualizations and other media

editable table of tools coming soon

Communicating the data

more to come here


Questions about air quality data

Questions tagged with question:air-quality-data will appear here

Title Author Updated Likes Comments
What strategies have been implemented to use citizen science successfully in litigation? @julia_e_masters about 2 years ago 1
What is “data storytelling” and how can it be used for environmental data? @bhamster over 2 years ago 5
What are examples of "real-life", immersive experiences that help people understand pollution? @fongvania over 2 years ago 5
What are ways to alert residents to air quality concerns without using cell phones or wifi? @bhamster over 2 years ago 2
What are examples of air quality data visualizations that don’t require coding or computationally intensive computer graphics? @bhamster over 2 years ago 2
What are some of the first things you do with air quality monitoring data to better understand it? @bhamster over 2 years ago 7
How do you turn results about environmental pollution into personal actions that people can take? @bhamster almost 3 years ago 2
How do you make results from environmental monitoring personally meaningful to people? @bhamster almost 3 years ago 2
What are ways to make dense CSV data more readable? @warren over 4 years ago 7
What are best practices and tools to help clean up data sets? @stevie over 4 years ago 24


Activities about air quality data data

Activity posts tagged with activity:air-quality-data will appear here


Activities should include a materials list, costs and a step-by-step guide to construction with photos. Learn what makes a good activity here.



Further reading and resources

  • Data Viz Project: a comprehensive online tool cataloging examples of data visualizations from the design firm Ferdio.
  • Data Carpentry: “Data Carpentry develops and teaches workshops on the fundamental data skills needed to conduct research.”
  • Wilson G, Bryan J, Cranston K, Kitzes J, Nederbragt L, Teal TK. 2017. Good enough practices in scientific computing. PLoS Comput Biol, 13(6): e1005510. LINK to paper.