Let’s talk about air quality data! Join us for Open Call on this topic every Tuesday until Dec. 14. Click here for details!


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

bhamster is asking a question about air-quality: Follow this topic

by bhamster | October 22, 2021 16:39 | #27958


As part of the current research area review on air quality data, we're gathering information on steps leading up to creating data visualizations.

These first data analysis and visualization steps will vary depending on what kind of air quality data someone has and how it was collected. For instance, real-time data collected continuously from a stationary air sensor versus intermittent data from a hand-held monitor that was used in different locations at different times.

Any tips that people can share about their first steps related to data analysis and visualization would be greatly appreciated!



6 Comments

I always start with units and work up from there. For example, there were dramatic differences in the units used for air particulate in the medical field versus the environmental field . First place to start is units to get a feel for the conversion and what's going on.

Different fields using different units is such an important point that's not immediately obvious. Thanks @Ag8n.

Your comment reminded me of this resource originally from Statistics for Action on common units in environmental testing, which also gets into orders of magnitude: https://publiclab.org/notes/kgradow1/12-17-2020/common-units-in-air-soil-and-water-testing


Thanks for the reference. I'll read it over. Regards.


Reply to this comment...


For example, in the medical manufacturing field, class 100,000 rooms are common. Those are not the same units used in the environmental work.

Reply to this comment...


I occasionally run an indoor stationary air quality sensor that continuously collects data on fine particulate matter (PM2.5), and one of my go-to first steps is to plot PM measurement against time. This graph helps me see any initial trends or patterns in how PM measurements change over time. It also illustrates potential problems with the data, like unexpected gaps in data or unusually high/low measurements.

Reply to this comment...


The data is impressive. Dumb question here. Does the instrument autimatically check it's zero point?

Is this a question? Click here to post it to the Questions page.

Reply to this comment...


Log in to comment