Low-cost sensor data for data weighting

Uncalibrated and calibrated sensor data used in Frischmon, et. al. "Improving the quantification of peak concentrations for air quality
sensors via data weighting." Atmospheric Measurement Techniques, 2025.

The uncalibrated data contains all sensor inputs used to build the calibration models. The calibrated data contains the concentrations predicted from the calibration models.

Please note the data was time-averaged (median) to 1-hour intervals prior to publication. The first hour of data collection was also removed prior to publication, as the metal oxide sensors require a warm-up period to reach operating temperatures.

File name key:
MLR: multiple linear regression model predictions
randomforest: Random forest model predictions
pw#: piecewise, with a percentile cut-off point at the #th percentile
offset#: sigmoidal weighting with a z-scored offset of #

Units:
CH4 concentration- ppm
TVOC concentration- ppb
CO concentration- ppm

Uncalibrated sensor data does not have units, as it is an uncalibrated sensor signal.