Articles | Volume 19, issue 9
https://doi.org/10.5194/amt-19-2923-2026
https://doi.org/10.5194/amt-19-2923-2026
Research article
 | 
04 May 2026
Research article |  | 04 May 2026

Evaluating machine learning model performance in a two-step colocation process for TVOC and BTEX sensor calibration

Caroline Frischmon, Jack Porter, Ethan Balagopalan, William Senga, Jill Johnston, and Michael Hannigan

Data sets

Low-cost sensor data for VOC and BTEX calibration Caroline Frischmon and Michael Hannigan https://doi.org/10.17632/fs25d4b64k.1

Download
Short summary
We implemented a two-step colocation strategy to improve the transferability of sensor calibration models to field conditions, particularly for total volatile organic compound (TVOC) and benzene, toluene, ethylbenzene, and xylene (BTEX) sensors. In our comparison of various calibration models, we found that they generally performed well even as they tended to overpredict baseline concentrations and underpredict peaks. This work provides important insights on TVOC and BTEX sensor calibration.
Share