Enhancing Accuracy of Indoor Air Quality Sensors via Automated Machine Learning Calibration

Qian, Juncheng; Wynn, Thomas; Liu, Bowen; Shan, Yuli; Bartington, Suzanne E.; Pope, Francis D.; Dai, Yuqing; Shi, Zongbo

doi:10.5194/amt-19-603-2026

Articles | Volume 19, issue 2

https://doi.org/10.5194/amt-19-603-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-19-603-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 2

Research article

|

23 Jan 2026

Research article |

| 23 Jan 2026

Enhancing Accuracy of Indoor Air Quality Sensors via Automated Machine Learning Calibration

Juncheng Qian, Thomas Wynn, Bowen Liu, Yuli Shan, Suzanne E. Bartington, Francis D. Pope, Yuqing Dai, and Zongbo Shi

Supplement

https://doi.org/10.5194/amt-19-603-2026-supplement

Data sets

DandE9996/sensor_calibration: Enhancing Accuracy of Indoor Air Quality Sensors via Automated Machine Learning Calibration (Sensor_Calibration) J. Qian and Y. Dai https://doi.org/10.5281/zenodo.18305879

Model code and software

DandE9996/sensor_calibration: Enhancing Accuracy of Indoor Air Quality Sensors via Automated Machine Learning Calibration (Sensor_Calibration) J. Qian and Y. Dai https://doi.org/10.5281/zenodo.18305879

Short summary

We developed a multi-stage AutoML (Automated Machine Learning) calibration framework to improve low-cost indoor PM_2.5 sensor accuracy. Using chamber tests with varied emission sources, the method corrected drift, humidity effects, and non-linear responses, raising R² above 0.9 and halving RMSE (Root Mean Square Error). The approach enables reliable, scalable indoor air quality monitoring for research and public health applications.