A machine learning calibration model using random forests to improve sensor performance for lower-cost air quality monitoring

Zimmerman, Naomi; Presto, Albert A.; Kumar, Sriniwasa P. N.; Gu, Jason; Hauryliuk, Aliaksei; Robinson, Ellis S.; Robinson, Allen L.; R. Subramanian,

doi:https://doi.org/10.5194/amt-11-291-2018

Articles | Volume 11, issue 1

Atmos. Meas. Tech., 11, 291–313, 2018

https://doi.org/10.5194/amt-11-291-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Atmos. Meas. Tech., 11, 291–313, 2018

https://doi.org/10.5194/amt-11-291-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 11, issue 1

Research article 15 Jan 2018

Research article | 15 Jan 2018

A machine learning calibration model using random forests to improve sensor performance for lower-cost air quality monitoring

Naomi Zimmerman et al.

Supplement

https://doi.org/10.5194/amt-11-291-2018-supplement

Data sets

A machine learning calibration model using random forests to improve sensor performance for lower-cost air quality monitoring (Version v1) N. Zimmerman, A. Presto, S. Kumar, J. Gu, A. Hauryliuk, E. Robinson, A. Robinson, and R. Subramanian https://doi.org/10.5281/zenodo.1146109

Short summary

Low-cost sensors promise neighborhood-scale air quality monitoring but have been plagued by inconsistent performance for precision, accuracy, and drift. CMU and SenSevere collaborated to develop the RAMP, which uses electrochemical sensors. We present a machine learning algorithm that overcomes previous performance issues and meets US EPA's data quality recommendations for personal exposure for NO₂ and tougher "supplemental monitoring" standards for CO & ozone across 19 RAMPs for several months.