Next Article in Journal
Empirical and Comparative Validation for a Building Energy Model Calibration Methodology
Next Article in Special Issue
Comparisons of Laboratory and On-Road Type-Approval Cycles with Idling Emissions. Implications for Periodical Technical Inspection (PTI) Sensors
Previous Article in Journal
Robust Wavelength Selection Using Filter-Wrapper Method and Input Scaling on Near Infrared Spectral Data
Previous Article in Special Issue
Wildfire Smoke Adjustment Factors for Low-Cost and Professional PM2.5 Monitors with Optical Sensors
Article

Application of Machine Learning for the in-Field Correction of a PM2.5 Low-Cost Sensor Network

1
Research Center for Environmental Changes, Academia Sinica, Nangang, Taipei 115, Taiwan
2
Department of Atmospheric Sciences, National Taiwan University, Taipei 106, Taiwan
3
Institute of Environmental Health, National Taiwan University, Taipei 106, Taiwan
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(17), 5002; https://doi.org/10.3390/s20175002
Received: 12 July 2020 / Revised: 27 August 2020 / Accepted: 31 August 2020 / Published: 3 September 2020
(This article belongs to the Special Issue Sensors for Air Quality Monitoring)
Many low-cost sensors (LCSs) are distributed for air monitoring without any rigorous calibrations. This work applies machine learning with PM2.5 from Taiwan monitoring stations to conduct in-field corrections on a network of 39 PM2.5 LCSs from July 2017 to December 2018. Three candidate models were evaluated: Multiple linear regression (MLR), support vector regression (SVR), and random forest regression (RFR). The model-corrected PM2.5 levels were compared with those of GRIMM-calibrated PM2.5. RFR was superior to MLR and SVR in its correction accuracy and computing efficiency. Compared to SVR, the root mean square errors (RMSEs) of RFR were 35% and 85% lower for the training and validation sets, respectively, and the computational speed was 35 times faster. An RFR with 300 decision trees was chosen as the optimal setting considering both the correction performance and the modeling time. An RFR with a nighttime pattern was established as the optimal correction model, and the RMSEs were 5.9 ± 2.0 μg/m3, reduced from 18.4 ± 6.5 μg/m3 before correction. This is the first work to correct LCSs at locations without monitoring stations, validated using laboratory-calibrated data. Similar models could be established in other countries to greatly enhance the usefulness of their PM2.5 sensor networks. View Full-Text
Keywords: efficient in-field PM2.5 correction; random forest model; particle sensing correction; in-field calibration; PM sensing device efficient in-field PM2.5 correction; random forest model; particle sensing correction; in-field calibration; PM sensing device
Show Figures

Figure 1

MDPI and ACS Style

Wang, W.-C.V.; Lung, S.-C.C.; Liu, C.-H. Application of Machine Learning for the in-Field Correction of a PM2.5 Low-Cost Sensor Network. Sensors 2020, 20, 5002. https://doi.org/10.3390/s20175002

AMA Style

Wang W-CV, Lung S-CC, Liu C-H. Application of Machine Learning for the in-Field Correction of a PM2.5 Low-Cost Sensor Network. Sensors. 2020; 20(17):5002. https://doi.org/10.3390/s20175002

Chicago/Turabian Style

Wang, Wen-Cheng V., Shih-Chun C. Lung, and Chun-Hu Liu. 2020. "Application of Machine Learning for the in-Field Correction of a PM2.5 Low-Cost Sensor Network" Sensors 20, no. 17: 5002. https://doi.org/10.3390/s20175002

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop