A machine learning field calibration method for improving the performance of low-cost particle sensors. (March 2021)

• Record Type: Journal Article
• Authors: Patra, Satya S.; Ramsisaria, Rishabh; Du, Ruihang; Wu, Tianren; Boor, Brandon E.
• Is Part Of: Building and environment. Volume 190(2021)
• Publication Date: 2021-03
• Subjects: Indoor air quality -- Particulate matter -- Sensors -- Aerosol size distributions -- Cooking emissions -- Optical particle counters; Buildings -- Environmental engineering -- Periodicals; Building -- Research -- Periodicals; Constructions -- Technique de l'environnement -- Périodiques; Electronic journals; 696
• DOI: 10.1016/j.buildenv.2020.107457
• Languages: English
• ISSNs: 0360-1323

Abstract

Abstract: Measurements of airborne particles in buildings with low-cost optical particle counters (OPCs) are often inaccurate and subject to uncertainties. This study introduces a methodology to improve the performance of low-cost OPCs in measuring indoor particles through machine learning. A two-month field measurement campaign was conducted in an occupied net-zero energy house. The studied OPCs (OPC–N2, Alphasense Ltd.) report size fractionated concentrations from 0.38 to 17.5 μm. Co-located reference instrumentation included a scanning mobility particle sizer (SMPS: 0.01–0.30 μm) and an optical particle sizer (OPS: 0.30–10 μm). The machine learning field calibration method applies Gaussian Process Regression (GPR) and includes two components: (1.) correction of the size-resolved OPC counting efficiency from 0.38 to 10 μm and (2.) prediction of volume size distributions (mass proxy) below the 0.38 μm detection limit of the OPC. The field calibration method is applicable to OPCs that report size fractionated concentrations. In (1.), a GPR function was used to correct the size-resolved counting efficiency of the OPCs between 0.38 and 10 μm using the OPS as reference. In (2.), a second GPR function was used to predict the volume size distribution below 0.38 μm using the SMPS/OPS as reference. This was done given the significant contribution of sub-0.38 μm particles to volume concentrations in the accumulation mode. The machine learning field calibration method resulted in a significant improvement in the accuracy of size-integrated volume concentrations ( PV 2.5, PV 10 ) reported by the OPCs as compared to the SMPS/OPS. Improvements were seen in the Pearson coefficient (before correction: 0.59–0.83; after correction: 0.98–0.99); coefficient of determination (before correction: 0.35–0.69; after correction: 0.97–0.98); and mean absolute percentage error (before correction: 35–69%; after correction: 19–25%). Highlights: Developed a new machine learning field calibration method for improving the performance of low-cost OPCs. A two-month measurement campaign was conducted in a net-zero energy house to evaluate the calibration method. Calibration method improves the accuracy with which OPCs report indoor particle volume size distributions. Method is first to account for the volume contribution of the "missing" sub-0.38 μm particles not measured by OPCs. A non-parametric, size-resolved approach to OPC calibration targets limitations in particle detection/sizing by OPCs.