Evaluation and Calibration of a Low-cost Particle Sensor in Ambient Conditions Using Machine Learning Technologies

Abstract

Abstract. Particle sensing technology has shown great potential for monitoring particulate matter (PM) with very few temporal and spatial restrictions because of low-cost, compact size, and easy operation. However, the performance of low-cost sensors for PM monitoring in ambient conditions has not been thoroughly evaluated. Monitoring results by low-cost sensors are often questionable. In this study, a low-cost fine particle monitor (Plantower PMS 5003) was co-located with a reference instrument, named Synchronized Hybrid Ambient Real-time Particulate (SHARP) monitor, in Calgary Varsity air monitoring station from December 2018 to April 2019. The study evaluated the performance of this low-cost PM sensor in ambient conditions and calibrated its readings using simple linear regression (SLR), multiple linear regression (MLR), and two more powerful machine learning algorithms using random search techniques for the best model architectures. The two machine learning algorithms are XGBoost and feedforward neural network (NN). Field evaluation showed that the Pearson r between the low-cost sensor and the SHAPR instrument was 0.78. Fligner and Killeen (F-K) test indicated a statistically significant difference between the variances of the PM2.5 values by the low-cost sensor and by the SHARP instrument. Large overestimations by the low-cost sensor before calibration were observed in the field and were believed to be caused by the variation of ambient relative humidity. The root mean square error (RMSE) was 9.93 when comparing the low-cost sensor with the SHARP instrument. The calibration by the feedforward NN had the smallest RMSE of 3.91 in the test dataset, compared to the calibrations by SLR (4.91), MLR (4.65), and XGBoost (4.19). After calibrations, the F-K test using the test dataset showed that the variances of the PM2.5 values by the NN and the XGBoost and by the reference method were not statistically significantly different. From this study, we conclude that feedforward NN is a promising method to address the poor performance of the low-cost sensors for PM2.5 monitoring. In addition, the random search method for hyperparameters was demonstrated to be an efficient approach for selecting the best model structure.

Evaluating Wildfire Smoke Transport Within a Coupled Fire‐Atmosphere Model Using a High‐Density Observation Network for an Episodic Smoke Event Along Utah's Wasatch Front

“…These results suggest that low‐cost sensors that are calibrated for wildfire smoke can be effective tools for characterizing smoke plumes from wildfires. Assessments between UDAQ FEM sites and AQ&U measurements (RMSE = 8–14 μg m −3 ; relative bias < 10%) in this study were comparable to low‐cost sensor performance found in other studies (Ardon‐Dryer et al, 2019; Bulot et al, 2019; Si et al, 2019). Observations from >500 low‐cost censors revealed that smoke plumes in complex terrain can exhibit significant spatial heterogeneity that lower density FEM‐based networks may be unable to depict.…”

“…In an effort to rectify these uncertainties and biases, several studies have applied correction factors to Plantower PMS measurements to improve their accuracy and reduce biases. When correction factors are applied to low‐cost sensors, reported RMSEs range between 3.89 and 13.1 μg m −3 when evaluated with reference monitors (Ardon‐Dryer et al, 2019; Bulot et al, 2019; Gupta et al, 2018; Si et al, 2019).…”

[Retracted] Assessing Deep Learning Techniques for the Recognition of Tropical Disease in Images from Parasitological Exams

“…Three convolutional layers, 03 (three) subsampling layers, and 01 (one) dense layer were defined, with the ReLU (rectified linear unit) being used as an activation function in the convolutional layers and the logistic sigmoid in the dense layer. CifarNet was implemented using the Keras library [ 16 ] with backend support for TensorFlow [ 14 ]. The SPNN has significant results in detecting patterns in images and a similar accuracy compared to more consolidated techniques such as the CNN and SVM, as proposed by Chaganti et al [ 17 ].…”

Quantitative Analysis for Application Specific Calibration Approaches for Low-Cost Sensors for Air Quality Monitoring

“…Various ML and AI models are explored to calibrate LCS. These models include single-variable linear regression (SLR) [27]- [30], multiple-variable linear regression (MLR) [31], [32], K-nearest neighbours (K-NN) [31], random forest (RF) [33]- [35], artificial neural networks (ANN) [35]- [39], support vector machine (SVM) [40], [41] extreme gradient boosting (XGB) [42], generalised additive model (GAM) [43].…”