Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Applications of low-cost sensing technologies for air quality monitoring and exposure assessment: How far have they gone?

End-user perspective of low-cost sensors for outdoor air pollution monitoring.

. Low-cost sensing strategies hold the promise of denser air quality monitoring networks, which could significantly improve our understanding of personal air pollution exposure. Additionally, low-cost air quality sensors could be deployed to areas where limited monitoring exists. However, low-cost sensors are frequently sensitive to environmental conditions and pollutant cross-sensitivities, which have historically been poorly addressed by laboratory calibrations, limiting their utility for monitoring. In this study, we investigated different calibration models for the Real-time Affordable Multi-Pollutant (RAMP) sensor package, which measures CO, NO2, O3, and CO2. We explored three methods: (1) laboratory univariate linear regression, (2) empirical multiple linear regression, and (3) machine-learning-based calibration models using random forests (RF). Calibration models were developed for 16–19 RAMP monitors (varied by pollutant) using training and testing windows spanning August 2016 through February 2017 in Pittsburgh, PA, US. The random forest models matched (CO) or significantly outperformed (NO2, CO2, O3) the other calibration models, and their accuracy and precision were robust over time for testing windows of up to 16 weeks. Following calibration, average mean absolute error on the testing data set from the random forest models was 38 ppb for CO (14 % relative error), 10 ppm for CO2 (2 % relative error), 3.5 ppb for NO2 (29 % relative error), and 3.4 ppb for O3 (15 % relative error), and Pearson r versus the reference monitors exceeded 0.8 for most units. Model performance is explored in detail, including a quantification of model variable importance, accuracy across different concentration ranges, and performance in a range of monitoring contexts including the National Ambient Air Quality Standards (NAAQS) and the US EPA Air Sensors Guidebook recommendations of minimum data quality for personal exposure measurement. A key strength of the RF approach is that it accounts for pollutant cross-sensitivities. This highlights the importance of developing multipollutant sensor packages (as opposed to single-pollutant monitors); we determined this is especially critical for NO2 and CO2. The evaluation reveals that only the RF-calibrated sensors meet the US EPA Air Sensors Guidebook recommendations of minimum data quality for personal exposure measurement. We also demonstrate that the RF-model-calibrated sensors could detect differences in NO2 concentrations between a near-road site and a suburban site less than 1.5 km away. From this study, we conclude that combining RF models with carefully controlled state-of-the-art multipollutant sensor packages as in the RAMP monitors appears to be a very promising approach to address the poor performance that has plagued low-cost air quality sensors.

/pdf/a-machine-learning-calibration-model-using-random-forests-to-3l9z20eje0.pdf

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

. A fast-growing area of research is the development of low-cost sensors for
measuring air pollutants. The affordability and size of low-cost particle
sensors makes them an attractive option for use in experiments requiring a
number of instruments such as high-density spatial mapping. However, for
these low-cost sensors to be useful for these types of studies their accuracy
and precision need to be quantified. We evaluated the Alphasense OPC-N2, a
promising low-cost miniature optical particle counter, for monitoring ambient
airborne particles at typical urban background sites in the UK. The precision
of the OPC-N2 was assessed by co-locating 14 instruments at a site to
investigate the variation in measured concentrations. Comparison to two
different reference optical particle counters as well as a TEOM-FDMS enabled
the accuracy of the OPC-N2 to be evaluated. Comparison of the OPC-N2 to the
reference optical instruments shows some limitations for measuring mass
concentrations of PM 1 , PM 2.5 and PM 10 . The OPC-N2 demonstrated
a significant positive artefact in measured particle mass during times of
high ambient RH (> 85 %) and a calibration factor was
developed based upon κ -Kohler theory, using average bulk particle
aerosol hygroscopicity. Application of this RH correction factor resulted in
the OPC-N2 measurements being within 33 % of the TEOM-FDMS, comparable to
the agreement between a reference optical particle counter and the TEOM-FDMS
(20 %). Inter-unit precision for the 14 OPC-N2 sensors of
22  ±  13 % for PM 10 mass concentrations was observed. Overall,
the OPC-N2 was found to accurately measure ambient airborne particle mass
concentration provided they are (i) correctly calibrated and (ii) corrected
for ambient RH. The level of precision demonstrated between multiple
OPC-N2s suggests that they would be
suitable devices for applications
where the spatial variability in particle concentration was to be determined.

/pdf/evaluation-of-a-low-cost-optical-particle-counter-alphasense-6wv5uuxg2t.pdf

Evaluation of a low-cost optical particle counter (Alphasense OPC-N2) for ambient air monitoring

https://digital.csic.es/bitstream/10261/174922/1/Assessment%20of%20air%20quality%20microsensors%20versus%20reference%20methods.pdf

P. Smith

Papers

Assessment of air quality microsensors versus reference methods: The EuNetAir joint exercise