Assessment of Low-Cost Particulate Matter Sensor Systems against Optical and Gravimetric Methods in a Field Co-Location in Norway

Vogt, Matthias; Schneider, Philipp; Castell, Núria; Hamer, P. D.

doi:10.3390/atmos12080961

Cited by 29 publications

(30 citation statements)

References 36 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the low-cost Sensirion SPS 30 has excellent inter-sensor precision with coefficients of determination above 0.9 [10], the ML model based on SPS 30 has the possibility of maintaining consistent performance even with new sensors. Therefore, the PM2.5 measurement results by the SPS 30 sensor are set as the input variable based on previous literature [10]. Environmental variables such as temperature and humidity have an effect on decreasing the accuracy of a In general, the ML algorithm functions as the relationship between input variables and output variables.…”

Section: Air Quality Measurement Instrumentsmentioning

confidence: 99%

“…It is very important to have consistent precision among low-cost sensors in order to build a monitoring sensor network system by the ML model. Because the low-cost Sensirion SPS 30 has excellent inter-sensor precision with coefficients of determination above 0.9 [10], the ML model based on SPS 30 has the possibility of maintaining consistent performance even with new sensors. Therefore, the PM 2.5 measurement results by the SPS 30 sensor are set as the input variable based on previous literature [10].…”

Section: Air Quality Measurement Instrumentsmentioning

confidence: 99%

“…Vogt et al [10] performed the comparison of three models of low-cost PM 2.5 sensors (Plantower 5003, Sensirion SPS 30 and Alphasense OPC-N3) against the gravimetric device in outdoor field. The SPS 30 sensor has higher accuracy and high correlation compared to other low-cost sensors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Assessment and Calibration of a Low-Cost PM2.5 Sensor Using Machine Learning (HybridLSTM Neural Network): Feasibility Study to Build an Air Quality Monitoring System

et al. 2021

View full text Add to dashboard Cite

Commercially available low-cost air quality sensors have low accuracy. The improved accuracy of low-cost PM2.5 sensors allows the use of low-cost sensor systems to reasonably investigate PM2.5 emissions from industrial activities or to accurately estimate individual exposure to PM2.5. In this work, we developed a new PM2.5 calibration model (HybridLSTM) by combining a deep neural network (DNN) optimized in calibration problems and a long short-term memory (LSTM) neural network optimized in time-dependent characteristics to improve the performance of conventional calibration algorithms of low-cost PM sensors. The PM2.5 concentrations, temperature and humidity by low-cost sensors and gravimetric-based PM2.5 measuring instrument were sampled for a sufficiently long time. The proposed model was compared with benchmarks (multiple linear regression model (MLR), DNN model) and low-cost sensor results. The gravimetric measurements were used as reference data to evaluate sensor accuracy. For root-mean-square error (RMSE) for PM2.5 concentrations, the proposed model reduced 41–60% of error when compared with the raw data of low-cost sensors, reduced 30–51% of error when compared with the MLR model and reduced 8–40% of error when compared with the MLR model. R2 of HybridLSTM, DNN, MLR and raw data were 93, 90, 80 and 59%, respectively. HybridLSTM showed the state-of-the-art calibration performance for a low-cost PM sensor. In other words, the proposed ML model has state-of-the-art calibration performance among the tested calibration algorithms.

show abstract

Section: Air Quality Measurement Instrumentsmentioning

confidence: 99%

Section: Air Quality Measurement Instrumentsmentioning

confidence: 99%

See 1 more Smart Citation

Assessment and Calibration of a Low-Cost PM2.5 Sensor Using Machine Learning (HybridLSTM Neural Network): Feasibility Study to Build an Air Quality Monitoring System

et al. 2021

View full text Add to dashboard Cite

show abstract

“…It is very important to have consistent precision among low-cost sensors in order to build a monitoring sensor network system by ML model. Because the low-cost Sensirion SPS 30 has excellent inter-sensor precision [10], the ML model based on SPS 30 have possibility of maintaining the consistent performance even with new sensors. Therefore, the PM2.5 measurement results by the SPS 30 sensor is set as the input variable.…”

Section: Air Quality Measurement Instrumentsmentioning

confidence: 99%

“…Vogt et al [10] performed the comparison of three models of low-cost PM2.5 sensors (Plantower 5003, Sensirion SPS30 and Alphasense OPC-N3) against the gravimetric device in outdoor field. Among the low-cost sensors, the SPS 30 sensor showed high accuracy in PM2.5 concentration measurement and high correlation among individual sensors.…”

Section: Introductionmentioning

confidence: 99%

Assessment and Calibration on Low-cost PM2.5 Sensor using Machin Learning (Hybrid-LSTM Neural Network): Feasibility Study to Build Air Quality Monitoring System

Park¹,

Yoo²,

Park³

et al. 2021

Preprint

View full text Add to dashboard Cite

Although commercially-available low-cost air quality sensors have low accuracy, the sensor system are being used to collect the data for the regulation of PM2.5 emission caused by industrial activities or to estimate the personal exposure for PM2.5. In this work, to solve the accuracy problem of low-cost PM sensor, we developed a new PM2.5 calibration model by combining the deep neural network (DNN) optimized in calibration problem and a LSTM optimized in time-dependent characteristics. First, two datasets were generated to test the accuracy performance and generalization performance of the PM2.5 calibration machine learning (ML) model. The PM2.5 concentrations, temperature and humidity by low-cost sensor and gravimetric-based PM2.5 measuring instrument were sampled for a sufficiently long time. The proposed model was compared with benchmark (multiple linear regression model) and low-cost sensor results. For root mean square error (RMSE) for PM2.5 concentrations, the proposed model reduced 41-60% of error compared to the raw data of low-cost sensor, and reduced 30-51% of error compared to the benchmark model. R2 of ML model, MLR and raw data were 93, 80 and 59 %. Also, the developed model still showed consistent calibration performance when calibrated with new sensors in different locations. Low-cost sensors combined with ML model not only can improve the calibration performance of benchmark, but also can be applied to the sensor monitoring systems for various epidemiologic investigations and regulatory decisions.

show abstract

Selective Detection of Functionalized Carbon Particles based on Polymer Semiconducting and Conducting Devices as Potential Particulate Matter Sensors

Song,

Chen,

Jiang

et al. 2023

Small

View full text Add to dashboard Cite

This paper reports a new mechanism for particulate matter detection and identification. Three types of carbon particles are synthesized with different functional groups to mimic the real particulates in atmospheric aerosol. After exposing polymer‐based organic devices in organic field effect transistor (OFET) architectures to the particle mist, the sensitivity and selectivity of the detection of different types of particles are shown by the current changes extracted from the transfer curves. The results indicate that the sensitivity of the devices is related to the structure and functional groups of the organic semiconducting layers, as well as the morphology. The predominant response is simulated by a model that yielded values of charge carrier density increase and charge carriers delivered per unit mass of particles. The research points out that polymer semiconductor devices have the ability to selectively detect particles with multiple functional groups, which reveals a future direction for selective detection of particulate matter.

show abstract

Assessment of Low-Cost Particulate Matter Sensor Systems against Optical and Gravimetric Methods in a Field Co-Location in Norway

Cited by 29 publications

References 36 publications

Assessment and Calibration of a Low-Cost PM2.5 Sensor Using Machine Learning (HybridLSTM Neural Network): Feasibility Study to Build an Air Quality Monitoring System

Assessment and Calibration of a Low-Cost PM2.5 Sensor Using Machine Learning (HybridLSTM Neural Network): Feasibility Study to Build an Air Quality Monitoring System

Assessment and Calibration on Low-cost PM2.5 Sensor using Machin Learning (Hybrid-LSTM Neural Network): Feasibility Study to Build Air Quality Monitoring System

Selective Detection of Functionalized Carbon Particles based on Polymer Semiconducting and Conducting Devices as Potential Particulate Matter Sensors

Contact Info

Product

Resources

About