Version 1
: Received: 27 October 2024 / Approved: 28 October 2024 / Online: 28 October 2024 (11:06:00 CET)
How to cite:
Ahmed, M.; Kong, J.; Jiang, N.; Duc, H. N.; Puppala, P.; Azzi, M.; Riley, M.; Barthelemy, X. A Bayesian-Optimized Surrogate Model Integrating Deep Learning Algorithms for Correcting PurpleAir Sensor Measurements. Preprints2024, 2024102105. https://doi.org/10.20944/preprints202410.2105.v1
Ahmed, M.; Kong, J.; Jiang, N.; Duc, H. N.; Puppala, P.; Azzi, M.; Riley, M.; Barthelemy, X. A Bayesian-Optimized Surrogate Model Integrating Deep Learning Algorithms for Correcting PurpleAir Sensor Measurements. Preprints 2024, 2024102105. https://doi.org/10.20944/preprints202410.2105.v1
Ahmed, M.; Kong, J.; Jiang, N.; Duc, H. N.; Puppala, P.; Azzi, M.; Riley, M.; Barthelemy, X. A Bayesian-Optimized Surrogate Model Integrating Deep Learning Algorithms for Correcting PurpleAir Sensor Measurements. Preprints2024, 2024102105. https://doi.org/10.20944/preprints202410.2105.v1
APA Style
Ahmed, M., Kong, J., Jiang, N., Duc, H. N., Puppala, P., Azzi, M., Riley, M., & Barthelemy, X. (2024). A Bayesian-Optimized Surrogate Model Integrating Deep Learning Algorithms for Correcting PurpleAir Sensor Measurements. Preprints. https://doi.org/10.20944/preprints202410.2105.v1
Chicago/Turabian Style
Ahmed, M., Matthew Riley and Xavier Barthelemy. 2024 "A Bayesian-Optimized Surrogate Model Integrating Deep Learning Algorithms for Correcting PurpleAir Sensor Measurements" Preprints. https://doi.org/10.20944/preprints202410.2105.v1
Abstract
Low-cost sensors are widely used for air quality monitoring due to their affordability, portability and easy maintenance. However, the performance of such sensors, such as PurpleAir Sensors (PAS), is often affected by changes in environmental (e.g., temperature and humidity) or emission conditions, and hence the resulting measurements require corrections to ensure accuracy and validity. Traditional correction methods, like those developed by the US-EPA, have limitations, particularly for applications to geographically diverse settings and sensors with no collocated referenced monitoring stations available. This study introduces BaySurcls, a Bayesian-optimised surrogate model integrating deep learning (DL) algorithms to improve the PurpleAir sensors PM2.5 (PAS2.5) measurement accuracy. The framework incorporates environmental variables such as humidity and temperature alongside aerosol characteristics, to refine sensor readings. The BaySurcls model corrects the PAS2.5 data for both collocated and non-collocated monitoring scenarios. A case study showed that BaySurcls outperforms all tested standalone models (DL or classical machine learning based) and the US-EPA correction method in terms of reducing root mean square errors in PAS2.5 data and enhancing correlations with the reference data, under both the collocation and non-collocation monitoring scenarios. This improvement is evident across multiple locations in New South Wales, Australia, demonstrating the model's adaptability. The findings confirm BaySurcls as a promising solution for improving the reliability of low-cost sensor data, thus facilitating its valid use in air quality research, impact assessment, and environmental management.
Keywords
Machine Learning (ML); Deep Learning (DL); BaySurcls; PurpleAir Sensor (PAS); PM2.5 Pollution; Data Correction
Subject
Environmental and Earth Sciences, Pollution
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
