Search
Nitrogen Dioxide Monitoring by Means of Low-Cost Autono-mous Platform and Sensor Calibration via Machine Learning with Global Data Correlation Enhancement
Abstract
Air quality significantly impacts the environment and human living conditions, with di-rect and indirect effects on the economy. Precise and prompt detection of air pollutants is crucial for mitigating risks and implementing strategies to control pollution within ac-ceptable thresholds. One of the common pollutants is nitrogen dioxide (NO2), high con-centration of which are detrimental to the human respiratory system and may lead to se-rious lung diseases. Unfortunately, reliable NO2 detection requires sophisticated and expensive apparatus. Although cheap sensors are now widespread, they lack accuracy and stability, and are highly sensitive to environmental conditions. The purpose of this study is to propose a novel approach to precise calibration of the low-cost NO2 sensors. It is illustrated using a custom-developed autonomous platform cost-efficient NO2 moni-toring. The platform utilizes various sensors alongside electronic circuitry, control and communication units, and drivers. The calibration strategy leverages comprehensive data from multiple reference stations, employing neural network (NN) and kriging interpola-tion metamodels. These models are built using diverse environmental parameters (tem-perature, pressure, humidity) and cross-referenced data gathered by surplus NO2 sensors. Instead of providing direct outputs of the calibrated sensor, our approach relies on pre-dicting affine correction coefficients, which increase flexibility of the correction process. Additionally, a calibration stage incorporating global correlation enhancement is devel-oped and applied. Demonstrative experiments extensively validate this approach, af-firming the platform and calibration methodology's practicality for reliable and cost-effective NO2 monitoring, especially keeping in mind that the predictive power of the enhanced sensor (correlation coefficient nearing 0.9 against reference data, RMSE < 3.5 µg/m3) is close to that of expensive reference equipment.
Citations
-
0
CrossRef
-
0
Web of Science
-
0
Scopus
Authors (4)
Cite as
Full text
- Publication version
- Accepted or Published Version
- DOI:
- Digital Object Identifier (open in new tab) 10.3390/s25082352
- License
-
open in new tab
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
SENSORS
no. 25,
ISSN: 1424-8220 - Language:
- English
- Publication year:
- 2025
- Bibliographic description:
- Kozieł S., Pietrenko-Dąbrowska A., Wójcikowski M., Pankiewicz B.: Nitrogen Dioxide Monitoring by Means of Low-Cost Autono-mous Platform and Sensor Calibration via Machine Learning with Global Data Correlation Enhancement// SENSORS -Vol. 25,iss. 8 (2025), s.1-28
- DOI:
- Digital Object Identifier (open in new tab) 10.3390/s25082352
- Sources of funding:
-
- Free publication
- Verified by:
- Gdańsk University of Technology
seen 0 times