High-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning

With air quality being one target in the sustainable development goals set by the United Nations, accurate monitoring also of indoor air quality is more important than ever. Chemiresistive gas sensors are an inexpensive and promising solution for the monitoring of volatile organic compounds, which a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yannick Robin, Johannes Amann, Tobias Baur, Payman Goodarzi, Caroline Schultealbert, Tizian Schneider, Andreas Schütze
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	volatile organic compounds (VOCs) indoor air quality (IAQ) deep neural networks neural network architecture search temperature-cycled operation (TCO) Meteorology. Climatology QC851-999
Acceso en línea:	https://doaj.org/article/32de8cf28a6340d7a1a1ee0c236072a7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:32de8cf28a6340d7a1a1ee0c236072a7
record_format	dspace
spelling	oai:doaj.org-article:32de8cf28a6340d7a1a1ee0c236072a72021-11-25T16:45:28ZHigh-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning10.3390/atmos121114872073-4433https://doaj.org/article/32de8cf28a6340d7a1a1ee0c236072a72021-11-01T00:00:00Zhttps://www.mdpi.com/2073-4433/12/11/1487https://doaj.org/toc/2073-4433With air quality being one target in the sustainable development goals set by the United Nations, accurate monitoring also of indoor air quality is more important than ever. Chemiresistive gas sensors are an inexpensive and promising solution for the monitoring of volatile organic compounds, which are of high concern indoors. To fully exploit the potential of these sensors, advanced operating modes, calibration, and data evaluation methods are required. This contribution outlines a systematic approach based on dynamic operation (temperature-cycled operation), randomized calibration (Latin hypercube sampling), and the use of advances in deep neural networks originally developed for natural language processing and computer vision, applying this approach to volatile organic compound measurements for indoor air quality monitoring. This paper discusses the pros and cons of deep neural networks for volatile organic compound monitoring in a laboratory environment by comparing the quantification accuracy of state-of-the-art data evaluation methods with a 10-layer deep convolutional neural network (TCOCNN). The overall performance of both methods was compared for complex gas mixtures with several volatile organic compounds, as well as interfering gases and changing ambient humidity in a comprehensive lab evaluation. Furthermore, both were tested under realistic conditions in the field with additional release tests of volatile organic compounds. The results obtained during field testing were compared with analytical measurements, namely the gold standard gas chromatography mass spectrometry analysis based on Tenax sampling, as well as two mobile systems, a gas chromatograph with photo-ionization detection for volatile organic compound monitoring and a gas chromatograph with a reducing compound photometer for the monitoring of hydrogen. The results showed that the TCOCNN outperforms state-of-the-art data evaluation methods, for example for critical pollutants such as formaldehyde, achieving an uncertainty of around 11 ppb even in complex mixtures, and offers a more robust volatile organic compound quantification in a laboratory environment, as well as in real ambient air for most targets.Yannick RobinJohannes AmannTobias BaurPayman GoodarziCaroline SchultealbertTizian SchneiderAndreas SchützeMDPI AGarticlevolatile organic compounds (VOCs)indoor air quality (IAQ)deep neural networksneural network architecture searchtemperature-cycled operation (TCO)Meteorology. ClimatologyQC851-999ENAtmosphere, Vol 12, Iss 1487, p 1487 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	volatile organic compounds (VOCs) indoor air quality (IAQ) deep neural networks neural network architecture search temperature-cycled operation (TCO) Meteorology. Climatology QC851-999
spellingShingle	volatile organic compounds (VOCs) indoor air quality (IAQ) deep neural networks neural network architecture search temperature-cycled operation (TCO) Meteorology. Climatology QC851-999 Yannick Robin Johannes Amann Tobias Baur Payman Goodarzi Caroline Schultealbert Tizian Schneider Andreas Schütze High-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning
description	With air quality being one target in the sustainable development goals set by the United Nations, accurate monitoring also of indoor air quality is more important than ever. Chemiresistive gas sensors are an inexpensive and promising solution for the monitoring of volatile organic compounds, which are of high concern indoors. To fully exploit the potential of these sensors, advanced operating modes, calibration, and data evaluation methods are required. This contribution outlines a systematic approach based on dynamic operation (temperature-cycled operation), randomized calibration (Latin hypercube sampling), and the use of advances in deep neural networks originally developed for natural language processing and computer vision, applying this approach to volatile organic compound measurements for indoor air quality monitoring. This paper discusses the pros and cons of deep neural networks for volatile organic compound monitoring in a laboratory environment by comparing the quantification accuracy of state-of-the-art data evaluation methods with a 10-layer deep convolutional neural network (TCOCNN). The overall performance of both methods was compared for complex gas mixtures with several volatile organic compounds, as well as interfering gases and changing ambient humidity in a comprehensive lab evaluation. Furthermore, both were tested under realistic conditions in the field with additional release tests of volatile organic compounds. The results obtained during field testing were compared with analytical measurements, namely the gold standard gas chromatography mass spectrometry analysis based on Tenax sampling, as well as two mobile systems, a gas chromatograph with photo-ionization detection for volatile organic compound monitoring and a gas chromatograph with a reducing compound photometer for the monitoring of hydrogen. The results showed that the TCOCNN outperforms state-of-the-art data evaluation methods, for example for critical pollutants such as formaldehyde, achieving an uncertainty of around 11 ppb even in complex mixtures, and offers a more robust volatile organic compound quantification in a laboratory environment, as well as in real ambient air for most targets.
format	article
author	Yannick Robin Johannes Amann Tobias Baur Payman Goodarzi Caroline Schultealbert Tizian Schneider Andreas Schütze
author_facet	Yannick Robin Johannes Amann Tobias Baur Payman Goodarzi Caroline Schultealbert Tizian Schneider Andreas Schütze
author_sort	Yannick Robin
title	High-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning
title_short	High-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning
title_full	High-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning
title_fullStr	High-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning
title_full_unstemmed	High-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning
title_sort	high-performance voc quantification for iaq monitoring using advanced sensor systems and deep learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/32de8cf28a6340d7a1a1ee0c236072a7
work_keys_str_mv	AT yannickrobin highperformancevocquantificationforiaqmonitoringusingadvancedsensorsystemsanddeeplearning AT johannesamann highperformancevocquantificationforiaqmonitoringusingadvancedsensorsystemsanddeeplearning AT tobiasbaur highperformancevocquantificationforiaqmonitoringusingadvancedsensorsystemsanddeeplearning AT paymangoodarzi highperformancevocquantificationforiaqmonitoringusingadvancedsensorsystemsanddeeplearning AT carolineschultealbert highperformancevocquantificationforiaqmonitoringusingadvancedsensorsystemsanddeeplearning AT tizianschneider highperformancevocquantificationforiaqmonitoringusingadvancedsensorsystemsanddeeplearning AT andreasschutze highperformancevocquantificationforiaqmonitoringusingadvancedsensorsystemsanddeeplearning
_version_	1718413010352996352

High-Performance VOC Quantification for IAQ Monitoring Using Advanced Sensor Systems and Deep Learning

Ejemplares similares