Comparison of Machine Learning Algorithms for Natural Gas Identification with Mixed Potential Electrochemical Sensor Arrays

Ma, Neal; Halley, Sleight; Ramaiyan, Kannan; Garzon, Fernando; Tsui, Lok-kun

doi:10.1149/2754-2726/acbe0c

Comparison of Machine Learning Algorithms for Natural Gas Identification with Mixed Potential Electrochemical Sensor Arrays

Journal Article · Sun Mar 05 23:00:00 EST 2023 · ECS Sensors Plus

DOI:https://doi.org/10.1149/2754-2726/acbe0c· OSTI ID:1960067

; ; Ramaiyan, Kannan; ;

Mixed-potential electrochemical sensor arrays consisting of indium tin oxide (ITO), La _0.87 Sr _0.13 CrO ₃ , Au, and Pt electrodes can detect the leaks from natural gas infrastructure. Algorithms are needed to correctly identify natural gas sources from background natural and anthropogenic sources such as wetlands or agriculture. We report for the first time a comparison of several machine learning methods for mixture identification in the context of natural gas emissions monitoring by mixed potential sensor arrays. Random Forest, Artificial Neural Network, and Nearest Neighbor methods successfully classified air mixtures containing only CH ₄ , two types of natural gas simulants, and CH ₄ +NH ₃ with >98% identification accuracy. The model complexity of these methods were optimized and the degree of robustness against overfitting was determined. Finally, these methods are benchmarked on both desktop PC and single-board computer hardware to simulate their application in a portable internet-of-things sensor package. The combined results show that the random forest method is the preferred method for mixture identification with its high accuracy (>98%), robustness against overfitting with increasing model complexity, and had less than 10 ms training time and less than 0.1 ms inference time on single-board computer hardware.

View Journal Article

Sponsoring Organization:: USDOE

Grant/Contract Number:: NONE; FE0031864

OSTI ID:: 1960067

Alternate ID(s):: OSTI ID: 1958225
OSTI ID: 1959774

Journal Information:: ECS Sensors Plus, Journal Name: ECS Sensors Plus Journal Issue: 1 Vol. 2; ISSN 2754-2726

Publisher:: The Electrochemical SocietyCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (47)

Machine Learning‐Enabled Smart Gas Sensing Platform for Identification of Industrial Gases Huang, Shirong; Croy, Alexander; Panes-Ruiz, Luis Antonio Advanced Intelligent Systems, Vol. 4, Issue 4 https://doi.org/10.1002/aisy.202200016	journal	March 2022
A cavity ring-down analyzer for measuring atmospheric levels of methane, carbon dioxide, and water vapor Crosson, E.R. Applied Physics B, Vol. 92, Issue 3, p. 403-408 https://doi.org/10.1007/s00340-008-3135-y	journal	August 2008
A comparative analysis of gradient boosting algorithms Bentéjac, Candice; Csörgő, Anna; Martínez-Muñoz, Gonzalo Artificial Intelligence Review, Vol. 54, Issue 3 https://doi.org/10.1007/s10462-020-09896-5	journal	August 2020
A review of mixed-potential type zirconia-based gas sensors Miura, Norio; Sato, Tomoaki; Anggraini, Sri Ayu Ionics, Vol. 20, Issue 7 https://doi.org/10.1007/s11581-014-1140-1	journal	May 2014
Additively manufactured mixed potential electrochemical sensors for NOx, C3H8, and NH3 detection Tsui, Lok-kun; Benavidez, Angelica; Evans, Lindsey Progress in Additive Manufacturing, Vol. 4, Issue 1 https://doi.org/10.1007/s40964-018-0054-2	journal	June 2018
Solid-state mixed potential gas sensors: theory, experiments and challenges Garzon, F. Solid State Ionics, Vol. 136-137, Issue 1-2 https://doi.org/10.1016/S0167-2738(00)00348-9	journal	November 2000
Highly selective CO sensor using stabilized zirconia and a couple of oxide electrodes Miura, Norio; Raisen, Takahisa; Lu, Geyu Sensors and Actuators B: Chemical, Vol. 47, Issue 1-3 https://doi.org/10.1016/S0925-4005(98)00053-7	journal	April 1998
Methane detection on the sub-ppm level with a near-infrared diode laser photoacoustic sensor Zéninari, V.; Parvitte, B.; Courtois, D. Infrared Physics & Technology, Vol. 44, Issue 4 https://doi.org/10.1016/S1350-4495(03)00135-X	journal	August 2003
Air quality assessment system based on self-driven drone and LoRaWAN network Simo, Attila; Dzitac, Simona; Dzitac, Ioan Computer Communications, Vol. 175 https://doi.org/10.1016/j.comcom.2021.04.032	journal	July 2021
Automatic signal decoding and sensor stability of a 3-electrode mixed-potential sensor for NOx/NH3 quantification Tsui, Lok-kun; Benavidez, Angelica; Palanisamy, Ponnusamy Electrochimica Acta, Vol. 283 https://doi.org/10.1016/j.electacta.2018.06.133	journal	September 2018
VideoGasNet: Deep learning for natural gas methane leak classification using an infrared camera Wang, Jingfan; Ji, Jingwei; Ravikumar, Arvind P. Energy, Vol. 238 https://doi.org/10.1016/j.energy.2021.121516	journal	January 2022
Discriminative dimensionality reduction for sensor drift compensation in electronic nose: A robust, low-rank, and sparse representation method Yi, Zhengkun Expert Systems with Applications, Vol. 148 https://doi.org/10.1016/j.eswa.2020.113238	journal	June 2020
Design of a portable optical sensor for methane gas detection Massie, Crawford; Stewart, George; McGregor, George Sensors and Actuators B: Chemical, Vol. 113, Issue 2 https://doi.org/10.1016/j.snb.2005.03.105	journal	February 2006
Design of a novel gas sensor structure based on mid-infrared absorption spectrum Zhang, Yu; Gao, Wenzhu; Song, Zhenyu Sensors and Actuators B: Chemical, Vol. 147, Issue 1 https://doi.org/10.1016/j.snb.2009.11.044	journal	May 2010
Bayesian decoding of the ammonia response of a zirconia-based mixed-potential sensor in the presence of hydrocarbon interference Tsitron, Julia; Kreller, Cortney R.; Sekhar, Praveen K. Sensors and Actuators B: Chemical, Vol. 192 https://doi.org/10.1016/j.snb.2013.10.115	journal	March 2014
Development and testing of an electrochemical methane sensor Sekhar, Praveen K.; Kysar, Jesse; Brosha, Eric L. Sensors and Actuators B: Chemical, Vol. 228 https://doi.org/10.1016/j.snb.2015.12.100	journal	June 2016
Quantitative decoding of the response a ceramic mixed potential sensor array for engine emissions control and diagnostics Tsui, Lok-kun; Benavidez, Angelica; Palanisamy, Ponnusamy Sensors and Actuators B: Chemical, Vol. 249 https://doi.org/10.1016/j.snb.2017.04.060	journal	October 2017
Using sensor arrays to decode NO /NH3/C3H8 gas mixtures for automotive exhaust monitoring Javed, Unab; Ramaiyan, Kannan P.; Kreller, Cortney R. Sensors and Actuators B: Chemical, Vol. 264 https://doi.org/10.1016/j.snb.2018.02.069	journal	July 2018
Classification and Regression of Binary Hydrocarbon Mixtures using Single Metal Oxide Semiconductor Sensor With Application to Natural Gas Detection Barriault, Matthew; Alexander, Isaac; Tasnim, Nishat Sensors and Actuators B: Chemical, Vol. 326 https://doi.org/10.1016/j.snb.2020.129012	journal	January 2021
Near-infrared methane sensor with neural network filtering Tian, Linbo; Sun, Jiachen; Zhang, Sasa Sensors and Actuators B: Chemical, Vol. 354 https://doi.org/10.1016/j.snb.2021.131207	journal	March 2022
A review of zirconia oxygen, NOx, and mixed potential gas sensors – History and current trends Halley, Sleight; Ramaiyan, Kannan Pasupathikovil; Tsui, Lok-kun Sensors and Actuators B: Chemical, Vol. 370 https://doi.org/10.1016/j.snb.2022.132363	journal	November 2022
Finding Hidden Signals in Chemical Sensors Using Deep Learning Cho, Soo-Yeon; Lee, Youhan; Lee, Sangwon Analytical Chemistry, Vol. 92, Issue 9 https://doi.org/10.1021/acs.analchem.0c00137	journal	April 2020
Adaptively Optimized Gas Analysis Model with Deep Learning for Near-Infrared Methane Sensors Sun, Jiachen; Tian, Linbo; Chang, Jun Analytical Chemistry, Vol. 94, Issue 4 https://doi.org/10.1021/acs.analchem.1c05059	journal	January 2022
A National Estimate of Methane Leakage from Pipeline Mains in Natural Gas Local Distribution Systems Weller, Zachary D.; Hamburg, Steven P.; von Fischer, Joseph C. Environmental Science & Technology, Vol. 54, Issue 14 https://doi.org/10.1021/acs.est.0c00437	journal	June 2020
Detection Limits of Optical Gas Imaging for Natural Gas Leak Detection in Realistic Controlled Conditions Zimmerle, Daniel; Vaughn, Timothy; Bell, Clay Environmental Science & Technology, Vol. 54, Issue 18 https://doi.org/10.1021/acs.est.0c01285	journal	August 2020
Methane Emissions from United States Natural Gas Gathering and Processing Marchese, Anthony J.; Vaughn, Timothy L.; Zimmerle, Daniel J. Environmental Science & Technology, Vol. 49, Issue 17 https://doi.org/10.1021/acs.est.5b02275	journal	August 2015
Machine Learning-Assisted Development of Sensitive Electrode Materials for Mixed Potential-Type NO₂ Gas Sensors Wang, Bin; Li, Weijia; Lu, Qi ACS Applied Materials & Interfaces, Vol. 13, Issue 42 https://doi.org/10.1021/acsami.1c14531	journal	October 2021
Machine Learning-Assisted Volatile Organic Compound Gas Classification Based on Polarized Mixed-Potential Gas Sensors Wang, Bin; Zhang, Jianyu; Wang, Tong ACS Applied Materials & Interfaces, Vol. 15, Issue 4 https://doi.org/10.1021/acsami.2c17348	journal	January 2023
Machine learning and computation-enabled intelligent sensor design Ballard, Zachary; Brown, Calvin; Madni, Asad M. Nature Machine Intelligence, Vol. 3, Issue 7 https://doi.org/10.1038/s42256-021-00360-9	journal	June 2021
Bio-inspired gas sensing: boosting performance with sensor optimization guided by “machine learning” Potyrailo, R. A.; Brewer, J.; Cheng, B. Faraday Discussions, Vol. 223 https://doi.org/10.1039/D0FD00035C	journal	January 2020
Machine learning and chemometrics for electrochemical sensors: moving forward to the future of analytical chemistry Puthongkham, Pumidech; Wirojsaengthong, Supacha; Suea-Ngam, Akkapol The Analyst, Vol. 146, Issue 21 https://doi.org/10.1039/D1AN01148K	journal	January 2021
Waggle: An open sensor platform for edge computing Beckman, Pete; Sankaran, Rajesh; Catlett, Charlie 2016 IEEE SENSORS https://doi.org/10.1109/ICSENS.2016.7808975	conference	October 2016
Nanowire-Based Sensor Array for Detection of Cross-Sensitive Gases Using PCA and Machine Learning Algorithms Khan, Md Ashfaque Hossain; Thomson, Brian; Debnath, Ratan IEEE Sensors Journal, Vol. 20, Issue 11 https://doi.org/10.1109/JSEN.2020.2972542	journal	June 2020
Machine Learning for Optical Gas Sensing: A Leaky-Mode Humidity Sensor as Example Kornienko, Vladimir V.; Nechepurenko, Igor A.; Tananaev, Peter N. IEEE Sensors Journal, Vol. 20, Issue 13 https://doi.org/10.1109/JSEN.2020.2978931	journal	July 2020
Detection and Estimation of Natural Gas Leakage Using UAV by Machine Learning Algorithms Sonkar, Sarvesh Kumar; Kumar, Prashant; George, Riya Catherine IEEE Sensors Journal, Vol. 22, Issue 8 https://doi.org/10.1109/JSEN.2022.3157872	journal	April 2022
The Emergence of Edge Computing Satyanarayanan, Mahadev Computer, Vol. 50, Issue 1 https://doi.org/10.1109/MC.2017.9	journal	January 2017
A Three Electrode Mixed Potential Sensor for Gas Detection and Discrimination Tsui, L. -k.; Benavidez, A. D.; Palanisamy, P. ECS Transactions, Vol. 75, Issue 16 https://doi.org/10.1149/07516.0009ecst	journal	August 2016
A Mixed-Potential Sensor Based on a Ce[sub 0.8]Gd[sub 0.2]O[sub 1.9] Electrolyte and Platinum and Gold Electrodes Mukundan, R.; Brosha, E. L.; Brown, D. R. Journal of The Electrochemical Society, Vol. 147, Issue 4 https://doi.org/10.1149/1.1393398	journal	January 2000
Combined Mixed Potential Electrochemical Sensors and Artificial Neural Networks for the Quantificationand Identification of Methane in Natural Gas Emissions Monitoring Halley, Sleight; Tsui, Lok-kun; Garzon, Fernando Journal of The Electrochemical Society, Vol. 168, Issue 9 https://doi.org/10.1149/1945-7111/ac2465	journal	September 2021
Open-path cavity ring-down methane sensor for mobile monitoring of natural gas emissions Mchale, Laura E.; Martinez, Benjamin; Miller, Thomas W. Optics Express, Vol. 27, Issue 14 https://doi.org/10.1364/OE.27.020084	journal	January 2019
Advanced Leak Detection and Quantification of Methane Emissions Using sUAS Hollenbeck, Derek; Zulevic, Demitrius; Chen, Yangquan Drones, Vol. 5, Issue 4 https://doi.org/10.3390/drones5040117	journal	October 2021
Review on Smart Gas Sensing Technology Feng, Shaobin; Farha, Fadi; Li, Qingjuan Sensors, Vol. 19, Issue 17 https://doi.org/10.3390/s19173760	journal	August 2019
Cavity Ring-Down Methane Sensor for Small Unmanned Aerial Systems Martinez, Benjamin; Miller, Thomas W.; Yalin, Azer P. Sensors, Vol. 20, Issue 2 https://doi.org/10.3390/s20020454	journal	January 2020
Capacitive and Infrared Gas Sensors for the Assessment of the Methane Number of LNG Fuels Sweelssen, Jörgen; Blokland, Huib; Rajamäki, Timo Sensors, Vol. 20, Issue 12 https://doi.org/10.3390/s20123345	journal	June 2020
Semiconductor Gas Sensors: Materials, Technology, Design, and Application Nikolic, Maria Vesna; Milovanovic, Vladimir; Vasiljevic, Zorka Z. Sensors, Vol. 20, Issue 22 https://doi.org/10.3390/s20226694	journal	November 2020
Chemical Gas Sensors: Recent Developments, Challenges, and the Potential of Machine Learning—A Review Yaqoob, Usman; Younis, Mohammad I. Sensors, Vol. 21, Issue 8 https://doi.org/10.3390/s21082877	journal	April 2021
A Systematic Literature Review on Distributed Machine Learning in Edge Computing Filho, Carlos Poncinelli; Marques, Elias; Chang, Victor Sensors, Vol. 22, Issue 7 https://doi.org/10.3390/s22072665	journal	March 2022

Similar Records

Combined Mixed Potential Electrochemical Sensors and Artificial Neural Networks for the Quantificationand Identification of Methane in Natural Gas Emissions Monitoring

Journal Article · Thu Sep 16 00:00:00 EDT 2021 · Journal of the Electrochemical Society · OSTI ID:1835397

Comparison of Machine Learning Algorithms for Natural Gas Identification with Mixed Potential Electrochemical Sensor Arrays

Citation Formats

References (47)

Similar Records

Related Subjects