The potential of low-cost tin-oxide sensors combined with machine learning for estimating atmospheric ch4 variations around background concentration. Martinez, R. R., Santaren, D., Laurent, O., Cropley, F., Mallet, C., Ramonet, M., Caldow, C., Rivier, L., Broquet, G., Bouchet, C., Juery, C., & Ciais, P. Atmosphere, 12(1):1–22, 2021. doi abstract bibtex Continued developments in instrumentation and modeling have driven progress in monitoring methane (CH4 ) emissions at a range of spatial scales. The sites that emit CH4 such as landfills, oil and gas extraction or storage infrastructure, intensive livestock farms account for a large share of global emissions, and need to be monitored on a continuous basis to verify the effectiveness of reductions policies. Low cost sensors are valuable to monitor methane (CH4 ) around such facilities because they can be deployed in a large number to sample atmospheric plumes and retrieve emission rates using dispersion models. Here we present two tests of three different versions of Figaro® TGS tin-oxide sensors for estimating CH4 concentrations variations, at levels similar to current atmospheric values, with a sought accuracy of 0.1 to 0.2 ppm. In the first test, we characterize the variation of the resistance of the tin-oxide semi-conducting sensors to controlled levels of CH4, H2 O and CO in the laboratory, to analyze cross-sensitivities. In the second test, we reconstruct observed CH4 variations in a room, that ranged from 1.9 and 2.4 ppm during a three month experiment from observed time series of resistances and other variables. To do so, a machine learning model is trained against true CH4 recorded by a high precision instrument. The machine-learning model using 30% of the data for training reconstructs CH4 within the target accuracy of 0.1 ppm only if training variables are representative of conditions during the testing period. The model-derived sensitivities of the sensors resistance to H2 O compared to CH4 are larger than those observed under controlled conditions, which deserves further characterization of all the factors influencing the resistance of the sensors.
@article{Martinez2021,
abstract = {Continued developments in instrumentation and modeling have driven progress in monitoring methane (CH4 ) emissions at a range of spatial scales. The sites that emit CH4 such as landfills, oil and gas extraction or storage infrastructure, intensive livestock farms account for a large share of global emissions, and need to be monitored on a continuous basis to verify the effectiveness of reductions policies. Low cost sensors are valuable to monitor methane (CH4 ) around such facilities because they can be deployed in a large number to sample atmospheric plumes and retrieve emission rates using dispersion models. Here we present two tests of three different versions of Figaro{\textregistered} TGS tin-oxide sensors for estimating CH4 concentrations variations, at levels similar to current atmospheric values, with a sought accuracy of 0.1 to 0.2 ppm. In the first test, we characterize the variation of the resistance of the tin-oxide semi-conducting sensors to controlled levels of CH4, H2 O and CO in the laboratory, to analyze cross-sensitivities. In the second test, we reconstruct observed CH4 variations in a room, that ranged from 1.9 and 2.4 ppm during a three month experiment from observed time series of resistances and other variables. To do so, a machine learning model is trained against true CH4 recorded by a high precision instrument. The machine-learning model using 30% of the data for training reconstructs CH4 within the target accuracy of 0.1 ppm only if training variables are representative of conditions during the testing period. The model-derived sensitivities of the sensors resistance to H2 O compared to CH4 are larger than those observed under controlled conditions, which deserves further characterization of all the factors influencing the resistance of the sensors.},
author = {Martinez, Rodrigo Rivera and Santaren, Diego and Laurent, Olivier and Cropley, Ford and Mallet, C{\'{e}}cile and Ramonet, Michel and Caldow, Christopher and Rivier, Leonard and Broquet, Gregoire and Bouchet, Caroline and Juery, Catherine and Ciais, Philippe},
doi = {10.3390/atmos12010107},
file = {:Users/villekasurinen/Downloads/atmosphere-12-00107-v2.pdf:pdf},
issn = {20734433},
journal = {Atmosphere},
keywords = {Artificial neural networks,Calibration,Low-cost sensors,Methane},
number = {1},
pages = {1--22},
title = {{The potential of low-cost tin-oxide sensors combined with machine learning for estimating atmospheric ch4 variations around background concentration}},
volume = {12},
year = {2021}
}
Downloads: 0
{"_id":"dbGNnXftB3yo28y8k","bibbaseid":"martinez-santaren-laurent-cropley-mallet-ramonet-caldow-rivier-etal-thepotentialoflowcosttinoxidesensorscombinedwithmachinelearningforestimatingatmosphericch4variationsaroundbackgroundconcentration-2021","author_short":["Martinez, R. R.","Santaren, D.","Laurent, O.","Cropley, F.","Mallet, C.","Ramonet, M.","Caldow, C.","Rivier, L.","Broquet, G.","Bouchet, C.","Juery, C.","Ciais, P."],"bibdata":{"bibtype":"article","type":"article","abstract":"Continued developments in instrumentation and modeling have driven progress in monitoring methane (CH4 ) emissions at a range of spatial scales. The sites that emit CH4 such as landfills, oil and gas extraction or storage infrastructure, intensive livestock farms account for a large share of global emissions, and need to be monitored on a continuous basis to verify the effectiveness of reductions policies. Low cost sensors are valuable to monitor methane (CH4 ) around such facilities because they can be deployed in a large number to sample atmospheric plumes and retrieve emission rates using dispersion models. Here we present two tests of three different versions of Figaro® TGS tin-oxide sensors for estimating CH4 concentrations variations, at levels similar to current atmospheric values, with a sought accuracy of 0.1 to 0.2 ppm. In the first test, we characterize the variation of the resistance of the tin-oxide semi-conducting sensors to controlled levels of CH4, H2 O and CO in the laboratory, to analyze cross-sensitivities. In the second test, we reconstruct observed CH4 variations in a room, that ranged from 1.9 and 2.4 ppm during a three month experiment from observed time series of resistances and other variables. To do so, a machine learning model is trained against true CH4 recorded by a high precision instrument. The machine-learning model using 30% of the data for training reconstructs CH4 within the target accuracy of 0.1 ppm only if training variables are representative of conditions during the testing period. The model-derived sensitivities of the sensors resistance to H2 O compared to CH4 are larger than those observed under controlled conditions, which deserves further characterization of all the factors influencing the resistance of the sensors.","author":[{"propositions":[],"lastnames":["Martinez"],"firstnames":["Rodrigo","Rivera"],"suffixes":[]},{"propositions":[],"lastnames":["Santaren"],"firstnames":["Diego"],"suffixes":[]},{"propositions":[],"lastnames":["Laurent"],"firstnames":["Olivier"],"suffixes":[]},{"propositions":[],"lastnames":["Cropley"],"firstnames":["Ford"],"suffixes":[]},{"propositions":[],"lastnames":["Mallet"],"firstnames":["Cécile"],"suffixes":[]},{"propositions":[],"lastnames":["Ramonet"],"firstnames":["Michel"],"suffixes":[]},{"propositions":[],"lastnames":["Caldow"],"firstnames":["Christopher"],"suffixes":[]},{"propositions":[],"lastnames":["Rivier"],"firstnames":["Leonard"],"suffixes":[]},{"propositions":[],"lastnames":["Broquet"],"firstnames":["Gregoire"],"suffixes":[]},{"propositions":[],"lastnames":["Bouchet"],"firstnames":["Caroline"],"suffixes":[]},{"propositions":[],"lastnames":["Juery"],"firstnames":["Catherine"],"suffixes":[]},{"propositions":[],"lastnames":["Ciais"],"firstnames":["Philippe"],"suffixes":[]}],"doi":"10.3390/atmos12010107","file":":Users/villekasurinen/Downloads/atmosphere-12-00107-v2.pdf:pdf","issn":"20734433","journal":"Atmosphere","keywords":"Artificial neural networks,Calibration,Low-cost sensors,Methane","number":"1","pages":"1–22","title":"The potential of low-cost tin-oxide sensors combined with machine learning for estimating atmospheric ch4 variations around background concentration","volume":"12","year":"2021","bibtex":"@article{Martinez2021,\nabstract = {Continued developments in instrumentation and modeling have driven progress in monitoring methane (CH4 ) emissions at a range of spatial scales. The sites that emit CH4 such as landfills, oil and gas extraction or storage infrastructure, intensive livestock farms account for a large share of global emissions, and need to be monitored on a continuous basis to verify the effectiveness of reductions policies. Low cost sensors are valuable to monitor methane (CH4 ) around such facilities because they can be deployed in a large number to sample atmospheric plumes and retrieve emission rates using dispersion models. Here we present two tests of three different versions of Figaro{\\textregistered} TGS tin-oxide sensors for estimating CH4 concentrations variations, at levels similar to current atmospheric values, with a sought accuracy of 0.1 to 0.2 ppm. In the first test, we characterize the variation of the resistance of the tin-oxide semi-conducting sensors to controlled levels of CH4, H2 O and CO in the laboratory, to analyze cross-sensitivities. In the second test, we reconstruct observed CH4 variations in a room, that ranged from 1.9 and 2.4 ppm during a three month experiment from observed time series of resistances and other variables. To do so, a machine learning model is trained against true CH4 recorded by a high precision instrument. The machine-learning model using 30% of the data for training reconstructs CH4 within the target accuracy of 0.1 ppm only if training variables are representative of conditions during the testing period. The model-derived sensitivities of the sensors resistance to H2 O compared to CH4 are larger than those observed under controlled conditions, which deserves further characterization of all the factors influencing the resistance of the sensors.},\nauthor = {Martinez, Rodrigo Rivera and Santaren, Diego and Laurent, Olivier and Cropley, Ford and Mallet, C{\\'{e}}cile and Ramonet, Michel and Caldow, Christopher and Rivier, Leonard and Broquet, Gregoire and Bouchet, Caroline and Juery, Catherine and Ciais, Philippe},\ndoi = {10.3390/atmos12010107},\nfile = {:Users/villekasurinen/Downloads/atmosphere-12-00107-v2.pdf:pdf},\nissn = {20734433},\njournal = {Atmosphere},\nkeywords = {Artificial neural networks,Calibration,Low-cost sensors,Methane},\nnumber = {1},\npages = {1--22},\ntitle = {{The potential of low-cost tin-oxide sensors combined with machine learning for estimating atmospheric ch4 variations around background concentration}},\nvolume = {12},\nyear = {2021}\n}\n\n","author_short":["Martinez, R. R.","Santaren, D.","Laurent, O.","Cropley, F.","Mallet, C.","Ramonet, M.","Caldow, C.","Rivier, L.","Broquet, G.","Bouchet, C.","Juery, C.","Ciais, P."],"key":"Martinez2021","id":"Martinez2021","bibbaseid":"martinez-santaren-laurent-cropley-mallet-ramonet-caldow-rivier-etal-thepotentialoflowcosttinoxidesensorscombinedwithmachinelearningforestimatingatmosphericch4variationsaroundbackgroundconcentration-2021","role":"author","urls":{},"keyword":["Artificial neural networks","Calibration","Low-cost sensors","Methane"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/TLd3uikK9J7eo5bBg","dataSources":["7X9iNW8s2TZStjYhZ","WQfw4bbzH25i62GQc"],"keywords":["artificial neural networks","calibration","low-cost sensors","methane"],"search_terms":["potential","low","cost","tin","oxide","sensors","combined","machine","learning","estimating","atmospheric","ch4","variations","around","background","concentration","martinez","santaren","laurent","cropley","mallet","ramonet","caldow","rivier","broquet","bouchet","juery","ciais"],"title":"The potential of low-cost tin-oxide sensors combined with machine learning for estimating atmospheric ch4 variations around background concentration","year":2021}