Application of Machine Learning for Calibrating Gas Sensors for Methane Emissions Monitoring
Methane leaks are a significant component of greenhouse gas emissions and a global problem for the oil and gas industry. Emissions occur from a wide variety of sites with no discernable patterns, requiring methodologies to frequently monitor these releases throughout the entire production chain. To...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/24/9898 |
| _version_ | 1797379378621972480 |
|---|---|
| author | Ballard Andrews Aditi Chakrabarti Mathieu Dauphin Andrew Speck |
| author_facet | Ballard Andrews Aditi Chakrabarti Mathieu Dauphin Andrew Speck |
| author_sort | Ballard Andrews |
| collection | DOAJ |
| description | Methane leaks are a significant component of greenhouse gas emissions and a global problem for the oil and gas industry. Emissions occur from a wide variety of sites with no discernable patterns, requiring methodologies to frequently monitor these releases throughout the entire production chain. To cost-effectively monitor widely dispersed well pads, we developed a methane point instrument to be deployed at facilities and connected to a cloud-based interpretation platform that provides real-time continuous monitoring in all weather conditions. The methane sensor is calibrated with machine learning methods of Gaussian process regression and the results are compared with artificial neural networks. A machine learning approach incorporates environmental effects into the sensor response and achieves the accuracies required for methane emissions monitoring with a small number of parameters. The sensors achieve an accuracy of 1 part per million methane (ppm) and can detect leaks at rates of less than 0.6 kg/h. |
| first_indexed | 2024-03-08T20:22:18Z |
| format | Article |
| id | doaj.art-b262fd8db1b74de085508bacec706856 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T20:22:18Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b262fd8db1b74de085508bacec7068562023-12-22T14:41:36ZengMDPI AGSensors1424-82202023-12-012324989810.3390/s23249898Application of Machine Learning for Calibrating Gas Sensors for Methane Emissions MonitoringBallard Andrews0Aditi Chakrabarti1Mathieu Dauphin2Andrew Speck3Schlumberger-Doll Research, Cambridge, MA 02139, USASchlumberger-Doll Research, Cambridge, MA 02139, USASchlumberger-Doll Research, Cambridge, MA 02139, USASchlumberger-Doll Research, Cambridge, MA 02139, USAMethane leaks are a significant component of greenhouse gas emissions and a global problem for the oil and gas industry. Emissions occur from a wide variety of sites with no discernable patterns, requiring methodologies to frequently monitor these releases throughout the entire production chain. To cost-effectively monitor widely dispersed well pads, we developed a methane point instrument to be deployed at facilities and connected to a cloud-based interpretation platform that provides real-time continuous monitoring in all weather conditions. The methane sensor is calibrated with machine learning methods of Gaussian process regression and the results are compared with artificial neural networks. A machine learning approach incorporates environmental effects into the sensor response and achieves the accuracies required for methane emissions monitoring with a small number of parameters. The sensors achieve an accuracy of 1 part per million methane (ppm) and can detect leaks at rates of less than 0.6 kg/h.https://www.mdpi.com/1424-8220/23/24/9898methane emissionsmachine learningGaussian process regressionartificial neural netsMO<sub>X</sub> sensors |
| spellingShingle | Ballard Andrews Aditi Chakrabarti Mathieu Dauphin Andrew Speck Application of Machine Learning for Calibrating Gas Sensors for Methane Emissions Monitoring Sensors methane emissions machine learning Gaussian process regression artificial neural nets MO<sub>X</sub> sensors |
| title | Application of Machine Learning for Calibrating Gas Sensors for Methane Emissions Monitoring |
| title_full | Application of Machine Learning for Calibrating Gas Sensors for Methane Emissions Monitoring |
| title_fullStr | Application of Machine Learning for Calibrating Gas Sensors for Methane Emissions Monitoring |
| title_full_unstemmed | Application of Machine Learning for Calibrating Gas Sensors for Methane Emissions Monitoring |
| title_short | Application of Machine Learning for Calibrating Gas Sensors for Methane Emissions Monitoring |
| title_sort | application of machine learning for calibrating gas sensors for methane emissions monitoring |
| topic | methane emissions machine learning Gaussian process regression artificial neural nets MO<sub>X</sub> sensors |
| url | https://www.mdpi.com/1424-8220/23/24/9898 |
| work_keys_str_mv | AT ballardandrews applicationofmachinelearningforcalibratinggassensorsformethaneemissionsmonitoring AT aditichakrabarti applicationofmachinelearningforcalibratinggassensorsformethaneemissionsmonitoring AT mathieudauphin applicationofmachinelearningforcalibratinggassensorsformethaneemissionsmonitoring AT andrewspeck applicationofmachinelearningforcalibratinggassensorsformethaneemissionsmonitoring |