Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models
The environmental impacts of global warming driven by methane (CH 4 ) emissions have catalyzed significant research initiatives in developing novel technologies that enable proactive and rapid detection of CH 4 . Several data-driven machine learning (ML) models were tested to determine how well they...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2024-02-01
|
| Series: | Environmental Health Insights |
| Online Access: | https://doi.org/10.1177/11786302241227307 |
| _version_ | 1827339481074630656 |
|---|---|
| author | Reek Majumder Jacquan Pollard M Sabbir Salek David Werth Gurcan Comert Adrian Gale Sakib Mahmud Khan Samuel Darko Mashrur Chowdhury |
| author_facet | Reek Majumder Jacquan Pollard M Sabbir Salek David Werth Gurcan Comert Adrian Gale Sakib Mahmud Khan Samuel Darko Mashrur Chowdhury |
| author_sort | Reek Majumder |
| collection | DOAJ |
| description | The environmental impacts of global warming driven by methane (CH 4 ) emissions have catalyzed significant research initiatives in developing novel technologies that enable proactive and rapid detection of CH 4 . Several data-driven machine learning (ML) models were tested to determine how well they identified fugitive CH 4 and its related intensity in the affected areas. Various meteorological characteristics, including wind speed, temperature, pressure, relative humidity, water vapor, and heat flux, were included in the simulation. We used the ensemble learning method to determine the best-performing weighted ensemble ML models built upon several weaker lower-layer ML models to (i) detect the presence of CH 4 as a classification problem and (ii) predict the intensity of CH 4 as a regression problem. The classification model performance for CH 4 detection was evaluated using accuracy, F1 score, Matthew’s Correlation Coefficient (MCC), and the area under the receiver operating characteristic curve (AUC ROC), with the top-performing model being 97.2%, 0.972, 0.945 and 0.995, respectively. The R 2 score was used to evaluate the regression model performance for CH 4 intensity prediction, with the R 2 score of the best-performing model being 0.858. The ML models developed in this study for fugitive CH 4 detection and intensity prediction can be used with fixed environmental sensors deployed on the ground or with sensors mounted on unmanned aerial vehicles (UAVs) for mobile detection. |
| first_indexed | 2024-03-07T20:00:24Z |
| format | Article |
| id | doaj.art-afdb6c6bd09b4b8ba51a72d3bc4ac62e |
| institution | Directory Open Access Journal |
| issn | 1178-6302 |
| language | English |
| last_indexed | 2024-03-07T20:00:24Z |
| publishDate | 2024-02-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Environmental Health Insights |
| spelling | doaj.art-afdb6c6bd09b4b8ba51a72d3bc4ac62e2024-02-28T10:03:23ZengSAGE PublishingEnvironmental Health Insights1178-63022024-02-011810.1177/11786302241227307Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction ModelsReek Majumder0Jacquan Pollard1M Sabbir Salek2David Werth3Gurcan Comert4Adrian Gale5Sakib Mahmud Khan6Samuel Darko7Mashrur Chowdhury8Glenn Department of Civil Engineering, Clemson University, Clemson, SC, USAGlenn Department of Civil Engineering, Clemson University, Clemson, SC, USAGlenn Department of Civil Engineering, Clemson University, Clemson, SC, USASavannah River National Laboratory, Aiken, SC, USAComp. Sci., Phy., and Engineering Department, Benedict College, Columbia, SC, USAComp. Sci., Phy., and Engineering Department, Benedict College, Columbia, SC, USAGlenn Department of Civil Engineering, Clemson University, Clemson, SC, USASchool of Arts and Sciences, Florida Memorial University, Miami Gardens, FL, USAGlenn Department of Civil Engineering, Clemson University, Clemson, SC, USAThe environmental impacts of global warming driven by methane (CH 4 ) emissions have catalyzed significant research initiatives in developing novel technologies that enable proactive and rapid detection of CH 4 . Several data-driven machine learning (ML) models were tested to determine how well they identified fugitive CH 4 and its related intensity in the affected areas. Various meteorological characteristics, including wind speed, temperature, pressure, relative humidity, water vapor, and heat flux, were included in the simulation. We used the ensemble learning method to determine the best-performing weighted ensemble ML models built upon several weaker lower-layer ML models to (i) detect the presence of CH 4 as a classification problem and (ii) predict the intensity of CH 4 as a regression problem. The classification model performance for CH 4 detection was evaluated using accuracy, F1 score, Matthew’s Correlation Coefficient (MCC), and the area under the receiver operating characteristic curve (AUC ROC), with the top-performing model being 97.2%, 0.972, 0.945 and 0.995, respectively. The R 2 score was used to evaluate the regression model performance for CH 4 intensity prediction, with the R 2 score of the best-performing model being 0.858. The ML models developed in this study for fugitive CH 4 detection and intensity prediction can be used with fixed environmental sensors deployed on the ground or with sensors mounted on unmanned aerial vehicles (UAVs) for mobile detection.https://doi.org/10.1177/11786302241227307 |
| spellingShingle | Reek Majumder Jacquan Pollard M Sabbir Salek David Werth Gurcan Comert Adrian Gale Sakib Mahmud Khan Samuel Darko Mashrur Chowdhury Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models Environmental Health Insights |
| title | Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models |
| title_full | Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models |
| title_fullStr | Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models |
| title_full_unstemmed | Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models |
| title_short | Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models |
| title_sort | development and evaluation of ensemble learning based environmental methane detection and intensity prediction models |
| url | https://doi.org/10.1177/11786302241227307 |
| work_keys_str_mv | AT reekmajumder developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels AT jacquanpollard developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels AT msabbirsalek developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels AT davidwerth developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels AT gurcancomert developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels AT adriangale developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels AT sakibmahmudkhan developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels AT samueldarko developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels AT mashrurchowdhury developmentandevaluationofensemblelearningbasedenvironmentalmethanedetectionandintensitypredictionmodels |