Decoding methane concentration in Alberta oil sands: A machine learning exploration

Most activities associated with Alberta’s oil sands industry are widely recognized as a serious threat to the environment, particularly the emission of greenhouse gases; the industrial residue that accumulates in oil sands tailings ponds (OSTPs) has the potential to emit large quantities of methane....

Full description

Saved in:
Bibliographic Details
Main Authors: Liubov Sysoeva, Ilhem Bouderbala, Miles H. Kent, Esha Saha, B.A. Zambrano-Luna, Russell Milne, Hao Wang
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Ecological Indicators
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1470160X24012925
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832576523637358592
author Liubov Sysoeva
Ilhem Bouderbala
Miles H. Kent
Esha Saha
B.A. Zambrano-Luna
Russell Milne
Hao Wang
author_facet Liubov Sysoeva
Ilhem Bouderbala
Miles H. Kent
Esha Saha
B.A. Zambrano-Luna
Russell Milne
Hao Wang
author_sort Liubov Sysoeva
collection DOAJ
description Most activities associated with Alberta’s oil sands industry are widely recognized as a serious threat to the environment, particularly the emission of greenhouse gases; the industrial residue that accumulates in oil sands tailings ponds (OSTPs) has the potential to emit large quantities of methane. Mathematical modeling of these emissions, and hence deducing where and why high methane concentrations can be found, is often infeasible due to complex interactions between different sources of methane and lack of availability of appropriate data. Additionally, stationing advanced monitoring devices either inside or in the vicinity of methane emitting sources can be expensive, and may require permits that are hard to obtain. Interpretable machine learning techniques, coupled with existing data from weather monitoring stations, offer a cost-effective alternative approach for modeling and understanding methane emissions sources. We introduce a multi-step framework for finding the primary factors associated with higher methane concentrations, powered by machine learning models (such as random forest) trained on high dimensional datasets sourced from multiple weather monitoring stations located in the Lower Athabasca region. The proposed framework can predict methane concentration levels, illustrate the dependence between the important features and their impact on these levels, and (via the incorporation of wind data) uncover locations of methane sources. We use it to locate such sources in northeastern Alberta. We additionally use Shapley values to find that O3’s relationship with methane concentration is consistently concave, while that of NOX changes from linear increase to a saturation function with increasing distance from OSTPs. This paper serves as a guide for building machine learning-driven models to estimate methane concentration in Alberta’s oil sands, or similar regions with methane-producing extractive industries.
format Article
id doaj-art-0543c880ccdd4d85bd72c9ac933b50cf
institution Kabale University
issn 1470-160X
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Ecological Indicators
spelling doaj-art-0543c880ccdd4d85bd72c9ac933b50cf2025-01-31T05:10:16ZengElsevierEcological Indicators1470-160X2025-01-01170112835Decoding methane concentration in Alberta oil sands: A machine learning explorationLiubov Sysoeva0Ilhem Bouderbala1Miles H. Kent2Esha Saha3B.A. Zambrano-Luna4Russell Milne5Hao Wang6Interdisciplinary Lab for Mathematical Ecology and Epidemiology (ILMEE), University of Alberta, Edmonton (AB), T6G 2J5, Canada; The Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton (AB), T6G 2J5, CanadaInterdisciplinary Lab for Mathematical Ecology and Epidemiology (ILMEE), University of Alberta, Edmonton (AB), T6G 2J5, Canada; The Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton (AB), T6G 2J5, Canada; Département de Biologie, Université Laval, Québec (QC), G1V 0A6, CanadaInterdisciplinary Lab for Mathematical Ecology and Epidemiology (ILMEE), University of Alberta, Edmonton (AB), T6G 2J5, Canada; The Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton (AB), T6G 2J5, CanadaInterdisciplinary Lab for Mathematical Ecology and Epidemiology (ILMEE), University of Alberta, Edmonton (AB), T6G 2J5, Canada; The Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton (AB), T6G 2J5, CanadaInterdisciplinary Lab for Mathematical Ecology and Epidemiology (ILMEE), University of Alberta, Edmonton (AB), T6G 2J5, Canada; The Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton (AB), T6G 2J5, CanadaInterdisciplinary Lab for Mathematical Ecology and Epidemiology (ILMEE), University of Alberta, Edmonton (AB), T6G 2J5, Canada; The Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton (AB), T6G 2J5, Canada; Corresponding authors.Interdisciplinary Lab for Mathematical Ecology and Epidemiology (ILMEE), University of Alberta, Edmonton (AB), T6G 2J5, Canada; The Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton (AB), T6G 2J5, Canada; Corresponding authors.Most activities associated with Alberta’s oil sands industry are widely recognized as a serious threat to the environment, particularly the emission of greenhouse gases; the industrial residue that accumulates in oil sands tailings ponds (OSTPs) has the potential to emit large quantities of methane. Mathematical modeling of these emissions, and hence deducing where and why high methane concentrations can be found, is often infeasible due to complex interactions between different sources of methane and lack of availability of appropriate data. Additionally, stationing advanced monitoring devices either inside or in the vicinity of methane emitting sources can be expensive, and may require permits that are hard to obtain. Interpretable machine learning techniques, coupled with existing data from weather monitoring stations, offer a cost-effective alternative approach for modeling and understanding methane emissions sources. We introduce a multi-step framework for finding the primary factors associated with higher methane concentrations, powered by machine learning models (such as random forest) trained on high dimensional datasets sourced from multiple weather monitoring stations located in the Lower Athabasca region. The proposed framework can predict methane concentration levels, illustrate the dependence between the important features and their impact on these levels, and (via the incorporation of wind data) uncover locations of methane sources. We use it to locate such sources in northeastern Alberta. We additionally use Shapley values to find that O3’s relationship with methane concentration is consistently concave, while that of NOX changes from linear increase to a saturation function with increasing distance from OSTPs. This paper serves as a guide for building machine learning-driven models to estimate methane concentration in Alberta’s oil sands, or similar regions with methane-producing extractive industries.http://www.sciencedirect.com/science/article/pii/S1470160X24012925Greenhouse gas emissionsFeature extractionTailings pondsMethane source detection
spellingShingle Liubov Sysoeva
Ilhem Bouderbala
Miles H. Kent
Esha Saha
B.A. Zambrano-Luna
Russell Milne
Hao Wang
Decoding methane concentration in Alberta oil sands: A machine learning exploration
Ecological Indicators
Greenhouse gas emissions
Feature extraction
Tailings ponds
Methane source detection
title Decoding methane concentration in Alberta oil sands: A machine learning exploration
title_full Decoding methane concentration in Alberta oil sands: A machine learning exploration
title_fullStr Decoding methane concentration in Alberta oil sands: A machine learning exploration
title_full_unstemmed Decoding methane concentration in Alberta oil sands: A machine learning exploration
title_short Decoding methane concentration in Alberta oil sands: A machine learning exploration
title_sort decoding methane concentration in alberta oil sands a machine learning exploration
topic Greenhouse gas emissions
Feature extraction
Tailings ponds
Methane source detection
url http://www.sciencedirect.com/science/article/pii/S1470160X24012925
work_keys_str_mv AT liubovsysoeva decodingmethaneconcentrationinalbertaoilsandsamachinelearningexploration
AT ilhembouderbala decodingmethaneconcentrationinalbertaoilsandsamachinelearningexploration
AT mileshkent decodingmethaneconcentrationinalbertaoilsandsamachinelearningexploration
AT eshasaha decodingmethaneconcentrationinalbertaoilsandsamachinelearningexploration
AT bazambranoluna decodingmethaneconcentrationinalbertaoilsandsamachinelearningexploration
AT russellmilne decodingmethaneconcentrationinalbertaoilsandsamachinelearningexploration
AT haowang decodingmethaneconcentrationinalbertaoilsandsamachinelearningexploration