Machine Learning to Predict Area Fugitive Emission Fluxes of GHGs from Open-Pit Mines
Greenhouse gas (GHG) emissions from open-pit mines pose a global climate challenge, which necessitates appropriate quantification to support effective mitigation measures. This study considers the area-fugitive methane advective flux (as a proxy for emission flux) released from a tailings pond and t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/13/2/210 |
| _version_ | 1797482842085654528 |
|---|---|
| author | Seyedahmad Kia Manoj K. Nambiar Jesse Thé Bahram Gharabaghi Amir A. Aliabadi |
| author_facet | Seyedahmad Kia Manoj K. Nambiar Jesse Thé Bahram Gharabaghi Amir A. Aliabadi |
| author_sort | Seyedahmad Kia |
| collection | DOAJ |
| description | Greenhouse gas (GHG) emissions from open-pit mines pose a global climate challenge, which necessitates appropriate quantification to support effective mitigation measures. This study considers the area-fugitive methane advective flux (as a proxy for emission flux) released from a tailings pond and two open-pit mines, denominated “old” and “new”, within a facility in northern Canada. To estimate the emission fluxes of methane from these sources, this research employed near-surface observations and modeling using the weather research and forecasting (WRF) passive tracer dispersion method. Various machine learning (ML) methods were trained and tested on these data for the operational forecasting of emissions. Predicted emission fluxes and meteorological variables from the WRF model were used as training and input datasets for ML algorithms. A series of 10 ML algorithms were evaluated. The four models that generated the most accurate forecasts were selected. These ML models are the multi-layer perception (MLP) artificial neural network, the gradient boosting (GBR), XGBOOST (XGB), and support vector machines (SVM). Overall, the simulations predicted the emission fluxes with R<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mn>2</mn></msup></semantics></math></inline-formula> (-) values higher than 0.8 (-). Considering the bias (Tonnes h<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula>), the ML predicted the emission fluxes within 6.3%, 3.3%, and 0.3% of WRF predictions for the old mine, new mine, and the pond, respectively. |
| first_indexed | 2024-03-09T22:38:18Z |
| format | Article |
| id | doaj.art-0118381116a741e6bffe72f58c8b04fc |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-09T22:38:18Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-0118381116a741e6bffe72f58c8b04fc2023-11-23T18:43:58ZengMDPI AGAtmosphere2073-44332022-01-0113221010.3390/atmos13020210Machine Learning to Predict Area Fugitive Emission Fluxes of GHGs from Open-Pit MinesSeyedahmad Kia0Manoj K. Nambiar1Jesse Thé2Bahram Gharabaghi3Amir A. Aliabadi4School of Engineering, University of Guelph, Guelph, ON N1G 2W1, CanadaSchool of Engineering, University of Guelph, Guelph, ON N1G 2W1, CanadaLakes Environmental, Waterloo, ON N2L 3L3, CanadaSchool of Engineering, University of Guelph, Guelph, ON N1G 2W1, CanadaSchool of Engineering, University of Guelph, Guelph, ON N1G 2W1, CanadaGreenhouse gas (GHG) emissions from open-pit mines pose a global climate challenge, which necessitates appropriate quantification to support effective mitigation measures. This study considers the area-fugitive methane advective flux (as a proxy for emission flux) released from a tailings pond and two open-pit mines, denominated “old” and “new”, within a facility in northern Canada. To estimate the emission fluxes of methane from these sources, this research employed near-surface observations and modeling using the weather research and forecasting (WRF) passive tracer dispersion method. Various machine learning (ML) methods were trained and tested on these data for the operational forecasting of emissions. Predicted emission fluxes and meteorological variables from the WRF model were used as training and input datasets for ML algorithms. A series of 10 ML algorithms were evaluated. The four models that generated the most accurate forecasts were selected. These ML models are the multi-layer perception (MLP) artificial neural network, the gradient boosting (GBR), XGBOOST (XGB), and support vector machines (SVM). Overall, the simulations predicted the emission fluxes with R<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mn>2</mn></msup></semantics></math></inline-formula> (-) values higher than 0.8 (-). Considering the bias (Tonnes h<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula>), the ML predicted the emission fluxes within 6.3%, 3.3%, and 0.3% of WRF predictions for the old mine, new mine, and the pond, respectively.https://www.mdpi.com/2073-4433/13/2/210emission fluxmachine learning (ML) methodopen-pit minesweather research and forecasting (WRF) |
| spellingShingle | Seyedahmad Kia Manoj K. Nambiar Jesse Thé Bahram Gharabaghi Amir A. Aliabadi Machine Learning to Predict Area Fugitive Emission Fluxes of GHGs from Open-Pit Mines Atmosphere emission flux machine learning (ML) method open-pit mines weather research and forecasting (WRF) |
| title | Machine Learning to Predict Area Fugitive Emission Fluxes of GHGs from Open-Pit Mines |
| title_full | Machine Learning to Predict Area Fugitive Emission Fluxes of GHGs from Open-Pit Mines |
| title_fullStr | Machine Learning to Predict Area Fugitive Emission Fluxes of GHGs from Open-Pit Mines |
| title_full_unstemmed | Machine Learning to Predict Area Fugitive Emission Fluxes of GHGs from Open-Pit Mines |
| title_short | Machine Learning to Predict Area Fugitive Emission Fluxes of GHGs from Open-Pit Mines |
| title_sort | machine learning to predict area fugitive emission fluxes of ghgs from open pit mines |
| topic | emission flux machine learning (ML) method open-pit mines weather research and forecasting (WRF) |
| url | https://www.mdpi.com/2073-4433/13/2/210 |
| work_keys_str_mv | AT seyedahmadkia machinelearningtopredictareafugitiveemissionfluxesofghgsfromopenpitmines AT manojknambiar machinelearningtopredictareafugitiveemissionfluxesofghgsfromopenpitmines AT jessethe machinelearningtopredictareafugitiveemissionfluxesofghgsfromopenpitmines AT bahramgharabaghi machinelearningtopredictareafugitiveemissionfluxesofghgsfromopenpitmines AT amiraaliabadi machinelearningtopredictareafugitiveemissionfluxesofghgsfromopenpitmines |