Semantic segmentation of methane plumes with hyperspectral machine learning models
Methane is the second most important greenhouse gas contributor to climate change; at the same time its reduction has been denoted as one of the fastest pathways to preventing temperature growth due to its short atmospheric lifetime. In particular, the mitigation of active point-sources associated w...
| Main Authors: | , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Springer Nature
2023
|
| _version_ | 1826311670679470080 |
|---|---|
| author | Růžička, V Mateo-Garcia, G Gómez-Chova, L Vaughan, A Guanter, L Markham, A |
| author_facet | Růžička, V Mateo-Garcia, G Gómez-Chova, L Vaughan, A Guanter, L Markham, A |
| author_sort | Růžička, V |
| collection | OXFORD |
| description | Methane is the second most important greenhouse gas contributor to climate change; at the same time its reduction has been denoted as one of the fastest pathways to preventing temperature growth due to its short atmospheric lifetime. In particular, the mitigation of active point-sources associated with the fossil fuel industry has a strong and cost-effective mitigation potential. Detection of methane plumes in remote sensing data is possible, but the existing approaches exhibit high false positive rates and need manual intervention. Machine learning research in this area is limited due to the lack of large real-world annotated datasets. In this work, we are publicly releasing a machine learning ready dataset with manually refined annotation of methane plumes. We present labelled hyperspectral data from the AVIRIS-NG sensor and provide simulated multispectral WorldView-3 views of the same data to allow for model benchmarking across hyperspectral and multispectral sensors. We propose sensor agnostic machine learning architectures, using classical methane enhancement products as input features. Our HyperSTARCOP model outperforms strong matched filter baseline by over 25% in F1 score, while reducing its false positive rate per classified tile by over 41.83%. Additionally, we demonstrate zero-shot generalisation of our trained model on data from the EMIT hyperspectral instrument, despite the differences in the spectral and spatial resolution between the two sensors: in an annotated subset of EMIT images HyperSTARCOP achieves a 40% gain in F1 score over the baseline. |
| first_indexed | 2024-03-07T08:13:10Z |
| format | Journal article |
| id | oxford-uuid:ca5cd06c-9d04-402a-aa08-57d4d85c19ff |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:13:10Z |
| publishDate | 2023 |
| publisher | Springer Nature |
| record_format | dspace |
| spelling | oxford-uuid:ca5cd06c-9d04-402a-aa08-57d4d85c19ff2023-12-05T12:24:03ZSemantic segmentation of methane plumes with hyperspectral machine learning modelsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:ca5cd06c-9d04-402a-aa08-57d4d85c19ffEnglishSymplectic ElementsSpringer Nature2023Růžička, VMateo-Garcia, GGómez-Chova, LVaughan, AGuanter, LMarkham, AMethane is the second most important greenhouse gas contributor to climate change; at the same time its reduction has been denoted as one of the fastest pathways to preventing temperature growth due to its short atmospheric lifetime. In particular, the mitigation of active point-sources associated with the fossil fuel industry has a strong and cost-effective mitigation potential. Detection of methane plumes in remote sensing data is possible, but the existing approaches exhibit high false positive rates and need manual intervention. Machine learning research in this area is limited due to the lack of large real-world annotated datasets. In this work, we are publicly releasing a machine learning ready dataset with manually refined annotation of methane plumes. We present labelled hyperspectral data from the AVIRIS-NG sensor and provide simulated multispectral WorldView-3 views of the same data to allow for model benchmarking across hyperspectral and multispectral sensors. We propose sensor agnostic machine learning architectures, using classical methane enhancement products as input features. Our HyperSTARCOP model outperforms strong matched filter baseline by over 25% in F1 score, while reducing its false positive rate per classified tile by over 41.83%. Additionally, we demonstrate zero-shot generalisation of our trained model on data from the EMIT hyperspectral instrument, despite the differences in the spectral and spatial resolution between the two sensors: in an annotated subset of EMIT images HyperSTARCOP achieves a 40% gain in F1 score over the baseline. |
| spellingShingle | Růžička, V Mateo-Garcia, G Gómez-Chova, L Vaughan, A Guanter, L Markham, A Semantic segmentation of methane plumes with hyperspectral machine learning models |
| title | Semantic segmentation of methane plumes with hyperspectral machine learning models |
| title_full | Semantic segmentation of methane plumes with hyperspectral machine learning models |
| title_fullStr | Semantic segmentation of methane plumes with hyperspectral machine learning models |
| title_full_unstemmed | Semantic segmentation of methane plumes with hyperspectral machine learning models |
| title_short | Semantic segmentation of methane plumes with hyperspectral machine learning models |
| title_sort | semantic segmentation of methane plumes with hyperspectral machine learning models |
| work_keys_str_mv | AT ruzickav semanticsegmentationofmethaneplumeswithhyperspectralmachinelearningmodels AT mateogarciag semanticsegmentationofmethaneplumeswithhyperspectralmachinelearningmodels AT gomezchoval semanticsegmentationofmethaneplumeswithhyperspectralmachinelearningmodels AT vaughana semanticsegmentationofmethaneplumeswithhyperspectralmachinelearningmodels AT guanterl semanticsegmentationofmethaneplumeswithhyperspectralmachinelearningmodels AT markhama semanticsegmentationofmethaneplumeswithhyperspectralmachinelearningmodels |